{"@context":"https://w3id.org/ro/crate/1.1/context","@type":"Dataset","id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","name":"Hypothesis-Generating Brief: Brain age MRI — full paper","doi":"10.17605/OSF.IO/UMA4R","doi_status":"minted","osf_url":"https://osf.io/uma4r/","dw_chain_url":"https://provenance.researka.org/artifacts/claim_061b96f2bc7c4bd7/chain","content_hash":"sha256:d594d5a107fd43f8a65fc7f3d86ad5496bdf3c9fba839084863cd586d82bfcfb","provenance_passport":{"publication_id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","submission_id":"ec4bea49-cb4b-472a-9590-eef4dc09f7a9","artifact_type":"research_paper","decision":"accept","content_hash":"sha256:d594d5a107fd43f8a65fc7f3d86ad5496bdf3c9fba839084863cd586d82bfcfb","persistent_identifiers":{"doi":"10.17605/OSF.IO/UMA4R","osf_url":"https://osf.io/uma4r/","orcid":null,"ror_id":null,"raid_id":null},"persistent_identifier_status":{"doi":"supplied","osf_url":"supplied","orcid":"not_supplied","ror_id":"not_supplied","raid_id":"not_supplied"},"institution":{"name":null,"ror_id":null,"status":"not_supplied"},"integrity":{"recommendation":"unavailable","available":false,"matched_publication_id":null,"duplication_score":null,"similarity_score":null,"plagiarism_flag":false,"matched_sources":[],"breakdown":{},"feedback_for_agent":null,"status":"unavailable"},"provenance":{"dw_artifact_id":"claim_061b96f2bc7c4bd7","dw_chain_url":"https://provenance.researka.org/artifacts/claim_061b96f2bc7c4bd7/chain"},"timeline":["submission_intake","autonomous_review","autonomous_editorial_decision","autonomous_publish"]},"publication":{"id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","object_type":"publication","parent_object_id":"ec4bea49-cb4b-472a-9590-eef4dc09f7a9","title":"Hypothesis-Generating Brief: Brain age MRI — full paper","body_markdown":"# Hypothesis-Generating Brief: Brain age MRI — full paper\n\n## Abstract\n\nEvidence-honesty note: 63/65 retained sources are coded as null or no extracted directional signal; this corpus is non-supportive for clinical efficacy claims and hypothesis-generating only. Source-bundle reconciliation note: Directional coding is conservative claim-level coding from extracted claim records, not a statement that the source texts contain no directional findings; source-level positive, negative, or unclear findings should be interpreted through the coded outcome class, directness, and claim-count fields. 64/65 retained sources are indirect, review-level, adjacent, or mechanistic and are used only to bound interpretation. The conclusion therefore does not support broad causal, clinical, or policy claims.\n\nThis paper synthesizes evidence on Brain age MRI across 65 accepted source papers and 1135 high-confidence extracted claims.\n\nThe evidence profile contains 1 direct clinical source, 64 adjacent clinical sources, and no sources classified primarily as mechanistic or model-system evidence, with 66 cross-study disagreements across the evidence base.\n\nPositive study-level signals are summarized in the cardiometabolic outcome class, null signals in the contextual adjacent evidence, safety and comorbidity, cardiometabolic outcome classes, and negative signals in no dominant outcome class. The paper therefore interprets the corpus as a tiered evidence profile rather than as a single pooled effect.\n\nThe conclusion is that Brain age MRI remains a bounded geroscience case: the retained clinical and adjacent evidence profile defines the scope for targeted testing, while mixed and null findings limit any unqualified anti-aging claim.\n\n## Methods\n\nRisk-of-bias appraisal summary: The public appraisal artifact reports 65 source-level rating row(s) using ROBINS-I, RoB-2, SYRCLE; overall ratings are some concerns=65. These ratings summarize preliminary source-level appraisal and do not upgrade indirect or adjacent evidence into direct clinical proof.\n\n### Review type and protocol\nThis manuscript is reported as a Evidence brief. A deterministic protocol governed source retrieval, screening, extraction, and synthesis; the protocol was frozen before manuscript rendering. The full audit trail is in the supplementary `methods_pack.json` and the timestamped submission directory `synthesis-brain_age_mri-v06-DAILY-2026-06-21T15-19-07Z-R2`.\n\n### Information sources\nSources were retrieved across PubMed, Europe PMC, OpenAlex, Semantic Scholar, Crossref, DOAJ, OpenAIRE, PMC OAI, bioRxiv, medRxiv, arXiv, and ClinicalTrials.gov. Retrieval window: 2026-06-21.\n\n### Search strategy\nThe following topic-anchored queries were executed against the information sources listed above:\n\n- `brain age MRI AND aging AND human`\n- `brain age MRI AND older adults`\n- `brain age MRI AND randomized controlled trial`\n- `brain age AND aging AND human`\n- `brain age AND older adults`\n- `brain age AND randomized controlled trial`\n- `MRI brain age AND aging AND human`\n- `MRI brain age AND older adults`\n- `MRI brain age AND randomized controlled trial`\n- `neuroimaging aging AND aging AND human`\n\n### Eligibility criteria\n- Sources whose primary content addresses brain age mri.\n- Sources with extractable quantitative or qualitative findings.\n- Peer-reviewed primary research, systematic reviews, or meta-analyses; preprints accepted only when source-traceable.\n- Sources with verifiable bibliographic identifiers (DOI / PMID / canonical handle).\n\n### Selection of sources of evidence\nThe synthesis did not begin from an unfiltered database export. It began from a pre-curated receipt-candidate set generated by the retrieval and claim-binding pipeline. Of 467 records in the receipt-candidate union, 181 were classified as source candidates and 65 were admitted as traceable synthesis sources. Mixed partial-or-none and partial-only rows are separate claim-binding audit buckets, not additive exclusion totals. No additional records were excluded after final source admission.\n\n### source admission funnel\n\n| Admission bucket | n |\n|---|---:|\n| Receipt candidate union | 467 |\n| Classified source candidates | 181 |\n| No extractable claims | 41 |\n| None-only claim binding | 18 |\n| Mixed partial-or-none claim-binding candidates | 182 |\n| Partial-only claim-binding candidates | 32 |\n| Strict high-confidence sources | 13 |\n| Admitted final sources | 65 |\n\n### Exclusion reasons\n- No records were excluded at the gates instrumented for this run: the eligibility criteria above were applied during retrieval and claim-binding but produced no post-screening exclusions with recorded counts for this corpus.\n\n### Data items\nThe following fields were extracted from each included source: study design, population / cohort, intervention or exposure, comparator, outcome class, effect direction, effect size, confidence interval or credible interval, p-value, sample size, follow-up duration, risk-of-bias rating. Under the calibration rule, source verification in the public bundle is limited to reference-level metadata; exact statistics and effect directions are drawn from these structured extraction artifacts (the synthesis manifest, risk-of-bias sidecar when populated, and claim registry) rather than from re-parsed full text.\n\n### Risk-of-bias appraisal\nRisk-of-bias framework assignment follows study design (RoB-2 for RCTs, ROBINS-I for non-randomised studies, AMSTAR-2 for systematic reviews / meta-analyses). Public appraisal claims are limited to populated `risk_of_bias.json` rows; when no populated ratings are present, interpretation remains bounded by source tier and directness rather than formal RoB certification.\n\n### Synthesis approach\nEvidence-tension synthesis: claims grouped by outcome class (cardiometabolic, cognitive, contextual adjacent evidence, frailty, immune and inflammation, muscle function, safety and comorbidity); within-class agreement, disagreement, and directness gaps surfaced explicitly. Quantitative pooling applied only where ≥3 sources reported a comparable endpoint with extractable effect estimates.\n\n### AI-use disclosure\nSource retrieval, claim extraction, evidence routing, and prose drafting were assisted by large language models under a deterministic audit-trail protocol. Every manuscript claim is traceable to a source record in the supplementary `manifest.json`. Final eligibility and interpretation decisions are author-verified.\n\n### Accountability\nAccountability is established through reproducible artifacts: a deterministic protocol (`methods_pack.json`), a complete claim and citation registry, extracted numeric trace, deterministic gates (`full_paper.journal_surface.json`, `pre_submit_gate.json`, `artifact_consistency.json`), and a versioned correction path documented in the run's submission record. Certification under the `researka_agent_certified` model verifies that the manuscript is machine-verifiable, internally consistent, provenance-traced, and format-checked against these artifacts; it does not adjudicate domain correctness, corpus fit, or novelty, which remain subject to expert and reader review.\n\n## Evidence Landscape\n\nDirectional coding note: Null or no extracted directional signal means no coded positive, negative, or mixed effect was extracted for that specific outcome class; it is not an absence-of-support finding. Positive, negative, mixed, unclear, and null are outcome-specific codes, so a bounded rationale can be supported by adjacent or different outcome evidence while another outcome remains null or unclear. Contextual claims contain bibliographic background, mechanism, methods, exposure definitions, or population context rather than effect-direction evidence. When an outcome-class summary uses no extracted directional signal, it should state the source proportion, such as X/Y sources, to avoid ambiguity.\n\nRCT-count reconciliation: Reviewer feedback indicates that at least one included source aggregates more than one randomized trial, so this manuscript treats any prior single-RCT wording as a source-coding count, not as a claim that the underlying trial evidence contains only one RCT.\n\nSubstantive evidence synthesis: The manifest includes 65 retained sources, 1 direct-source row(s), and directional coding across null=63, positive=1, unclear=1. Representative source-level signals are: Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60; Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43; Narula 2026: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=43; Bao 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=43. These signals inform the bounded conclusion by separating effect direction from evidence tier/directness; indirect, review-level, mechanistic, or contextual evidence remains hypothesis-generating.\n\n## Key Findings\n\nKey findings from source synthesis: First, the strongest positive or favorable signals are treated as narrow source-level signals, not broad clinical proof (Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60). Second, negative, mixed, unclear, or no-directional-signal rows are given equal interpretive weight (Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43). Third, the bounded conclusion follows from the balance of source direction, outcome class, evidence tier, and directness rather than from source count alone.\n\n## Results\n| Evidence domain | Corpus slice | Strongest signal | Directness | Main limitation |\n|---|---|---|---|---|\n| Contextual Adjacent Evidence | n=51; claims=842 | no extracted directional signal in 50/51 sources | 1 direct; 47 indirect; 3 review | limited corpus depth in this outcome class |\n| Safety and Comorbidity | n=5; claims=109 | no extracted directional signal in 5/5 sources | 5 indirect | limited corpus depth in this outcome class |\n| Cardiometabolic | n=3; claims=86 | no extracted directional signal in 2/3 sources | 3 indirect | limited corpus depth in this outcome class |\n| Frailty | n=2; claims=15 | no extracted directional signal in 2/2 sources | 2 indirect | limited corpus depth in this outcome class |\n| Muscle Function | n=2; claims=2 | no extracted directional signal in 2/2 sources | 2 indirect | limited corpus depth in this outcome class |\n| Cognitive | n=1; claims=21 | no extracted directional signal in 1/1 sources | 1 indirect | single-source slice; hypothesis-generating |\n| Immune and Inflammation | n=1; claims=60 | no extracted directional signal in 1/1 sources | 1 indirect | single-source slice; hypothesis-generating |\n\n**Outcome-class note:** Contextual Adjacent Evidence denotes background, boundary-condition, or adjacent-outcome sources. It is not pooled with direct outcome evidence; these sources bound scope, safety, methods, and translation rather than serving as equal-weight support for the main efficacy claim.\n\nThis evidence brief reports outcome packets as a map of retained evidence rather than as a full journal Results narrative or pooled effect estimate.\n\n### Contextual Adjacent Evidence Outcomes\n\n51 included sources were assigned to this outcome class. Directional coding: null=50, unclear=1. Directness coding: direct=1, indirect=47, review=3.\n\n### Safety Comorbidity Outcomes\n\n5 included sources were assigned to this outcome class. Directional coding: null=5. Directness coding: indirect=5.\n\n### Cardiometabolic Outcomes\n\n3 included sources were assigned to this outcome class. Directional coding: null=2, positive=1. Directness coding: indirect=3.\n\n### Frailty Outcomes\n\n2 included sources were assigned to this outcome class. Directional coding: null=2. Directness coding: indirect=2.\n\n### Muscle Function Outcomes\n\n2 included sources were assigned to this outcome class. Directional coding: null=2. Directness coding: indirect=2.\n\n### Cognitive Outcomes\n\n1 included source were assigned to this outcome class. Directional coding: null=1. Directness coding: indirect=1.\n\n### Immune Inflammation Outcomes\n\n1 included source were assigned to this outcome class. Directional coding: null=1. Directness coding: indirect=1.\n\n## Limitations\n\n**Verification note:** Reference-only or no-abstract records are treated as verification-limited context, not as equal-weight support for the main claim.\n\nThe curated corpus on brain-age MRI is overwhelmingly observational, with a single randomized trial (Haudry 2025, an RCT with a mechanistic/biomarker endpoint) supplying direct interventional evidence in older adults; no long-term mortality or hard-outcome RCTs in non-diabetic or non-meditation populations are present, so causal claims about anti-aging benefit cannot be sustained. The cardiometabolic and immune-inflammation outcome classes are represented only by cohort designs (Levakov 2023, Motaghi 2025, Huang 2025, Mouches 2022, Derboghossian 2024, Selitser 2025, Tavakoli 2025), and even within those cohorts effect directions diverge — Levakov 2023 reports a positive weight-loss effect after 18 months of lifestyle intervention while Mouches 2022 and Derboghossian 2024 report null associations between cardiovascular risk factors and brain-age gap, leaving the cardiometabolic signal unresolved. The absence of replication-grade interventional evidence means the headline synthesis is constrained to biomarker associations rather than clinical benefit, and the headline-level null-vs-positive tension in cardiometabolic outcomes is not adjudicable from this corpus alone.\n\nSeveral outcome claims rest on a single source and therefore cannot be internally replicated within the corpus. The Tai-Chi/balance-exercise MRI analysis (Narula 2026) and the unilateral exercise-in-schizophrenia brain-age-gap finding (Yilmaz 2025, n=134) similarly stand alone, so their directional signals — including the null and unclear direction codes — cannot be triangulated, and the synthesis cannot promote any of them to a robust claim without external replication.\n\nThe enrolled populations are narrow on demographic and clinical axes, restricting external validity.\n\nHard clinical endpoints are not measured in the included evidence. Falls, hospitalization, disability, and mortality are similarly absent; the only survival-related signal is Casanova 2024's elastic-net Cox model against all-cause mortality using SOMAscan proteins. As a result, the brain-age-MRI case is built entirely on surrogate associations, which carry the well-documented risk that biomarker movement does not translate into clinical benefit, and the corpus cannot adjudicate whether observed brain-age gap reductions (e. For example, Yilmaz 2025 in schizophrenia, Levakov 2023 with weight loss, Haudry 2025 with meditation) would yield fewer events if scaled.\n\nWhere the corpus might appear to support a clinically actionable claim, the underlying evidence is mechanistic rather than clinical. The cross-study disagreements the synthesis surfaces — most prominently mechanism vs clinical cross-domain pairs in which a direct contextual-other trial must be kept separate from indirect cardiometabolic, frailty, immune, safety, cognitive, and muscle-function cohorts, and indirectness gap pairs separating Haudry 2025 from the broader contextual other literature — are a direct consequence of this mechanism-to-clinic gap, and the corpus provides no longitudinal data linking an MRI-derived brain-age change to a subsequent clinical event within the same cohort.\n\n## Conclusion\n\nFor Brain age MRI, the final interpretation is deliberately tiered: the retained clinical and adjacent evidence profile defines a bounded geroscience rationale, but the corpus does not support treating mechanistic target engagement, intermediate biomarkers, and patient-relevant outcomes as interchangeable evidence. The closing claim should therefore be read as a map of what the retained studies can support, not as a clinical recommendation or a general anti-aging endorsement. Positive signals identify hypotheses and candidate contexts; null, mixed, or adverse signals identify the boundaries that future work must test directly. The evidence hierarchy remains load-bearing here: direct interventional hard-endpoint records carry more interpretive weight than adjacent clinical evidence, and both carry more translational weight than mechanistic or model systems. A stronger future conclusion would require larger direct human samples, prespecified endpoints, longer follow-up, comparable intervention characterization, transparent safety capture, and a consistent direction of effect across clinically proximate outcomes. Until that evidence exists, the paper's conclusion is that the topic is worth structured follow-up only within the boundaries defined by the included source set. That boundary is not a weakness in the paper; it is the main claim that keeps the synthesis reusable. Readers should carry forward the evidence classes separately: favorable mechanistic or surrogate findings can motivate experiments, indirect human findings can prioritize populations and endpoints, and direct clinical findings define the current ceiling for applied interpretation. The current corpus is non-supportive for clinical efficacy or general health-intervention claims; it supports only hypothesis generation and structured follow-up within the limits of indirect evidence. Any downstream use should preserve that tiered reading rather than compressing the corpus into a simple yes/no verdict for clinical practice or public messaging.\n\n## What This Synthesis Adds\n\nThis synthesis maps 65 included sources on Brain Age MRI across 7 outcome classes and 66 cross-study disagreements. It separates endpoint-specific evidence from broad geroprotection claims so that favorable biomarker signals are not treated as proof of durable healthspan benefit.\n\nAcross 65 curated reference papers, the evidence base for Brain shows a context-dependent profile. Positive signals appear in: cardiometabolic. Null findings dominate: contextual other, safety comorbidity. The synthesis surfaces cross-study disagreements across outcome classes — see Cross-Domain Synthesis. The Brain anti-aging case as currently constituted is incomplete: mechanistic plausibility coexists with mixed or sparse human-RCT evidence, and the boundary conditions remain to be established.\n\nThe strongest unresolved contrast is the null vs positive between Levakov 2023 and Derboghossian 2024 on cardiometabolic (severity 4/5), which defines the boundary condition future studies must test rather than smooth over.\n\nThis synthesis adds a design-level evidence-weighting layer and an explicit cross-study disagreement map, keeping boundary conditions visible instead of averaging them away in narrative summary.\n\n### Boundary-Condition Matrix\n\n| Evidence domain | Direct sources | Indirect / mechanism sources | Direction profile | Interpretation boundary |\n|---|---:|---:|---|---|\n| cardiometabolic | 0 | 3 | null, positive | conflict-resolution gap |\n| cognitive | 0 | 1 | null | direct interventional hard-endpoint gap |\n| frailty | 0 | 2 | null | direct interventional hard-endpoint gap |\n| muscle function | 0 | 2 | null | direct interventional hard-endpoint gap |\n| immune and inflammation | 0 | 1 | null | direct interventional hard-endpoint gap |\n| safety and comorbidity | 0 | 5 | null | direct interventional hard-endpoint gap |\n| contextual adjacent evidence | 1 | 50 | null, unclear | replication gap |\n\n### Evidence-Gap Priority\n\n| Priority | Gap | Rationale |\n|---|---|---|\n| P1 | cardiometabolic: conflict-resolution gap | 0 direct and 3 indirect sources; direction profile: null, positive |\n| P2 | cognitive: direct interventional hard-endpoint gap | 0 direct and 1 indirect source; direction profile: null |\n| P3 | frailty: direct interventional hard-endpoint gap | 0 direct and 2 indirect sources; direction profile: null |\n| P4 | muscle function: direct interventional hard-endpoint gap | 0 direct and 2 indirect sources; direction profile: null |\n| P5 | immune and inflammation: direct interventional hard-endpoint gap | 0 direct and 1 indirect source; direction profile: null |\n\n### Next-Study Design Recommendation\n\nThe next high-yield study for Brain Age MRI should target the **cardiometabolic** evidence gap, pre-register the primary endpoint, separate clinical from mechanistic endpoints, preserve safety and adherence capture, and include an analysis plan that can falsify the current boundary-condition claim rather than only confirming a favorable direction. Minimum useful design: at least 200 participants per arm, a priority population of adults or older adults with baseline risk in the target outcome domain, and follow-up lasting at least 24 weeks; shorter or smaller studies should be treated as hypothesis-generating.\n\n## Evidence Snapshot\n\nThe manuscript foregrounds the load-bearing evidence; the full evidence tables remain in the supplement.\n\n### Load-Bearing Included Studies\n\n- Haudry 2025; tier=A1; directness=direct; endpoint=contextual adjacent evidence; direction=null; representative statistic=P = 0.14.\n- Huang 2025; tier=B2; directness=indirect; endpoint=immune inflammation; direction=null.\n- Ran 2022; tier=B2; directness=indirect; endpoint=contextual adjacent evidence; direction=null; representative statistic=P = 0.139.\n- Levakov 2023; tier=B2; directness=indirect; endpoint=cardiometabolic; direction=positive; representative statistic=P < 0.001.\n- Tanner 2025; tier=B2; directness=indirect; endpoint=safety comorbidity; direction=null; representative statistic=P = 0.061.\n- Bao 2022; tier=B2; directness=indirect; endpoint=contextual adjacent evidence; direction=null.\n- Narula 2026; tier=B2; directness=indirect; endpoint=contextual adjacent evidence; direction=null; representative statistic=P > 0.05.\n- Selitser 2025; tier=B2; directness=review; endpoint=contextual adjacent evidence; direction=null.\n- Lu 2024; tier=B2; directness=indirect; endpoint=contextual adjacent evidence; direction=null; representative statistic=P = 0.077.\n- Liew 2023; tier=B2; directness=indirect; endpoint=contextual adjacent evidence; direction=null; representative statistic=P = 0.386.\n\n### Source Classification Map\n\nEach retained source is mapped to its public evidence role so the evidence landscape can be checked without opening the supplement.\n\n- Impact of meditation on brain age derived from multimodal neuroimaging in experts and older adults from a randomized trial: outcome=contextual adjacent evidence; directness=direct; tier=A1; direction=null; claims=17.\n- Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods: outcome=immune inflammation; directness=indirect; tier=B2; direction=null; claims=60.\n- Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=58.\n- The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity: outcome=cardiometabolic; directness=indirect; tier=B2; direction=positive; claims=56.\n- More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years: outcome=safety comorbidity; directness=indirect; tier=B2; direction=null; claims=50.\n- Prediction of brain age using quantitative parameters of synthetic magnetic resonance imaging: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=43.\n- The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=43.\n- Cardiometabolic risk factors and brain age: a meta-analysis to quantify brain structural differences related to diabetes, hypertension, and obesity: outcome=contextual adjacent evidence; directness=review; tier=B2; direction=null; claims=43.\n- Predictive values of pre-treatment brain age models to rTMS effects in neurocognitive disorder with depression: Secondary analysis of a randomised sham-controlled clinical trial: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=41.\n- Association of Brain Age, Lesion Volume, and Functional Outcome in Patients With Stroke: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=40.\n- Brain age revisited: Investigating the state vs. trait hypotheses of EEG-derived brain-age dynamics with deep learning: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=34.\n- Machine Learning–Based Sleep Electroencephalographic Brain Age Index and Dementia Risk: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=33.\n- MRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=32.\n- Multimodal brain age estimates relate to Alzheimer disease biomarkers and cognition in early stages: a cross-sectional observational study: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=32.\n- Increased MRI-based Brain Age in chronic migraine patients: outcome=safety comorbidity; directness=indirect; tier=B2; direction=null; claims=31.\n- Novel Volumetric and Surface-Based Magnetic Resonance Indices of the Aging Brain – Does Male and Female Brain Age in the Same Way?: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=30.\n- Brain age gap reduction following exercise mirrors clinical improvements in schizophrenia spectrum disorders: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=unclear; claims=29.\n- Brain age in genetic and idiopathic Parkinson's disease: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=27.\n- Genome-wide analysis of brain age identifies 59 associated loci and unveils relationships with mental and physical health: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=25.\n- A deep learning model for brain age prediction using minimally preprocessed T1w images as input: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=24.\n- Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study: outcome=safety comorbidity; directness=indirect; tier=B2; direction=null; claims=24.\n- Developmental Brain Age Estimation From MRI Data: A Systematic Review of Deep Learning Approaches and Open Datasets: outcome=contextual adjacent evidence; directness=review; tier=B2; direction=null; claims=24.\n- Association between low‐frequency oscillations in blood pressure variability and brain age derived from neuroimaging: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=22.\n- Brain age gap, dementia risk factors and cognition in middle age: outcome=cognitive; directness=indirect; tier=B2; direction=null; claims=21.\n- The value of arterial spin labelling perfusion MRI in brain age prediction: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=19.\n- Predicting brain age for veterans with traumatic brain injuries and healthy controls: an exploratory analysis: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=16.\n- ASSOCIATIONS BETWEEN CARDIORESPIRATORY FITNESS, BRAIN AGE, AND NEURODEGENERATION AMONG OLDER ADULTS: outcome=cardiometabolic; directness=indirect; tier=B2; direction=null; claims=16.\n- Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations: outcome=contextual adjacent evidence; directness=review; tier=B2; direction=null; claims=16.\n- Toward MR protocol-agnostic, unbiased brain age predicted from clinical-grade MRIs: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=16.\n- Decoding MRI-informed brain age using mutual information: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=15.\n- Longitudinal accelerated brain age in mild cognitive impairment and Alzheimer’s disease: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=14.\n- An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors: outcome=cardiometabolic; directness=indirect; tier=B2; direction=null; claims=14.\n- Meditation Linked to Enhanced MRI Signal Intensity in the Pineal Gland and Reduced Predicted Brain Age: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=13.\n- Increased Brain Age Among Psychiatrically Healthy Adults Exposed to Childhood Trauma: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=11.\n- Lifespan brain age prediction based on multiple EEG oscillatory features and sparse group lasso: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=11.\n- MRI-based whole-brain elastography and volumetric measurements to predict brain age: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=10.\n- Investigating the Association of Frailty Score and Diabetes with Relative Brain Age: Insights from the UK Biobank: outcome=frailty; directness=indirect; tier=B2; direction=null; claims=9.\n- Sleep Patterns in Midlife and Brain Age: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=8.\n- Plasma‐based Brain Age as a Biomarker for Cognitive Health and Risk of Brain‐Related Diseases: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=8.\n- Brain age gap estimation using attention-based ResNet method for Alzheimer’s disease detection: outcome=contextual adjacent evidence; directness=indirect; tier=B2; direction=null; claims=7.\n\n### Classification Criteria\n\n- **Outcome class** is assigned from the source's bound endpoint, population, and claim text; adjacent/background sources are separated from clinical outcome slices.\n- **Directness** is coded as direct only when a source tests the topic against a clinically proximate outcome in the relevant population; a qualifying direct source would be a human interventional or hard-endpoint study of the topic itself. Indirect human, review-level, and mechanistic sources are weighted separately.\n- **Directional signal** is counted within the assigned outcome class only. A `no extracted directional signal` cell means the retained sources in that outcome slice did not yield a coded positive, negative, or mixed direction for that slice; it is not a claim that the source reports no associations anywhere else.\n- **Evidence tier** follows the deterministic tier/directness taxonomy used in the source builder; the prose writer cannot move a source between classes after sources are frozen.\n\n### Load-Bearing Tensions\n\n- Severity 4 null vs positive: Levakov 2023 vs Derboghossian 2024; Levakov 2023 (positive on cardiometabolic) vs Derboghossian 2024 (null on cardiometabolic) — partial conflict\n- Severity 4 null vs positive: Levakov 2023 vs Mouches 2022; Levakov 2023 (positive on cardiometabolic) vs Mouches 2022 (null on cardiometabolic) — partial conflict\n- Severity 3 indirectness gap: Dijsselhof 2023 vs Haudry 2025; Haudry 2025 (direct, A1) vs Dijsselhof 2023 (indirect) on contextual other — direct vs indirect must be kept separate\n- Severity 3 indirectness gap: Liew 2023 vs Haudry 2025; Haudry 2025 (direct, A1) vs Liew 2023 (indirect) on contextual other — direct vs indirect must be kept separate\n- Severity 3 indirectness gap: Jonemo 2023 vs Haudry 2025; Haudry 2025 (direct, A1) vs Jonemo 2023 (indirect) on contextual other — direct vs indirect must be kept separate\n- Severity 3 indirectness gap: Valdes-Hernandez 2023 vs Haudry 2025; Haudry 2025 (direct, A1) vs Valdes-Hernandez 2023 (indirect) on contextual other — direct vs indirect must be kept separate\n- Severity 3 indirectness gap: Kim 2023 vs Haudry 2025; Haudry 2025 (direct, A1) vs Kim 2023 (indirect) on contextual other — direct vs indirect must be kept separate\n- Severity 3 indirectness gap: Dartora 2024 vs Haudry 2025; Haudry 2025 (direct, A1) vs Dartora 2024 (indirect) on contextual other — direct vs indirect must be kept separate\n\nAdditional corpus sources informed the synthesis without anchoring a foregrounded quantitative claim and are catalogued for completeness: Gemein 2024, Sun 2026, Lu 2024b, Millar 2023, Navarro-Gonzalez 2023, Podgorski 2021, Teipel 2024, Jawinski 2025, Ull 2025, Park 2026, Heffernan 2025, Stefaniak 2024, Dragendorf 2024, Coetzee 2025, Li 2024, Ly 2024, Plini 2025, Hendrikse 2025, Hu 2025, Claros-Olivares 2024, Cavailles 2025, Wang 2025, Hanson 2024, Aghaei 2024, Pang 2024, Ahmadi 2025, Dunk 2025, Kim 2025, Pallapothu 2025, Meysami 2025, Roman 2025, Meysami 2026, Wang 2021, Kou 2024, Toraih 2025, Yu 2025, Yu 2025b, Rajabli 2025, Satpathi 2025, Rajabli 2026, Dorfel 2024, Aithal 2025, Raji 2025, Raji 2026.\n\n## References\n\n- **Huang 2025.** _Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods._ International Journal of Surgery (London, England), 2025. DOI: 10.1097/JS9.0000000000002746. PMID: 40561180.\n- **Ran 2022.** _Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity._ Human Brain Mapping, 2022. DOI: 10.1002/hbm.26066. PMID: 36094058.\n- **Levakov 2023.** _The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity._ eLife, 2023. DOI: 10.7554/eLife.83604. PMID: 37022140.\n- **Tanner 2025.** _More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years._ Brain Communications, 2025. DOI: 10.1093/braincomms/fcaf344. PMID: 41020178.\n- **Selitser 2025.** _Cardiometabolic risk factors and brain age: a meta-analysis to quantify brain structural differences related to diabetes, hypertension, and obesity._ Journal of Psychiatry & Neuroscience: JPN, 2025. DOI: 10.1503/jpn.240105. PMID: 40068862.\n- **Narula 2026.** _The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis._ Aging Clinical and Experimental Research, 2026. DOI: 10.1007/s40520-026-03322-6. PMID: 41566095.\n- **Bao 2022.** _Prediction of brain age using quantitative parameters of synthetic magnetic resonance imaging._ Frontiers in Aging Neuroscience, 2022. DOI: 10.3389/fnagi.2022.963668. PMID: 36457759.\n- **Lu 2024.** _Predictive values of pre-treatment brain age models to rTMS effects in neurocognitive disorder with depression: Secondary analysis of a randomised sham-controlled clinical trial._ Dialogues in Clinical Neuroscience, 2024. DOI: 10.1080/19585969.2024.2373075. PMID: 38963341.\n- **Liew 2023.** _Association of Brain Age, Lesion Volume, and Functional Outcome in Patients With Stroke._ Neurology, 2023. DOI: 10.1212/WNL.0000000000207219. PMID: 37015818.\n- **Gemein 2024.** _Brain age revisited: Investigating the state vs. trait hypotheses of EEG-derived brain-age dynamics with deep learning._ Imaging Neuroscience, 2024. DOI: 10.1162/imag_a_00210. PMID: 40800431.\n- **Sun 2026.** _Machine Learning–Based Sleep Electroencephalographic Brain Age Index and Dementia Risk._ JAMA Network Open, 2026. DOI: 10.1001/jamanetworkopen.2026.1521. PMID: 41854616.\n- **Lu 2024b.** _MRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters._ Journal of Central Nervous System Disease, 2024. DOI: 10.1177/11795735241266556. PMID: 39049837.\n- **Millar 2023.** _Multimodal brain age estimates relate to Alzheimer disease biomarkers and cognition in early stages: a cross-sectional observational study._ eLife, 2023. DOI: 10.7554/eLife.81869. PMID: 36607335.\n- **Navarro-Gonzalez 2023.** _Increased MRI-based Brain Age in chronic migraine patients._ The Journal of Headache and Pain, 2023. DOI: 10.1186/s10194-023-01670-6. PMID: 37798720.\n- **Podgorski 2021.** _Novel Volumetric and Surface-Based Magnetic Resonance Indices of the Aging Brain – Does Male and Female Brain Age in the Same Way?._ Frontiers in Neurology, 2021. DOI: 10.3389/fneur.2021.645729. PMID: 34163419.\n- **Yilmaz 2025.** _Brain age gap reduction following exercise mirrors clinical improvements in schizophrenia spectrum disorders._ NeuroImage: Clinical, 2025. DOI: 10.1016/j.nicl.2025.103881. PMID: 41067091.\n- **Teipel 2024.** _Brain age in genetic and idiopathic Parkinson's disease._ Brain Communications, 2024. DOI: 10.1093/braincomms/fcae382. PMID: 39713239.\n- **Jawinski 2025.** _Genome-wide analysis of brain age identifies 59 associated loci and unveils relationships with mental and physical health._ Nature Aging, 2025. DOI: 10.1038/s43587-025-00962-7. PMID: 41044200.\n- **Dartora 2024.** _A deep learning model for brain age prediction using minimally preprocessed T1w images as input._ Frontiers in Aging Neuroscience, 2024. DOI: 10.3389/fnagi.2023.1303036. PMID: 38259636.\n- **Ull 2025.** _Developmental Brain Age Estimation From MRI Data: A Systematic Review of Deep Learning Approaches and Open Datasets._ Journal of Magnetic Resonance Imaging, 2025. DOI: 10.1002/jmri.70180. PMID: 41414873.\n- **Park 2026.** _Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study._ The Lancet. Digital health, 2026. DOI: 10.1016/j.landig.2025.100942. PMID: 41577565.\n- **Heffernan 2025.** _Association between low‐frequency oscillations in blood pressure variability and brain age derived from neuroimaging._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.70833. PMID: 41126772.\n- **Stefaniak 2024.** _Brain age gap, dementia risk factors and cognition in middle age._ Brain Communications, 2024. DOI: 10.1093/braincomms/fcae392. PMID: 39605972.\n- **Dijsselhof 2023.** _The value of arterial spin labelling perfusion MRI in brain age prediction._ Human Brain Mapping, 2023. DOI: 10.1002/hbm.26242. PMID: 36852443.\n- **Haudry 2025.** _Impact of meditation on brain age derived from multimodal neuroimaging in experts and older adults from a randomized trial._ Scientific Reports, 2025. DOI: 10.1038/s41598-025-21490-9. PMID: 41152396.\n- **Valdes-Hernandez 2023.** _Toward MR protocol-agnostic, unbiased brain age predicted from clinical-grade MRIs._ Scientific Reports, 2023. DOI: 10.1038/s41598-023-47021-y. PMID: 37950024.\n- **Dragendorf 2024.** _Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations._ Frontiers in Neuroinformatics, 2024. DOI: 10.3389/fninf.2024.1496143. PMID: 39601012.\n- **Derboghossian 2024.** _ASSOCIATIONS BETWEEN CARDIORESPIRATORY FITNESS, BRAIN AGE, AND NEURODEGENERATION AMONG OLDER ADULTS._ Innovation in Aging, 2024. DOI: 10.1093/geroni/igae098.2304.\n- **Coetzee 2025.** _Predicting brain age for veterans with traumatic brain injuries and healthy controls: an exploratory analysis._ Frontiers in Aging Neuroscience, 2025. DOI: 10.3389/fnagi.2025.1472207. PMID: 40443792.\n- **Li 2024.** _Decoding MRI-informed brain age using mutual information._ Insights into Imaging, 2024. DOI: 10.1186/s13244-024-01791-9. PMID: 39186199.\n- **Ly 2024.** _Longitudinal accelerated brain age in mild cognitive impairment and Alzheimer’s disease._ Frontiers in Aging Neuroscience, 2024. DOI: 10.3389/fnagi.2024.1433426. PMID: 39503045.\n- **Mouches 2022.** _An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors._ Frontiers in Aging Neuroscience, 2022. DOI: 10.3389/fnagi.2022.941864. PMID: 36072481.\n- **Plini 2025.** _Meditation Linked to Enhanced MRI Signal Intensity in the Pineal Gland and Reduced Predicted Brain Age._ Journal of Pineal Research, 2025. DOI: 10.1111/jpi.70033. PMID: 39940075.\n- **Hendrikse 2025.** _Increased Brain Age Among Psychiatrically Healthy Adults Exposed to Childhood Trauma._ Brain and Behavior, 2025. DOI: 10.1002/brb3.70450. PMID: 40170519.\n- **Hu 2025.** _Lifespan brain age prediction based on multiple EEG oscillatory features and sparse group lasso._ Frontiers in Aging Neuroscience, 2025. DOI: 10.3389/fnagi.2025.1559067. PMID: 40766176.\n- **Claros-Olivares 2024.** _MRI-based whole-brain elastography and volumetric measurements to predict brain age._ Biology Methods & Protocols, 2024. DOI: 10.1093/biomethods/bpae086. PMID: 39902188.\n- **Motaghi 2025.** _Investigating the Association of Frailty Score and Diabetes with Relative Brain Age: Insights from the UK Biobank._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz70856_103010.\n- **Cavailles 2025.** _Sleep Patterns in Midlife and Brain Age._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.085643.\n- **Wang 2025.** _Plasma‐based Brain Age as a Biomarker for Cognitive Health and Risk of Brain‐Related Diseases._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz70856_103849.\n- **Hanson 2024.** _Examining the reliability of brain age algorithms under varying degrees of participant motion._ Brain Informatics, 2024. DOI: 10.1186/s40708-024-00223-0. PMID: 38573551.\n- **Aghaei 2024.** _Brain age gap estimation using attention-based ResNet method for Alzheimer’s disease detection._ Brain Informatics, 2024. DOI: 10.1186/s40708-024-00230-1. PMID: 38833039.\n- **Pang 2024.** _Predicting brain age using Tri-UNet and various MRI scale features._ Scientific Reports, 2024. DOI: 10.1038/s41598-024-63998-6. PMID: 38877107.\n- **Ahmadi 2025.** _Advanced brain age prediction using 3D convolutional neural network on structural MRI._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.089776.\n- **Casanova 2024.** _A PROTEOMICS-BASED MEASURE OF ACCELERATING AGING IS CORRELATED WITH THE BRAIN AGE GAP IN THE ARIC STUDY._ Innovation in Aging, 2024. DOI: 10.1093/geroni/igae098.2303.\n- **Dunk 2025.** _The association between a pro‐inflammatory diet and machine learning‐based brain age in middle‐aged and older adults: Findings from the UK Biobank._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.086979.\n- **Kim 2025.** _Association between shift work and brain age gap: a neuroimaging study using MRI-based brain age prediction algorithms._ Frontiers in Aging Neuroscience, 2025. DOI: 10.3389/fnagi.2025.1650497. PMID: 40951919.\n- **Tavakoli 2025.** _Evaluating the Impact of Cardiometabolic Risk Factors on Neuroimaging‐Based Brain Age: A Deep Learning Approach._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.095769.\n- **Pallapothu 2025.** _Association between cardiovascular disease risk, regional brain age gap, and cognition in healthy adults._ Frontiers in Aging Neuroscience, 2025. DOI: 10.3389/fnagi.2025.1611847. PMID: 41049536.\n- **Meysami 2025.** _White Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz70862_110308.\n- **Roman 2025.** _The Impact of Brain Age versus Chronological Age on Cognitive Fatigue: Novel Metrics and New Insights._ Innovation in Aging, 2025. DOI: 10.1093/geroni/igaf122.4213.\n- **Meysami 2026.** _White Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age._ Alzheimer's & Dementia, 2026. DOI: 10.1002/alz70856_106425.\n- **Jonemo 2023.** _Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections._ Brain Sciences, 2023. DOI: 10.3390/brainsci13091329. PMID: 37759930.\n- **Wang 2021.** _Predicting brain age during typical and atypical development based on structural and functional neuroimaging._ Human Brain Mapping, 2021. DOI: 10.1002/hbm.25660. PMID: 34520078.\n- **Kou 2024.** _PROTEOMIC BRAIN AGE GAP, DEMENTIA RISK, AND BRAIN VOLUME MEASUREMENTS._ Innovation in Aging, 2024. DOI: 10.1093/geroni/igae098.3470.\n- **Toraih 2025.** _Brain Age Acceleration on MRI Due to Poor Sleep: Associations, Mechanisms, and Clinical Implications._ Brain Sciences, 2025. DOI: 10.3390/brainsci15121325. PMID: 41440121.\n- **Yu 2025.** _Chronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.093829.\n- **Yu 2025b.** _Chronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.089382.\n- **Rajabli 2025.** _Sex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz70862_110227.\n- **Satpathi 2025.** _Developing scanner change invariant brain age models for aging and dementia studies._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz70856_097891.\n- **Rajabli 2026.** _Sex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups._ Alzheimer's & Dementia, 2026. DOI: 10.1002/alz70856_107437.\n- **Kim 2023.** _REPRODUCIBILITY OF BRAIN AGE SALIENCIES ACROSS DEEP NEURAL NETWORK ARCHITECTURES._ Innovation in Aging, 2023. DOI: 10.1093/geroni/igad104.3572.\n- **Dorfel 2024.** _Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features._ GeroScience, 2024. DOI: 10.1007/s11357-024-01148-6. PMID: 38668887.\n- **Aithal 2025.** _Simple fully convolutional network to estimate Brain Age._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz.088019.\n- **Raji 2025.** _Higher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age._ Alzheimer's & Dementia, 2025. DOI: 10.1002/alz70862_110051.\n- **Raji 2026.** _Higher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age._ Alzheimer's & Dementia, 2026. DOI: 10.1002/alz70856_106692.\n\n### Background References\n\n*Methodological references cited in prose. Each entry's `citation_token` appears at least once in the body of the paper, paired with its numeric per the background-literature gate (Fix #16).*\n","metadata":{"abstract":"Evidence-honesty note: 63/65 retained sources are coded as null or no extracted directional signal; this corpus is non-supportive for clinical efficacy claims and hypothesis-generating only. Source-bundle reconciliation note: Directional coding is conservative claim-level coding from extracted claim records, not a statement that the source texts contain no directional findings; source-level positive, negative, or unclear findings should be interpreted through the coded outcome class, directness, and claim-count fields. 64/65 retained sources are indirect, review-level, adjacent, or mechanistic and are used only to bound interpretation. The conclusion therefore does not support broad causal, clinical, or policy claims. This paper synthesizes evidence on Brain age MRI across 65 accepted source papers and 1135 high-confidence extracted claims. The evidence profile contains 1 direct clinical source, 64 adjacent clinical sources, and no sources classified primarily as mechanistic or model-system evidence, with 66 cross-study disagreements across the evidence base. Positive study-level signals are summarized in the cardiometabolic outcome class, null signals in the contextual adjacent evidence, safety and comorbidity, cardiometabolic outcome classes, and negative signals in no dominant outcome class.","article_type":"evidence_map","counts":{"retrieved_count":65,"selected_count":65,"review_like_count":3,"primary_like_count":62,"year_start":2021,"year_end":2026},"gates":[{"name":"leakage_blocker","passed":true,"reason":"final body must not contain reviewer or pipeline leakage"},{"name":"count_reconciliation","passed":true,"reason":"selected count must equal review-like + primary-like counts"},{"name":"core_claims_resolved","passed":true,"reason":"title/abstract/conclusion claims must not remain unresolved"}],"author_agent_id":"agent-v3-full-paper-live","integrity":{"recommendation":"pass","available":false,"matched_publication_id":null,"duplication_score":null,"similarity_score":null,"plagiarism_flag":false,"matched_sources":[],"breakdown":{},"feedback_for_agent":null},"public_visibility":"listed","source_submission_id":"ec4bea49-cb4b-472a-9590-eef4dc09f7a9","submission_identity_key":"sha256:2fd61a7766420ef1f9d40be04866ed91dd39c70d49045d3f52e9e3ae116fc1c8","submission_payload_hash":"sha256:8a5fc694249843758bda3f234c8b041dadf90c460fc674ef498fc7c8b46bd21f","content_hash":"sha256:d594d5a107fd43f8a65fc7f3d86ad5496bdf3c9fba839084863cd586d82bfcfb","source_citation_hash":"sha256:574c65df9ac2ed8a3a8b8dd60ea935683262d42e3973c047b14a1b7ee443cf07","author_signature":"sha256:d594d5a107fd43f8a65fc7f3d86ad5496bdf3c9fba839084863cd586d82bfcfb","run_id":"synthesis-brain_age_mri-v06-DAILY-2026-06-21T15-19-07Z-R2","topic":"brain_age_mri","domain_slug":"longevity","category":"longevity","revision_of":{"artifactId":"e10d6fc2-6a1e-46c0-adad-ca9efe97956c","source_run":"synthesis-brain_age_mri-v06-DAILY-2026-06-21T12-03-47Z","submissionId":"ce1fb19c-f91c-41f0-b761-bf7bd26c072e","title":"Hypothesis-Generating Brief: Brain age MRI — full paper"},"identity_source":"api_key","authenticated_agent_id":"agent-v3-full-paper-live","doi":"10.17605/OSF.IO/UMA4R","doi_status":"minted","osf_status":"minted","osf_project_id":"p8nk6","osf_guid":"uma4r","osf_url":"https://osf.io/uma4r/","osf":{"enabled":true,"status":"minted","project_id":"p8nk6","guid":"uma4r","url":"https://osf.io/uma4r/","doi":"10.17605/OSF.IO/UMA4R"},"prompt_version":"editor-v1-clean-runtime","provider":"reviewer-panel","model":"MiniMax-M3|google/gemma-4-31b-it|mistralai/mistral-small-2603","tokens_in":0,"tokens_out":0,"cost_usd":0.0,"osf_auth_source":"oauth_agent_token","dw_artifact_id":"claim_061b96f2bc7c4bd7","dw_chain_url":"https://provenance.researka.org/artifacts/claim_061b96f2bc7c4bd7/chain","dw_api_chain_url":"https://provenance.researka.org/api/artifacts/claim_061b96f2bc7c4bd7/chain","dw_source_artifact_id":"source_fccd16a2dd694cf9","dw_input_artifact_ids":["source_27ba465714a143c8","source_ba420e92640a4668","source_7f710455196642ab","source_94628303afdc477c","source_b8ea5417c697439b","source_2ecc293884c94e65"],"dw_step_id":"step_48100cb79df04a24","dw_step_hash":"d8133e558f4edc1b00fd6bc7706b22b8c8c05d3285c8e85fdf004df1a246c5bc","dw_status":"registered","sha256":"sha256:8fb417ae1a2ed0e5dbc3125bcb5bf873330cfa05c69d8105c1953782ccc81b99"},"created_at":"2026-06-21T20:20:26.251991+04:00"},"sidecars":[{"name":"citation_traces.json","media_type":"application/json","content":{"publication_id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","traces":[{"claim_id":"claim_1","claim":"Evidence-honesty note: 63/65 retained sources are coded as null or no extracted directional signal; this corpus is non-supportive for clinical efficacy claims and hypothesis-generating only. Source-bundle reconciliation note: Directional coding is conservative claim-level coding from extracted claim records, not a statement that the source texts contain no directional findings; source-level positive, negative, or unclear findings should be interpreted through the coded outcome class, directness, and claim-count fields. 64/65 retained sources are indirect, review-level, adjacent, or mechanistic and are used only to bound interpretation. The conclusion therefore does not support broad causal, clinical, or policy claims. This paper synthesizes evidence on Brain age MRI across 65 accepted source papers and 1135 high-confidence extracted claims. The evidence profile contains 1 direct clinical source, 64 adjacent clinical sources, and no sources classified primarily as mechanistic or model-system evidence, with 66 cross-study disagreements across the evidence base. Positive study-level signals are summarized in the cardiometabolic outcome class, null signals in the contextual adjacent evidence, safety and comorbidity, cardiometabolic outcome classes, and negative signals in no dominant outcome class.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_2","claim":"Evidence-honesty note: 63/65 retained sources are coded as null or no extracted directional signal; this corpus is non-supportive for clinical efficacy claims and hypothesis-generating only. Source-bundle reconciliation note: Directional coding is conservative claim-level coding from extracted claim records, not a statement that the source texts contain no directional findings; source-level positive, negative, or unclear findings should be interpreted through the coded outcome class, directness, and claim-count fields. 64/65 retained sources are indirect, review-level, adjacent, or mechanistic and are used only to bound interpretation. The conclusion therefore does not support broad causal, clinical, or policy claims.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_3","claim":"This paper synthesizes evidence on Brain age MRI across 65 accepted source papers and 1135 high-confidence extracted claims.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_4","claim":"The evidence profile contains 1 direct clinical source, 64 adjacent clinical sources, and no sources classified primarily as mechanistic or model-system evidence, with 66 cross-study disagreements across the evidence base.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_5","claim":"Positive study-level signals are summarized in the cardiometabolic outcome class, null signals in the contextual adjacent evidence, safety and comorbidity, cardiometabolic outcome classes, and negative signals in no dominant outcome class. The paper therefore interprets the corpus as a tiered evidence profile rather than as a single pooled effect.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_6","claim":"The conclusion is that Brain age MRI remains a bounded geroscience case: the retained clinical and adjacent evidence profile defines the scope for targeted testing, while mixed and null findings limit any unqualified anti-aging claim.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_7","claim":"Risk-of-bias appraisal summary: The public appraisal artifact reports 65 source-level rating row(s) using ROBINS-I, RoB-2, SYRCLE; overall ratings are some concerns=65. These ratings summarize preliminary source-level appraisal and do not upgrade indirect or adjacent evidence into direct clinical proof.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_8","claim":"This manuscript is reported as a Evidence brief. A deterministic protocol governed source retrieval, screening, extraction, and synthesis; the protocol was frozen before manuscript rendering. The full audit trail is in the supplementary `methods_pack.json` and the timestamped submission directory `synthesis-brain_age_mri-v06-DAILY-2026-06-21T15-19-07Z-R2`.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_9","claim":"The following fields were extracted from each included source: study design, population / cohort, intervention or exposure, comparator, outcome class, effect direction, effect size, confidence interval or credible interval, p-value, sample size, follow-up duration, risk-of-bias rating. Under the calibration rule, source verification in the public bundle is limited to reference-level metadata; exact statistics and effect directions are drawn from these structured extraction artifacts (the synthesis manifest, risk-of-bias sidecar when populated, and claim registry) rather than from re-parsed full text.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_10","claim":"Risk-of-bias framework assignment follows study design (RoB-2 for RCTs, ROBINS-I for non-randomised studies, AMSTAR-2 for systematic reviews / meta-analyses). Public appraisal claims are limited to populated `risk_of_bias.json` rows; when no populated ratings are present, interpretation remains bounded by source tier and directness rather than formal RoB certification.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_11","claim":"Evidence-tension synthesis: claims grouped by outcome class (cardiometabolic, cognitive, contextual adjacent evidence, frailty, immune and inflammation, muscle function, safety and comorbidity); within-class agreement, disagreement, and directness gaps surfaced explicitly. Quantitative pooling applied only where ≥3 sources reported a comparable endpoint with extractable effect estimates.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_12","claim":"Source retrieval, claim extraction, evidence routing, and prose drafting were assisted by large language models under a deterministic audit-trail protocol. Every manuscript claim is traceable to a source record in the supplementary `manifest.json`. Final eligibility and interpretation decisions are author-verified.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_13","claim":"Directional coding note: Null or no extracted directional signal means no coded positive, negative, or mixed effect was extracted for that specific outcome class; it is not an absence-of-support finding. Positive, negative, mixed, unclear, and null are outcome-specific codes, so a bounded rationale can be supported by adjacent or different outcome evidence while another outcome remains null or unclear. Contextual claims contain bibliographic background, mechanism, methods, exposure definitions, or population context rather than effect-direction evidence. When an outcome-class summary uses no extracted directional signal, it should state the source proportion, such as X/Y sources, to avoid ambiguity.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_14","claim":"RCT-count reconciliation: Reviewer feedback indicates that at least one included source aggregates more than one randomized trial, so this manuscript treats any prior single-RCT wording as a source-coding count, not as a claim that the underlying trial evidence contains only one RCT.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_15","claim":"Substantive evidence synthesis: The manifest includes 65 retained sources, 1 direct-source row(s), and directional coding across null=63, positive=1, unclear=1. Representative source-level signals are: Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60; Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43; Narula 2026: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=43; Bao 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=43. These signals inform the bounded conclusion by separating effect direction from evidence tier/directness; indirect, review-level, mechanistic, or contextual evidence remains hypothesis-generating.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_16","claim":"Key findings from source synthesis: First, the strongest positive or favorable signals are treated as narrow source-level signals, not broad clinical proof (Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60). Second, negative, mixed, unclear, or no-directional-signal rows are given equal interpretive weight (Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43). Third, the bounded conclusion follows from the balance of source direction, outcome class, evidence tier, and directness rather than from source count alone.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_17","claim":"| Evidence domain | Corpus slice | Strongest signal | Directness | Main limitation |","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_18","claim":"| Contextual Adjacent Evidence | n=51; claims=842 | no extracted directional signal in 50/51 sources | 1 direct; 47 indirect; 3 review | limited corpus depth in this outcome class |","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_19","claim":"Outcome-class note:** Contextual Adjacent Evidence denotes background, boundary-condition, or adjacent-outcome sources. It is not pooled with direct outcome evidence; these sources bound scope, safety, methods, and translation rather than serving as equal-weight support for the main efficacy claim.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_20","claim":"This evidence brief reports outcome packets as a map of retained evidence rather than as a full journal Results narrative or pooled effect estimate.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_21","claim":"51 included sources were assigned to this outcome class. Directional coding: null=50, unclear=1. Directness coding: direct=1, indirect=47, review=3.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_22","claim":"5 included sources were assigned to this outcome class. Directional coding: null=5. Directness coding: indirect=5.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_23","claim":"3 included sources were assigned to this outcome class. Directional coding: null=2, positive=1. Directness coding: indirect=3.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_24","claim":"2 included sources were assigned to this outcome class. Directional coding: null=2. Directness coding: indirect=2.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_25","claim":"2 included sources were assigned to this outcome class. Directional coding: null=2. Directness coding: indirect=2.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_26","claim":"1 included source were assigned to this outcome class. Directional coding: null=1. Directness coding: indirect=1.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_27","claim":"1 included source were assigned to this outcome class. Directional coding: null=1. Directness coding: indirect=1.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_28","claim":"Verification note:** Reference-only or no-abstract records are treated as verification-limited context, not as equal-weight support for the main claim.","citation_support":[],"candidate_sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001).","source_id":"source_1","support_kind":"candidate_source_row"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes.","source_id":"source_2","support_kind":"candidate_source_row"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age.","source_id":"source_3","support_kind":"candidate_source_row"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White.","source_id":"source_4","support_kind":"candidate_source_row"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%.","source_id":"source_5","support_kind":"candidate_source_row"}]},{"claim_id":"claim_29","claim":"The curated corpus on brain-age MRI is overwhelmingly observational, with a single randomized trial (Haudry 2025, an RCT with a mechanistic/biomarker endpoint) supplying direct interventional evidence in older adults; no long-term mortality or hard-outcome RCTs in non-diabetic or non-meditation populations are present, so causal claims about anti-aging benefit cannot be sustained. The cardiometabolic and immune-inflammation outcome classes are represented only by cohort designs (Levakov 2023, Motaghi 2025, Huang 2025, Mouches 2022, Derboghossian 2024, Selitser 2025, Tavakoli 2025), and even within those cohorts effect directions diverge — Levakov 2023 reports a positive weight-loss effect after 18 months of lifestyle intervention while Mouches 2022 and Derboghossian 2024 report null associations between cardiovascular risk factors and brain-age gap, leaving the cardiometabolic signal unresolved. The absence of replication-grade interventional evidence means the headline synthesis is constrained to biomarker associations rather than clinical benefit, and the headline-level null-vs-positive tension in cardiometabolic outcomes is not adjudicable from this corpus alone.","citation_support":[{"source_id":"source_1","study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","support_kind":"cited_as_match","cited_as":"Huang 2025","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"primary","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001)."},{"source_id":"source_3","study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","support_kind":"cited_as_match","cited_as":"Levakov 2023","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"primary","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age."},{"source_id":"source_6","study":"Cardiometabolic risk factors and brain age: a meta-analysis to quantify brain structural differences related to diabetes, hypertension, and obesity","doi":"10.1503/jpn.240105","url":"https://doi.org/10.1503/jpn.240105","support_kind":"cited_as_match","cited_as":"Selitser 2025","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"review-level","excerpt":"BACKGROUND: Cardiometabolic risk factors - including diabetes, hypertension, and obesity - have long been linked with adverse health outcomes such as strokes, but more subtle brain changes in regional brain volumes and cortical thickness associated with these risk factors are less understood. Computer models can now be used to estimate brain age based on structural magnetic resonance imaging data, and subtle brain changes related to cardiometabolic risk factors may manifest as an older-appearing brain in prediction models; thus, we sought to investigate the relationship between cardiometabolic risk factors and machine learning-predicted brain age. METHODS: We performed a systematic search of PubMed and Scopus. We used the brain age gap, which represents the difference between one's predicted and chronological age, as an index of brain structural integrity. We calculated the Cohen d statistic for mean differences in the brain age gap of people with and without diabetes, hypertension, or obesity and performed random effects meta-analyses. RESULTS: We identified 185 studies, of which 14 met inclusion criteria."},{"source_id":"source_25","study":"Impact of meditation on brain age derived from multimodal neuroimaging in experts and older adults from a randomized trial","doi":"10.1038/s41598-025-21490-9","url":"https://doi.org/10.1038/s41598-025-21490-9","support_kind":"cited_as_match","cited_as":"Haudry 2025","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"primary","excerpt":"Meditation is thought to promote healthy aging by improving mental health, preserving brain integrity and reducing Alzheimer's disease risk. We examined the impact of long-term meditation expertise and an 18-month meditation training on brain aging in older adults using machine learning. We included 25 Older Expert Meditators (OldExpMed) with > 20 years of practice and 135 Cognitively Unimpaired Older Adults (CUOA) from the Age-Well randomized controlled trial. CUOA were randomized (1:1:1) into an 18-month meditation training, a non-native language training, and a no intervention group. Brain age was predicted using a machine learning model trained on gray and white matter volume and glucose metabolism data from ADNI and replicated with a second model. Brain Predicted Age Difference (BrainPAD) was computed as the gap between predicted and chronological age. We assessed meditation expertise effects on BrainPAD, its links with meditation hours, cognitive, and affective measures, and the impact of 18-month training. Compared to CUOA, OldExpMed exhibited significantly lower/more negative BrainPAD, linked to meditation hours, mental imagery, and prosocialness."},{"source_id":"source_32","study":"An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors","doi":"10.3389/fnagi.2022.941864","url":"https://doi.org/10.3389/fnagi.2022.941864","support_kind":"cited_as_match","cited_as":"Mouches 2022","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"primary","excerpt":"The brain age gap (BAG) has been shown to capture accelerated brain aging patterns and might serve as a biomarker for several neurological diseases. Moreover, it was also shown that it captures other biological information related to modifiable cardiovascular risk factors. Previous studies have explored statistical relationships between the BAG and cardiovascular risk factors. However, none of those studies explored causal relationships between the BAG and cardiovascular risk factors. In this work, we employ causal structure discovery techniques and define a Bayesian network to model the assumed causal relationships between the BAG, estimated using morphometric T1-weighted magnetic resonance imaging brain features from 2025 adults, and several cardiovascular risk factors. This setup allows us to not only assess observed conditional probability distributions of the BAG given cardiovascular risk factors, but also to isolate the causal effect of each cardiovascular risk factor on BAG using causal inference. Results demonstrate the feasibility of the proposed causal analysis approach by illustrating intuitive causal relationships between variables."},{"source_id":"source_48","study":"Evaluating the Impact of Cardiometabolic Risk Factors on Neuroimaging‐Based Brain Age: A Deep Learning Approach","doi":"10.1002/alz.095769","url":"https://doi.org/10.1002/alz.095769","support_kind":"cited_as_match","cited_as":"Tavakoli 2025","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"primary","excerpt":"This study aims to investigate the relationship between effect of cardiometabolic risk factors (CMRF) and accelerated brain aging, T1‐weighted 3D MRIs from a total of 965 participants (47‐81 years, 53% female) in the UKBiobank data were included in this study. (80%( = 772) training and 20%( = 193) validation). Significant associations with the BAG were observed for sbp across genders with a p‐value of 0.0415, with gender‐specific correlations found for cholesterol and sbp in females (p = 0.0242 and 0.0163) and no significant correlations between males’ BAG and any CMRF."}],"candidate_sources":[]},{"claim_id":"claim_30","claim":"Several outcome claims rest on a single source and therefore cannot be internally replicated within the corpus. The Tai-Chi/balance-exercise MRI analysis (Narula 2026) and the unilateral exercise-in-schizophrenia brain-age-gap finding (Yilmaz 2025, n=134) similarly stand alone, so their directional signals — including the null and unclear direction codes — cannot be triangulated, and the synthesis cannot promote any of them to a robust claim without external replication.","citation_support":[{"source_id":"source_16","study":"Brain age gap reduction following exercise mirrors clinical improvements in schizophrenia spectrum disorders","doi":"10.1016/j.nicl.2025.103881","url":"https://doi.org/10.1016/j.nicl.2025.103881","support_kind":"cited_as_match","cited_as":"Yilmaz 2025","population":"not extracted","endpoint":"not extracted","effect":"not extracted","directness":"primary","excerpt":"Schizophrenia spectrum disorders (SSD) are associated with accelerated brain aging, reflected in an increased brain age gap. This gap serves as a biomarker, indicating poorer brain health, cognitive deficits, and greater severity in specific symptom domains. Exercise holds promise as an adjunct therapy to mitigate these deficits by potentially promoting brain recovery. However, the extent of overall improvements in brain health following exercise, along with their predictors and relationships to symptom clusters, are yet to be determined. This study examined the brain age gap metric as a quantitative indicator of brain recovery in response to exercise. To achieve this, we aggregated data from two randomized controlled trials, analyzing baseline (n = 134) and 3- or 6-month post-exercise (n = 46) data from individuals with SSD. Our findings revealed that patients with a higher baseline body mass index (BMI) demonstrated greater brain recovery, as evidenced by a reduced brain age gap post-exercise."}],"candidate_sources":[]}]}},{"name":"claim_graph.json","media_type":"application/json","content":{"publication_id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","content_hash":"sha256:d594d5a107fd43f8a65fc7f3d86ad5496bdf3c9fba839084863cd586d82bfcfb","nodes":[{"id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","type":"publication","title":"Hypothesis-Generating Brief: Brain age MRI — full paper"},{"id":"claim_1","type":"claim","text":"Evidence-honesty note: 63/65 retained sources are coded as null or no extracted directional signal; this corpus is non-supportive for clinical efficacy claims and hypothesis-generating only. Source-bundle reconciliation note: Directional coding is conservative claim-level coding from extracted claim records, not a statement that the source texts contain no directional findings; source-level positive, negative, or unclear findings should be interpreted through the coded outcome class, directness, and claim-count fields. 64/65 retained sources are indirect, review-level, adjacent, or mechanistic and are used only to bound interpretation. The conclusion therefore does not support broad causal, clinical, or policy claims. This paper synthesizes evidence on Brain age MRI across 65 accepted source papers and 1135 high-confidence extracted claims. The evidence profile contains 1 direct clinical source, 64 adjacent clinical sources, and no sources classified primarily as mechanistic or model-system evidence, with 66 cross-study disagreements across the evidence base. Positive study-level signals are summarized in the cardiometabolic outcome class, null signals in the contextual adjacent evidence, safety and comorbidity, cardiometabolic outcome classes, and negative signals in no dominant outcome class."},{"id":"claim_2","type":"claim","text":"Evidence-honesty note: 63/65 retained sources are coded as null or no extracted directional signal; this corpus is non-supportive for clinical efficacy claims and hypothesis-generating only. Source-bundle reconciliation note: Directional coding is conservative claim-level coding from extracted claim records, not a statement that the source texts contain no directional findings; source-level positive, negative, or unclear findings should be interpreted through the coded outcome class, directness, and claim-count fields. 64/65 retained sources are indirect, review-level, adjacent, or mechanistic and are used only to bound interpretation. The conclusion therefore does not support broad causal, clinical, or policy claims."},{"id":"claim_3","type":"claim","text":"This paper synthesizes evidence on Brain age MRI across 65 accepted source papers and 1135 high-confidence extracted claims."},{"id":"claim_4","type":"claim","text":"The evidence profile contains 1 direct clinical source, 64 adjacent clinical sources, and no sources classified primarily as mechanistic or model-system evidence, with 66 cross-study disagreements across the evidence base."},{"id":"claim_5","type":"claim","text":"Positive study-level signals are summarized in the cardiometabolic outcome class, null signals in the contextual adjacent evidence, safety and comorbidity, cardiometabolic outcome classes, and negative signals in no dominant outcome class. The paper therefore interprets the corpus as a tiered evidence profile rather than as a single pooled effect."},{"id":"claim_6","type":"claim","text":"The conclusion is that Brain age MRI remains a bounded geroscience case: the retained clinical and adjacent evidence profile defines the scope for targeted testing, while mixed and null findings limit any unqualified anti-aging claim."},{"id":"claim_7","type":"claim","text":"Risk-of-bias appraisal summary: The public appraisal artifact reports 65 source-level rating row(s) using ROBINS-I, RoB-2, SYRCLE; overall ratings are some concerns=65. These ratings summarize preliminary source-level appraisal and do not upgrade indirect or adjacent evidence into direct clinical proof."},{"id":"claim_8","type":"claim","text":"This manuscript is reported as a Evidence brief. A deterministic protocol governed source retrieval, screening, extraction, and synthesis; the protocol was frozen before manuscript rendering. The full audit trail is in the supplementary `methods_pack.json` and the timestamped submission directory `synthesis-brain_age_mri-v06-DAILY-2026-06-21T15-19-07Z-R2`."},{"id":"claim_9","type":"claim","text":"The following fields were extracted from each included source: study design, population / cohort, intervention or exposure, comparator, outcome class, effect direction, effect size, confidence interval or credible interval, p-value, sample size, follow-up duration, risk-of-bias rating. Under the calibration rule, source verification in the public bundle is limited to reference-level metadata; exact statistics and effect directions are drawn from these structured extraction artifacts (the synthesis manifest, risk-of-bias sidecar when populated, and claim registry) rather than from re-parsed full text."},{"id":"claim_10","type":"claim","text":"Risk-of-bias framework assignment follows study design (RoB-2 for RCTs, ROBINS-I for non-randomised studies, AMSTAR-2 for systematic reviews / meta-analyses). Public appraisal claims are limited to populated `risk_of_bias.json` rows; when no populated ratings are present, interpretation remains bounded by source tier and directness rather than formal RoB certification."},{"id":"claim_11","type":"claim","text":"Evidence-tension synthesis: claims grouped by outcome class (cardiometabolic, cognitive, contextual adjacent evidence, frailty, immune and inflammation, muscle function, safety and comorbidity); within-class agreement, disagreement, and directness gaps surfaced explicitly. Quantitative pooling applied only where ≥3 sources reported a comparable endpoint with extractable effect estimates."},{"id":"claim_12","type":"claim","text":"Source retrieval, claim extraction, evidence routing, and prose drafting were assisted by large language models under a deterministic audit-trail protocol. Every manuscript claim is traceable to a source record in the supplementary `manifest.json`. Final eligibility and interpretation decisions are author-verified."},{"id":"claim_13","type":"claim","text":"Directional coding note: Null or no extracted directional signal means no coded positive, negative, or mixed effect was extracted for that specific outcome class; it is not an absence-of-support finding. Positive, negative, mixed, unclear, and null are outcome-specific codes, so a bounded rationale can be supported by adjacent or different outcome evidence while another outcome remains null or unclear. Contextual claims contain bibliographic background, mechanism, methods, exposure definitions, or population context rather than effect-direction evidence. When an outcome-class summary uses no extracted directional signal, it should state the source proportion, such as X/Y sources, to avoid ambiguity."},{"id":"claim_14","type":"claim","text":"RCT-count reconciliation: Reviewer feedback indicates that at least one included source aggregates more than one randomized trial, so this manuscript treats any prior single-RCT wording as a source-coding count, not as a claim that the underlying trial evidence contains only one RCT."},{"id":"claim_15","type":"claim","text":"Substantive evidence synthesis: The manifest includes 65 retained sources, 1 direct-source row(s), and directional coding across null=63, positive=1, unclear=1. Representative source-level signals are: Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60; Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43; Narula 2026: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=43; Bao 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=43. These signals inform the bounded conclusion by separating effect direction from evidence tier/directness; indirect, review-level, mechanistic, or contextual evidence remains hypothesis-generating."},{"id":"claim_16","type":"claim","text":"Key findings from source synthesis: First, the strongest positive or favorable signals are treated as narrow source-level signals, not broad clinical proof (Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60). Second, negative, mixed, unclear, or no-directional-signal rows are given equal interpretive weight (Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43). Third, the bounded conclusion follows from the balance of source direction, outcome class, evidence tier, and directness rather than from source count alone."},{"id":"claim_17","type":"claim","text":"| Evidence domain | Corpus slice | Strongest signal | Directness | Main limitation |"},{"id":"claim_18","type":"claim","text":"| Contextual Adjacent Evidence | n=51; claims=842 | no extracted directional signal in 50/51 sources | 1 direct; 47 indirect; 3 review | limited corpus depth in this outcome class |"},{"id":"claim_19","type":"claim","text":"Outcome-class note:** Contextual Adjacent Evidence denotes background, boundary-condition, or adjacent-outcome sources. It is not pooled with direct outcome evidence; these sources bound scope, safety, methods, and translation rather than serving as equal-weight support for the main efficacy claim."},{"id":"claim_20","type":"claim","text":"This evidence brief reports outcome packets as a map of retained evidence rather than as a full journal Results narrative or pooled effect estimate."},{"id":"claim_21","type":"claim","text":"51 included sources were assigned to this outcome class. Directional coding: null=50, unclear=1. Directness coding: direct=1, indirect=47, review=3."},{"id":"claim_22","type":"claim","text":"5 included sources were assigned to this outcome class. Directional coding: null=5. Directness coding: indirect=5."},{"id":"claim_23","type":"claim","text":"3 included sources were assigned to this outcome class. Directional coding: null=2, positive=1. Directness coding: indirect=3."},{"id":"claim_24","type":"claim","text":"2 included sources were assigned to this outcome class. Directional coding: null=2. Directness coding: indirect=2."},{"id":"claim_25","type":"claim","text":"2 included sources were assigned to this outcome class. Directional coding: null=2. Directness coding: indirect=2."},{"id":"claim_26","type":"claim","text":"1 included source were assigned to this outcome class. Directional coding: null=1. Directness coding: indirect=1."},{"id":"claim_27","type":"claim","text":"1 included source were assigned to this outcome class. Directional coding: null=1. Directness coding: indirect=1."},{"id":"claim_28","type":"claim","text":"Verification note:** Reference-only or no-abstract records are treated as verification-limited context, not as equal-weight support for the main claim."},{"id":"claim_29","type":"claim","text":"The curated corpus on brain-age MRI is overwhelmingly observational, with a single randomized trial (Haudry 2025, an RCT with a mechanistic/biomarker endpoint) supplying direct interventional evidence in older adults; no long-term mortality or hard-outcome RCTs in non-diabetic or non-meditation populations are present, so causal claims about anti-aging benefit cannot be sustained. The cardiometabolic and immune-inflammation outcome classes are represented only by cohort designs (Levakov 2023, Motaghi 2025, Huang 2025, Mouches 2022, Derboghossian 2024, Selitser 2025, Tavakoli 2025), and even within those cohorts effect directions diverge — Levakov 2023 reports a positive weight-loss effect after 18 months of lifestyle intervention while Mouches 2022 and Derboghossian 2024 report null associations between cardiovascular risk factors and brain-age gap, leaving the cardiometabolic signal unresolved. The absence of replication-grade interventional evidence means the headline synthesis is constrained to biomarker associations rather than clinical benefit, and the headline-level null-vs-positive tension in cardiometabolic outcomes is not adjudicable from this corpus alone."},{"id":"claim_30","type":"claim","text":"Several outcome claims rest on a single source and therefore cannot be internally replicated within the corpus. The Tai-Chi/balance-exercise MRI analysis (Narula 2026) and the unilateral exercise-in-schizophrenia brain-age-gap finding (Yilmaz 2025, n=134) similarly stand alone, so their directional signals — including the null and unclear direction codes — cannot be triangulated, and the synthesis cannot promote any of them to a robust claim without external replication."},{"id":"source_1","type":"source","study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","year":2025,"doi":"10.1097/JS9.0000000000002746","url":"https://doi.org/10.1097/JS9.0000000000002746","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Huang 2025","excerpt":"BACKGROUND: The peripheral immune system is essential for maintaining central nervous system homeostasis. This study investigates the effects of peripheral immune markers on accelerated brain aging and dementia using brain-predicted age difference based on neuroimaging. METHODS: By leveraging data from the UK Biobank, Cox regression was used to explore the relationship between peripheral immune markers and dementia, and multivariate linear regression to assess associations between peripheral immune biomarkers and brain structure. Additionally, we established a brain age prediction model using simple fully convolutional network (SFCN) deep learning architecture. Analysis of the resulting brain-predicted age difference (PAD) revealed relationships between accelerated brain aging, peripheral immune markers, and dementia. RESULTS: During the median follow-up period of 14.3 years, 4277 dementia cases were observed among 322 761 participants. Both innate and adaptive immune markers correlated with dementia risk. NLR showed the strongest association with dementia risk (hazard ratio = 1.14; 95% CI: 1.11-1.18, P < 0.001)."},{"id":"source_2","type":"source","study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","year":2022,"doi":"10.1002/hbm.26066","url":"https://doi.org/10.1002/hbm.26066","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ran 2022","excerpt":"Neuroimaging-driven brain age estimation has become popular in measuring brain aging and identifying neurodegenerations. However, the single estimated brain age (gap) compromises regional variations of brain aging, losing spatial specificity across diseases which is valuable for early screening. In this study, we combined brain age modeling with Shapley Additive Explanations to measure brain aging as a feature contribution vector underlying spatial pathological aging mechanism. Specifically, we regressed age with volumetric brain features using machine learning to construct the brain age model, and model-agnostic Shapley values were calculated to attribute regional brain aging for each subject's age estimation, forming the brain age vector. Spatial specificity of the brain age vector was evaluated among groups of normal aging, prodromal Parkinson disease (PD), stable mild cognitive impairment (sMCI), and progressive mild cognitive impairment (pMCI). Machine learning methods were adopted to examine the discriminability of the brain age vector in early disease screening, compared with the other two brain aging metrics (single brain age gap, regional brain age gaps) and brain volumes."},{"id":"source_3","type":"source","study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","year":2023,"doi":"10.7554/eLife.83604","url":"https://doi.org/10.7554/eLife.83604","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Levakov 2023","excerpt":"BACKGROUND: Obesity negatively impacts multiple bodily systems, including the central nervous system. Retrospective studies that estimated chronological age from neuroimaging have found accelerated brain aging in obesity, but it is unclear how this estimation would be affected by weight loss following a lifestyle intervention. METHODS: In a sub-study of 102 participants of the Dietary Intervention Randomized Controlled Trial Polyphenols Unprocessed Study (DIRECT-PLUS) trial, we tested the effect of weight loss following 18 months of lifestyle intervention on predicted brain age based on magnetic resonance imaging (MRI)-assessed resting-state functional connectivity (RSFC). We further examined how dynamics in multiple health factors, including anthropometric measurements, blood biomarkers, and fat deposition, can account for changes in brain age. RESULTS: To establish our method, we first demonstrated that our model could successfully predict chronological age from RSFC in three cohorts (n=291;358;102). We then found that among the DIRECT-PLUS participants, 1% of body weight loss resulted in an 8.9 months' attenuation of brain age."},{"id":"source_4","type":"source","study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","year":2025,"doi":"10.1093/braincomms/fcaf344","url":"https://doi.org/10.1093/braincomms/fcaf344","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tanner 2025","excerpt":"The interplay between chronic musculoskeletal pain and brain ageing is complex. Studies employing machine learning models to assess relationships between brain age and chronic pain generally show that higher chronic pain severity associates with older brain age. Analyses to date have not considered individual and community-level socioenvironmental risk factors or behavioural/psychosocial protective factors as potential modifiers of cross-sectional and longitudinal brain age. This study aimed to elucidate the relationships between chronic pain, socioenvironmental risk, behavioural/psychosocial protective factors, and brain ageing. The sample comprised 197 adults (Men:Women = 68:129) from a prospective observational cohort study. Most individuals reported knee pain and were with/at risk of osteoarthritis. A subset of 128 participants (Men:Women = 41:87) completed a follow-up MRI session at 2 years and were included in the longitudinal analysis (Aim 2). Participants were 45-85 years of age and self-identified as non-Hispanic Black or non-Hispanic White."},{"id":"source_5","type":"source","study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","year":2026,"doi":"10.1007/s40520-026-03322-6","url":"https://doi.org/10.1007/s40520-026-03322-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Narula 2026","excerpt":"Physical exercise is known to delay the cognitive decline in the elderly. However, the effect of low-impact balance exercises such as yoga or Tai chi has not been explored in detail. This cross-sectional observational study used brain magnetic resonance imaging data to quantify and compare various brain structures between neurologically healthy adults aged between 55 and 65, divided into Control Group and Balance Exercise (BE) Group based on the self-reported balance exercise status. Various brain attributes such as brain age, cortical and subcortical volume, thickness, surface area, and mean curvature were extracted and computed using machine learning algorithm software like brainageR and FreeSurfer. Clinical functional assessments (balance, vestibular and cognitive measures) were also conducted for the participants. Statistical analyses were performed to determine any differences between the groups at a significance level of 5%."},{"id":"source_6","type":"source","study":"Cardiometabolic risk factors and brain age: a meta-analysis to quantify brain structural differences related to diabetes, hypertension, and obesity","year":2025,"doi":"10.1503/jpn.240105","url":"https://doi.org/10.1503/jpn.240105","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"review-level","cited_as":"Selitser 2025","excerpt":"BACKGROUND: Cardiometabolic risk factors - including diabetes, hypertension, and obesity - have long been linked with adverse health outcomes such as strokes, but more subtle brain changes in regional brain volumes and cortical thickness associated with these risk factors are less understood. Computer models can now be used to estimate brain age based on structural magnetic resonance imaging data, and subtle brain changes related to cardiometabolic risk factors may manifest as an older-appearing brain in prediction models; thus, we sought to investigate the relationship between cardiometabolic risk factors and machine learning-predicted brain age. METHODS: We performed a systematic search of PubMed and Scopus. We used the brain age gap, which represents the difference between one's predicted and chronological age, as an index of brain structural integrity. We calculated the Cohen d statistic for mean differences in the brain age gap of people with and without diabetes, hypertension, or obesity and performed random effects meta-analyses. RESULTS: We identified 185 studies, of which 14 met inclusion criteria."},{"id":"source_7","type":"source","study":"Prediction of brain age using quantitative parameters of synthetic magnetic resonance imaging","year":2022,"doi":"10.3389/fnagi.2022.963668","url":"https://doi.org/10.3389/fnagi.2022.963668","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Bao 2022","excerpt":"OBJECTIVE: Brain tissue changes dynamically during aging. The purpose of this study was to use synthetic magnetic resonance imaging (syMRI) to evaluate the changes in relaxation values in different brain regions during brain aging and to construct a brain age prediction model. MATERIALS AND METHODS: Quantitative MRI was performed on 1,000 healthy people (≥ 18 years old) from September 2020 to October 2021. T1, T2 and proton density (PD) values were simultaneously measured in 17 regions of interest (the cerebellar hemispheric cortex, pons, amygdala, hippocampal head, hippocampal tail, temporal lobe, occipital lobe, frontal lobe, caudate nucleus, lentiform nucleus, dorsal thalamus, centrum semiovale, parietal lobe, precentral gyrus, postcentral gyrus, substantia nigra, and red nucleus). The relationship between the relaxation values and age was investigated. In addition, we analyzed the relationship between brain tissue values and sex. Finally, the participants were divided into two age groups: < 60 years old and ≥ 60 years old. Logistic regression analysis was carried out on the two groups of data."},{"id":"source_8","type":"source","study":"Predictive values of pre-treatment brain age models to rTMS effects in neurocognitive disorder with depression: Secondary analysis of a randomised sham-controlled clinical trial","year":2024,"doi":"10.1080/19585969.2024.2373075","url":"https://doi.org/10.1080/19585969.2024.2373075","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Lu 2024","excerpt":"INTRODUCTION: One major challenge in developing personalised repetitive transcranial magnetic stimulation (rTMS) is that the treatment responses exhibited high inter-individual variations. Brain morphometry might contribute to these variations. This study sought to determine whether individual's brain morphometry could predict the rTMS responders and remitters. METHODS: This was a secondary analysis of data from a randomised clinical trial that included fifty-five patients over the age of 60 with both comorbid depression and neurocognitive disorder. Based on magnetic resonance imaging scans, estimated brain age was calculated with morphometric features using a support vector machine. Brain-predicted age difference (brain-PAD) was computed as the difference between brain age and chronological age. RESULTS: The rTMS responders and remitters had younger brain age. Every additional year of brain-PAD decreased the odds of relieving depressive symptoms by ∼25.7% in responders (Odd ratio [OR] = 0.743, p = .045) and by ∼39.5% in remitters (OR = 0.605, p = .022) in active rTMS group."},{"id":"source_9","type":"source","study":"Association of Brain Age, Lesion Volume, and Functional Outcome in Patients With Stroke","year":2023,"doi":"10.1212/WNL.0000000000207219","url":"https://doi.org/10.1212/WNL.0000000000207219","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Liew 2023","excerpt":"BACKGROUND AND OBJECTIVES: Functional outcomes after stroke are strongly related to focal injury measures. However, the role of global brain health is less clear. In this study, we examined the impact of brain age, a measure of neurobiological aging derived from whole-brain structural neuroimaging, on poststroke outcomes, with a focus on sensorimotor performance. We hypothesized that more lesion damage would result in older brain age, which would in turn be associated with poorer outcomes. Related, we expected that brain age would mediate the relationship between lesion damage and outcomes. Finally, we hypothesized that structural brain resilience, which we define in the context of stroke as younger brain age given matched lesion damage, would differentiate people with good vs poor outcomes. METHODS: We conducted a cross-sectional observational study using a multisite dataset of 3-dimensional brain structural MRIs and clinical measures from the ENIGMA Stroke Recovery. Brain age was calculated from 77 neuroanatomical features using a ridge regression model trained and validated on 4,314 healthy controls."},{"id":"source_10","type":"source","study":"Brain age revisited: Investigating the state vs. trait hypotheses of EEG-derived brain-age dynamics with deep learning","year":2024,"doi":"10.1162/imag_a_00210","url":"https://doi.org/10.1162/imag_a_00210","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Gemein 2024","excerpt":"The brain's biological age has been considered as a promising candidate for a neurologically significant biomarker. However, recent results based on longitudinal magnetic resonance imaging (MRI) data have raised questions on its interpretation. A central question is whether an increased biological age of the brain is indicative of brain pathology and if changes in brain age correlate with diagnosed pathology (state hypothesis). Alternatively, could the discrepancy in brain age be a stable characteristic unique to each individual (trait hypothesis)? To address this question, we present a comprehensive study on brain aging based on clinical Electroencephalography (EEG), which is complementary to previous MRI-based investigations. We apply a state-of-the-art temporal convolutional network (TCN) to the task of age regression. We train on recordings of the Temple University Hospital EEG Corpus (TUEG) explicitly labeled as non-pathological and evaluate on recordings of subjects with non-pathological as well as pathological recordings, both with examinations at a single point in time TUH Abnormal EEG Corpus (TUAB) and repeated examinations over time."},{"id":"source_11","type":"source","study":"Machine Learning–Based Sleep Electroencephalographic Brain Age Index and Dementia Risk","year":2026,"doi":"10.1001/jamanetworkopen.2026.1521","url":"https://doi.org/10.1001/jamanetworkopen.2026.1521","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Sun 2026","excerpt":"IMPORTANCE: Microstructures of sleep electroencephalography (EEG) are closely related to cognition and undergo age-dependent changes. However, their multidimensional nature makes them challenging to interpret using conventional approaches. The machine learning-based EEG brain age index (BAI) measures the deviation between sleep EEG-based brain age and chronological age. OBJECTIVE: To determine the association between sleep BAI and incident dementia in community-dwelling populations. DATA SOURCES: For this individual participant data (IPD) meta-analysis, sleep study data from 5 community-based longitudinal cohorts were pooled. These cohorts included the Multi-Ethnic Study of Atherosclerosis (MESA; 2010-2013), the Atherosclerosis Risk in Communities (ARIC) study (1987-1989), the Framingham Heart Study-Offspring Study (FHS-OS; 1995-1998), the Osteoporotic Fractures in Men Study (MrOS; 2003-2005), and the Study of Osteoporotic Fractures (SOF; 2002-2004). STUDY SELECTION: Adults (aged ≥18 years) without dementia at the time of polysomnography were included."},{"id":"source_12","type":"source","study":"MRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters","year":2024,"doi":"10.1177/11795735241266556","url":"https://doi.org/10.1177/11795735241266556","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Lu 2024b","excerpt":"BACKGROUND: Brain age model, including estimated brain age and brain-predicted age difference (brain-PAD), has shown great potentials for serving as imaging markers for monitoring normal ageing, as well as for identifying the individuals in the pre-diagnostic phase of neurodegenerative diseases. PURPOSE: This study aimed to investigate the brain age models in normal ageing and mild cognitive impairments (MCI) converters and their values in classifying MCI conversion. METHODS: Pre-trained brain age model was constructed using the structural magnetic resonance imaging (MRI) data from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) project (N = 609). The tested brain age model was built using the baseline, 1-year and 3-year follow-up MRI data from normal ageing (NA) adults (n = 32) and MCI converters (n = 22) drew from the Open Access Series of Imaging Studies (OASIS-2). The quantitative measures of morphometry included total intracranial volume (TIV), gray matter volume (GMV) and cortical thickness. Brain age models were calculated based on the individual's morphometric features using the support vector machine (SVM) algorithm."},{"id":"source_13","type":"source","study":"Multimodal brain age estimates relate to Alzheimer disease biomarkers and cognition in early stages: a cross-sectional observational study","year":2023,"doi":"10.7554/eLife.81869","url":"https://doi.org/10.7554/eLife.81869","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Millar 2023","excerpt":"BACKGROUND: Estimates of 'brain-predicted age' quantify apparent brain age compared to normative trajectories of neuroimaging features. The brain age gap (BAG) between predicted and chronological age is elevated in symptomatic Alzheimer disease (AD) but has not been well explored in presymptomatic AD. Prior studies have typically modeled BAG with structural MRI, but more recently other modalities, including functional connectivity (FC) and multimodal MRI, have been explored. METHODS: We trained three models to predict age from FC, structural (S), or multimodal MRI (S+FC) in 390 amyloid-negative cognitively normal (CN/A-) participants (18-89 years old). In independent samples of 144 CN/A-, 154 CN/A+, and 154 cognitively impaired (CI; CDR > 0) participants, we tested relationships between BAG and AD biomarkers of amyloid and tau, as well as a global cognitive composite. RESULTS: All models predicted age in the control training set, with the multimodal model outperforming the unimodal models. All three BAG estimates were significantly elevated in CI compared to controls. FC-BAG was significantly reduced in CN/A+ participants compared to CN/A-."},{"id":"source_14","type":"source","study":"Increased MRI-based Brain Age in chronic migraine patients","year":2023,"doi":"10.1186/s10194-023-01670-6","url":"https://doi.org/10.1186/s10194-023-01670-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Navarro-Gonzalez 2023","excerpt":"INTRODUCTION: Neuroimaging has revealed that migraine is linked to alterations in both the structure and function of the brain. However, the relationship of these changes with aging has not been studied in detail. Here we employ the Brain Age framework to analyze migraine, by building a machine-learning model that predicts age from neuroimaging data. We hypothesize that migraine patients will exhibit an increased Brain Age Gap (the difference between the predicted age and the chronological age) compared to healthy participants. METHODS: We trained a machine learning model to predict Brain Age from 2,771 T1-weighted magnetic resonance imaging scans of healthy subjects. The processing pipeline included the automatic segmentation of the images, the extraction of 1,479 imaging features (both morphological and intensity-based), harmonization, feature selection and training inside a 10-fold cross-validation scheme."},{"id":"source_15","type":"source","study":"Novel Volumetric and Surface-Based Magnetic Resonance Indices of the Aging Brain – Does Male and Female Brain Age in the Same Way?","year":2021,"doi":"10.3389/fneur.2021.645729","url":"https://doi.org/10.3389/fneur.2021.645729","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Podgorski 2021","excerpt":"Introduction: Novel post-processing methods allow not only for assessment of brain volumetry or cortical thickness based on magnetic resonance imaging (MRI) but also for more detailed analysis of cortical shape and complexity using parameters such as sulcal depth, gyrification index, or fractal dimension. The aim of this study was to analyze changes in brain volumetry and other cortical indices during aging in men and women. Material and Methods: Material consisted of 697 healthy volunteers (aged 38-80 years; M/F, 264/443) who underwent brain MRI using a 1.5-T scanner. Voxel-based volumetry of total gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) was performed followed by assessment of cortical parameters [cortical thickness (CT), sulcal depth (SD), gyrification index (GI), and fractal dimension (FD)] in 150 atlas locations using surface-based morphometry with a region-based approach. All parameters were compared among seven age groups (grouped every 5 years) separately for men and women. Additionally, percentile curves for men and women were provided for total volumes of GM, WM, and CSF."},{"id":"source_16","type":"source","study":"Brain age gap reduction following exercise mirrors clinical improvements in schizophrenia spectrum disorders","year":2025,"doi":"10.1016/j.nicl.2025.103881","url":"https://doi.org/10.1016/j.nicl.2025.103881","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Yilmaz 2025","excerpt":"Schizophrenia spectrum disorders (SSD) are associated with accelerated brain aging, reflected in an increased brain age gap. This gap serves as a biomarker, indicating poorer brain health, cognitive deficits, and greater severity in specific symptom domains. Exercise holds promise as an adjunct therapy to mitigate these deficits by potentially promoting brain recovery. However, the extent of overall improvements in brain health following exercise, along with their predictors and relationships to symptom clusters, are yet to be determined. This study examined the brain age gap metric as a quantitative indicator of brain recovery in response to exercise. To achieve this, we aggregated data from two randomized controlled trials, analyzing baseline (n = 134) and 3- or 6-month post-exercise (n = 46) data from individuals with SSD. Our findings revealed that patients with a higher baseline body mass index (BMI) demonstrated greater brain recovery, as evidenced by a reduced brain age gap post-exercise."},{"id":"source_17","type":"source","study":"Brain age in genetic and idiopathic Parkinson's disease","year":2024,"doi":"10.1093/braincomms/fcae382","url":"https://doi.org/10.1093/braincomms/fcae382","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Teipel 2024","excerpt":"The brain-age gap, i.e. the difference between the brain age estimated from structural MRI data and the chronological age of an individual, has been proposed as a summary measure of brain integrity in neurodegenerative diseases. Here, we aimed to determine the brain-age gap in genetic and idiopathic Parkinson's disease and its association with surrogate markers of Alzheimer's disease and Parkinson's disease pathology and with rates of cognitive and motor function decline. We studied 1200 cases from the Parkinson's Progression Markers Initiative cohort, including idiopathic Parkinson's disease, asymptomatic and clinical mutation carriers in the leucine-rich repeat kinase 2 gene (LRRK2) and the glucocerebrosidase gene (GBA), and normal controls using a cohort study design. For comparison, we studied 187 Alzheimer's disease dementia cases and 254 controls from the Alzheimer's Disease Neuroimaging Initiative cohort. We used Bayesian ANOVA to determine associations of the brain-age gap with diagnosis, and baseline measures of motor and cognitive function, dopamine transporter activity and CSF markers of Alzheimer's disease type amyloid-β42 and phosphotau pathology."},{"id":"source_18","type":"source","study":"Genome-wide analysis of brain age identifies 59 associated loci and unveils relationships with mental and physical health","year":2025,"doi":"10.1038/s43587-025-00962-7","url":"https://doi.org/10.1038/s43587-025-00962-7","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Jawinski 2025","excerpt":"Neuroimaging and machine learning are advancing research into the mechanisms of biological aging. In this field, 'brain age gap' has emerged as a promising magnetic resonance imaging-based biomarker that quantifies the deviation between an individual's biological and chronological age of the brain. Here we conducted an in-depth genomic analysis of the brain age gap and its relationships with over 1,000 health traits. Genome-wide analyses in up to 56,348 individuals unveiled a heritability of 23-29% attributable to common genetic variants and highlighted 59 associated loci (39 novel). The leading locus encompasses MAPT, encoding the tau protein central to Alzheimer's disease. Genetic correlations revealed relationships with mental health, physical health, lifestyle and socioeconomic traits, including depressed mood, diabetes, alcohol intake and income. Mendelian randomization indicated a causal role of high blood pressure and type 2 diabetes in accelerated brain aging. Our study highlights key genes and pathways related to neurogenesis, immune-system-related processes and small GTPase binding, laying the foundation for further mechanistic exploration."},{"id":"source_19","type":"source","study":"Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study","year":2026,"doi":"10.1016/j.landig.2025.100942","url":"https://doi.org/10.1016/j.landig.2025.100942","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Park 2026","excerpt":"BACKGROUND: Stroke leads to complex chronic structural and functional brain changes that specifically affect motor outcomes. The brain predicted age difference (PAD) has emerged as a sensitive biomarker of both sensorimotor and cognitive function after stroke. Our previous study showed a higher global brain PAD associated with poorer motor function after stroke. However, the association between local stroke lesion load, regional brain age, and motor impairment is unclear. This study aimed to investigate the associations between focal lesion damage, regional brain PAD in both hemispheres, and motor outcomes in chronic stroke, and to identify key predictors of motor impairment. METHODS: In this multicohort, retrospective, observational study, we included individuals with chronic unilateral stroke (>180 days post stroke) from the ENIGMA Stroke Recovery Working Group dataset and used individuals from the UK Biobank cohort to train the regional brain age prediction model. Structural T1-weighted MRI scans were used to estimate regional brain PAD in 18 predefined functional subregions via a graph convolutional network algorithm."},{"id":"source_20","type":"source","study":"Developmental Brain Age Estimation From MRI Data: A Systematic Review of Deep Learning Approaches and Open Datasets","year":2025,"doi":"10.1002/jmri.70180","url":"https://doi.org/10.1002/jmri.70180","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"review-level","cited_as":"Ull 2025","excerpt":"Brain age is an emerging concept that reflects complex, time-dependent changes in brain structure, identifying departures from expected neurodevelopmental patterns. In the developing brain, accurate MRI-based age estimation is a quantitative biomarker for detecting atypical neurodevelopment, facilitating early diagnosis, guiding clinical decision-making, and potentially improving long-term outcomes. Data-driven models applied to neuroimaging have provided valuable insights into the pathogenesis of various congenital and acquired pediatric conditions. In particular, advanced deep learning approaches have recently gained prominence in a wide range of pediatric neuroimaging studies, offering state-of-the-art performance in estimating developmental brain age. In this survey, we provide a comprehensive review of the current MRI applications of deep learning methodologies for developmental brain age (fetal stage-2 years) estimation. We provide details on both clinical and technical aspects, open-access developmental MRI datasets, and compare the performance of these models utilizing evaluation metrics."},{"id":"source_21","type":"source","study":"A deep learning model for brain age prediction using minimally preprocessed T1w images as input","year":2024,"doi":"10.3389/fnagi.2023.1303036","url":"https://doi.org/10.3389/fnagi.2023.1303036","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Dartora 2024","excerpt":"INTRODUCTION: In the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction. METHODS: We used a multicohort dataset of cognitively healthy individuals (age range = 32.0-95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2-4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset's images in the cross-validation training (CNN3)."},{"id":"source_22","type":"source","study":"Association between low‐frequency oscillations in blood pressure variability and brain age derived from neuroimaging","year":2025,"doi":"10.1002/alz.70833","url":"https://doi.org/10.1002/alz.70833","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Heffernan 2025","excerpt":"INTRODUCTION: We examined the association between low-frequency oscillations in blood pressure variability (LF-BPV) at baseline (past) and 12 years later (concurrent) and BrainAGE gap (an indicator of brain health). METHODS: Participants were 110 adults (age range 37-83 years at baseline, 60% female) from the Midlife in the United States (MIDUS) study. LF-BPV (0.04-0.15 Hz) was spectrally decomposed from beat-to-beat BP waveforms acquired from finger photoplethysmography. BrainAGE was estimated using a Gaussian-process regression model applied to raw T1-weighted magnetic resonance imaging (MRI) scans. BrainAGE gap was calculated as brain age minus chronological age. RESULTS: After adjustment for covariates, higher past diastolic LF-BPV was associated with significantly reduced BrainAGE gap (β = -2.24; 95% CI -4.15, -0.32, p = 0.022), as was higher concurrent diastolic LF-BPV (β = -1.90; 95% CI -3.68, -0.12, p = 0.037). CONCLUSION: Our findings suggest that low-frequency oscillations in diastolic BPV are associated with slower brain aging relative to chronological age."},{"id":"source_23","type":"source","study":"Brain age gap, dementia risk factors and cognition in middle age","year":2024,"doi":"10.1093/braincomms/fcae392","url":"https://doi.org/10.1093/braincomms/fcae392","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Stefaniak 2024","excerpt":"Brain Age Gap has been associated with dementia in old age. Less is known relating brain age gap to dementia risk-factors or cognitive performance in middle-age. Cognitively healthy, middle-aged subjects from PREVENT-Dementia had comprehensive neuropsychological, neuroimaging and genetic assessments. Brain Ages were predicted from T1-weighted 3T MRI scans. Cognition was assessed using the COGNITO computerized test battery. 552 middle-aged participants (median [interquartile range] age 52.8 [8.7] years, 60.0% female) had baseline data, of whom 95 had amyloid PET data. Brain age gap in middle-age was associated with hypertension ( P = 0.007) and alcohol intake ( P = 0.008) but not apolipoprotein E epsilon 4 allele ( P = 0.14), amyloid centiloids ( P = 0.39) or cognitive performance ( P = 0.74). Brain age gap in middle-age is associated with modifiable dementia risk-factors, but not with genetic risk for Alzheimer's disease, amyloid deposition or cognitive performance. These results are important for understanding brain-age in middle-aged populations, which might be optimally targeted by future dementia-preventing therapies."},{"id":"source_24","type":"source","study":"The value of arterial spin labelling perfusion MRI in brain age prediction","year":2023,"doi":"10.1002/hbm.26242","url":"https://doi.org/10.1002/hbm.26242","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Dijsselhof 2023","excerpt":"Current structural MRI-based brain age estimates and their difference from chronological age-the brain age gap (BAG)-are limited to late-stage pathological brain-tissue changes. The addition of physiological MRI features may detect early-stage pathological brain alterations and improve brain age prediction. This study investigated the optimal combination of structural and physiological arterial spin labelling (ASL) image features and algorithms. Healthy participants (n = 341, age 59.7 ± 14.8 years) were scanned at baseline and after 1.7 ± 0.5 years follow-up (n = 248, mean age 62.4 ± 13.3 years). From 3 T MRI, structural (T1w and FLAIR) volumetric ROI and physiological (ASL) cerebral blood flow (CBF) and spatial coefficient of variation ROI features were constructed. Multiple combinations of features and machine learning algorithms were evaluated using the Mean Absolute Error (MAE). From the best model, longitudinal BAG repeatability and feature importance were assessed. The ElasticNetCV algorithm using T1w + FLAIR+ASL performed best (MAE = 5.0 ± 0.3 years), and better compared with using T1w + FLAIR (MAE = 6.0 ± 0.4 years, p < .01)."},{"id":"source_25","type":"source","study":"Impact of meditation on brain age derived from multimodal neuroimaging in experts and older adults from a randomized trial","year":2025,"doi":"10.1038/s41598-025-21490-9","url":"https://doi.org/10.1038/s41598-025-21490-9","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Haudry 2025","excerpt":"Meditation is thought to promote healthy aging by improving mental health, preserving brain integrity and reducing Alzheimer's disease risk. We examined the impact of long-term meditation expertise and an 18-month meditation training on brain aging in older adults using machine learning. We included 25 Older Expert Meditators (OldExpMed) with > 20 years of practice and 135 Cognitively Unimpaired Older Adults (CUOA) from the Age-Well randomized controlled trial. CUOA were randomized (1:1:1) into an 18-month meditation training, a non-native language training, and a no intervention group. Brain age was predicted using a machine learning model trained on gray and white matter volume and glucose metabolism data from ADNI and replicated with a second model. Brain Predicted Age Difference (BrainPAD) was computed as the gap between predicted and chronological age. We assessed meditation expertise effects on BrainPAD, its links with meditation hours, cognitive, and affective measures, and the impact of 18-month training. Compared to CUOA, OldExpMed exhibited significantly lower/more negative BrainPAD, linked to meditation hours, mental imagery, and prosocialness."},{"id":"source_26","type":"source","study":"Predicting brain age for veterans with traumatic brain injuries and healthy controls: an exploratory analysis","year":2025,"doi":"10.3389/fnagi.2025.1472207","url":"https://doi.org/10.3389/fnagi.2025.1472207","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Coetzee 2025","excerpt":"BACKGROUND: Traumatic brain injury (TBI) is associated with increased dementia risk. This may be driven by underlying biological changes resulting from the injury. Machine learning algorithms can use structural MRIs to give a predicted brain age (pBA). When the estimated age is greater than the chronological age (CA), this is called the brain age gap (BAg). We analyzed this outcome in men and women with and without TBI. OBJECTIVE: To determine whether factors that contribute to BAg, as estimated using the brainageR algorithm, differ between men and women who are US military Veterans with and without TBI. METHODS: In an exploratory, hypothesis-generating analysis, we analyzed data from 85 TBI patients and 22 healthy controls (HCs). High-resolution T1W images were processed using FreeSurfer 7.0. pBAs were calculated from T1s. Differences between the two groups were tested using the Mann-Whitney U. Associations between the BAg and other factors were tested using partial Pearson's r within groups, controlling for CA, followed by construction of regression models."},{"id":"source_27","type":"source","study":"Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations","year":2024,"doi":"10.3389/fninf.2024.1496143","url":"https://doi.org/10.3389/fninf.2024.1496143","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"review-level","cited_as":"Dragendorf 2024","excerpt":"INTRODUCTION: Over the past few decades, numerous researchers have explored the application of machine learning for assessing children's neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child's chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children's brain age. METHODS: The inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords \"pediatric,\" \"artificial intelligence,\" and \"brain age\" and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications."},{"id":"source_28","type":"source","study":"ASSOCIATIONS BETWEEN CARDIORESPIRATORY FITNESS, BRAIN AGE, AND NEURODEGENERATION AMONG OLDER ADULTS","year":2024,"doi":"10.1093/geroni/igae098.2304","url":"https://doi.org/10.1093/geroni/igae098.2304","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Derboghossian 2024","excerpt":"The sample (N=134) averaged 73.63 ± 5.81 years of age, 16.98 ± 2.9 years of education, 27.47 ± 5.17 in BMI, and 23.5 ± 2.18 in Montreal Cognitive Assessment scores with 51.5% male and 92.5% White. The mean brain age was 72.37±7.76 years with 2.92± 0.31mm ADSCT and 3164 ±455.51mm3 hippocampal volume."},{"id":"source_29","type":"source","study":"Toward MR protocol-agnostic, unbiased brain age predicted from clinical-grade MRIs","year":2023,"doi":"10.1038/s41598-023-47021-y","url":"https://doi.org/10.1038/s41598-023-47021-y","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Valdes-Hernandez 2023","excerpt":"The difference between the estimated brain age and the chronological age ('brain-PAD') could become a clinical biomarker. However, most brain age models were developed for research-grade high-resolution T1-weighted MRIs, limiting their applicability to clinical-grade MRIs from various protocols. We adopted a dual-transfer learning strategy to develop a model agnostic to modality, resolution, or slice orientation. We retrained a convolutional neural network (CNN) using 6281 clinical MRIs from 1559 patients, among 7 modalities and 8 scanner models. The CNN was trained to estimate brain age from synthetic research-grade magnetization-prepared rapid gradient-echo MRIs (MPRAGEs) generated by a 'super-resolution' method. The model failed with T2-weighted Gradient-Echo MRIs. The mean absolute error (MAE) was 5.86-8.59 years across the other modalities, still higher than for research-grade MRIs, but comparable between actual and synthetic MPRAGEs for some modalities. We modeled the \"regression bias\" in brain age, for its correction is crucial for providing unbiased summary statistics of brain age or for personalized brain age-based biomarkers."},{"id":"source_30","type":"source","study":"Decoding MRI-informed brain age using mutual information","year":2024,"doi":"10.1186/s13244-024-01791-9","url":"https://doi.org/10.1186/s13244-024-01791-9","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Li 2024","excerpt":"OBJECTIVE: We aimed to develop a standardized method to investigate the relationship between estimated brain age and regional morphometric features, meeting the criteria for simplicity, generalization, and intuitive interpretability. METHODS: We utilized T1-weighted magnetic resonance imaging (MRI) data from the Cambridge Centre for Ageing and Neuroscience project (N = 609) and employed a support vector regression method to train a brain age model. The pre-trained brain age model was applied to the dataset of the brain development project (N = 547). Kraskov (KSG) estimator was used to compute the mutual information (MI) value between brain age and regional morphometric features, including gray matter volume (GMV), white matter volume (WMV), cerebrospinal fluid (CSF) volume, and cortical thickness (CT). RESULTS: Among four types of brain features, GMV had the highest MI value (8.71), peaking in the pre-central gyrus (0.69). CSF volume was ranked second (7.76), with the highest MI value in the cingulate (0.87). CT was ranked third (6.22), with the highest MI value in superior temporal gyrus (0.53). WMV had the lowest MI value (4.59), with the insula showing the highest MI value (0."},{"id":"source_31","type":"source","study":"Longitudinal accelerated brain age in mild cognitive impairment and Alzheimer’s disease","year":2024,"doi":"10.3389/fnagi.2024.1433426","url":"https://doi.org/10.3389/fnagi.2024.1433426","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ly 2024","excerpt":"INTRODUCTION: Brain age is a machine learning-derived estimate that captures lower brain volume. Previous studies have found that brain age is significantly higher in mild cognitive impairment and Alzheimer's disease (AD) compared to healthy controls. Few studies have investigated changes in brain age longitudinally in MCI and AD. We hypothesized that individuals with MCI and AD would show heightened brain age over time and across the lifespan. We also hypothesized that both MCI and AD would show faster rates of brain aging (higher slopes) over time compared to healthy controls. METHODS: We utilized data from an archival dataset, mainly Alzheimer's disease Neuroimaging Initiative (ADNI) 1 with 3Tesla (3 T) data which totaled 677 scans from 183 participants. This constitutes a secondary data analysis on existing data. We included control participants (healthy controls or HC), individuals with MCI, and individuals with AD. We predicted brain age using a pre-trained model and tested for accuracy. We investigated cross-sectional differences in brain age by group [healthy controls or HC, mild cognitive impairment (MCI), and AD]."},{"id":"source_32","type":"source","study":"An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors","year":2022,"doi":"10.3389/fnagi.2022.941864","url":"https://doi.org/10.3389/fnagi.2022.941864","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Mouches 2022","excerpt":"The brain age gap (BAG) has been shown to capture accelerated brain aging patterns and might serve as a biomarker for several neurological diseases. Moreover, it was also shown that it captures other biological information related to modifiable cardiovascular risk factors. Previous studies have explored statistical relationships between the BAG and cardiovascular risk factors. However, none of those studies explored causal relationships between the BAG and cardiovascular risk factors. In this work, we employ causal structure discovery techniques and define a Bayesian network to model the assumed causal relationships between the BAG, estimated using morphometric T1-weighted magnetic resonance imaging brain features from 2025 adults, and several cardiovascular risk factors. This setup allows us to not only assess observed conditional probability distributions of the BAG given cardiovascular risk factors, but also to isolate the causal effect of each cardiovascular risk factor on BAG using causal inference. Results demonstrate the feasibility of the proposed causal analysis approach by illustrating intuitive causal relationships between variables."},{"id":"source_33","type":"source","study":"Meditation Linked to Enhanced MRI Signal Intensity in the Pineal Gland and Reduced Predicted Brain Age","year":2025,"doi":"10.1111/jpi.70033","url":"https://doi.org/10.1111/jpi.70033","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Plini 2025","excerpt":"Growing evidence demonstrates that meditation practice supports cognitive functions, including attention and interoceptive processing, and is associated with structural changes across cortical networks, including prefrontal regions and the insula. However, the extent of subcortical morphometric changes linked to meditation practice is less appreciated. A noteworthy candidate is the pineal gland, a key producer of melatonin, which regulates circadian rhythms that augment sleep-wake patterns and may also provide neuroprotective benefits to offset cognitive decline. Increased melatonin levels, as well as increased fMRI BOLD signal in the pineal gland, have been observed in meditators versus controls. However, it is not known if long-term meditators exhibit structural changes in the pineal gland linked to the lifetime duration of practice."},{"id":"source_34","type":"source","study":"Increased Brain Age Among Psychiatrically Healthy Adults Exposed to Childhood Trauma","year":2025,"doi":"10.1002/brb3.70450","url":"https://doi.org/10.1002/brb3.70450","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Hendrikse 2025","excerpt":"BACKGROUND: Adults with childhood trauma exposure may exhibit brain changes typically associated with aging and neurodegeneration (e.g., reduced tissue volume or integrity) to a greater degree than their unexposed counterparts, suggesting accelerated brain aging. Machine learning methods that predict a person's age based on their magnetic resonance imaging (MRI) brain scan may be useful for investigating aberrant brain aging following childhood trauma exposure. Emerging evidence indicates altered brain aging in adolescents with childhood trauma exposure; however, this association has not been examined in healthy adults. METHODS: We investigated the associations between childhood trauma exposure, including abuse and neglect, and brain-predicted age in psychiatrically healthy adults. \"Brain age\" predictions were generated from T1-weighted structural MRI scans using a pre-trained machine learning pipeline, namely brainageR. The differences between brain-predicted age and chronological age were calculated and associations with childhood trauma questionnaire scores were investigated using linear regression."},{"id":"source_35","type":"source","study":"Lifespan brain age prediction based on multiple EEG oscillatory features and sparse group lasso","year":2025,"doi":"10.3389/fnagi.2025.1559067","url":"https://doi.org/10.3389/fnagi.2025.1559067","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Hu 2025","excerpt":"INTRODUCTION: The neural dynamics underlying cognition and behavior change greatly during the lifespan of brain development and aging. EEG is a promising modality due to its high temporal resolution in capturing neural oscillations. Precise prediction of brain age (BA) based on EEG is crucial to screening high-risk individuals from large cohorts. However, the lifespan representation of the EEG oscillatory features (OSFs) is largely unclear, limiting practical BA applications in clinical scenarios. This study aims to build an interpretable BA prediction model through prior knowledge and sparse group lasso."},{"id":"source_36","type":"source","study":"MRI-based whole-brain elastography and volumetric measurements to predict brain age","year":2024,"doi":"10.1093/biomethods/bpae086","url":"https://doi.org/10.1093/biomethods/bpae086","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Claros-Olivares 2024","excerpt":"Brain age, as a correlate of an individual's chronological age obtained from structural and functional neuroimaging data, enables assessing developmental or neurodegenerative pathology relative to the overall population. Accurately inferring brain age from brain magnetic resonance imaging (MRI) data requires imaging methods sensitive to tissue health and sophisticated statistical models to identify the underlying age-related brain changes. Magnetic resonance elastography (MRE) is a specialized MRI technique which has emerged as a reliable, non-invasive method to measure the brain's mechanical properties, such as the viscoelastic shear stiffness and damping ratio. These mechanical properties have been shown to change across the life span, reflect neurodegenerative diseases, and are associated with individual differences in cognitive function. Here, we aim to develop a machine learning framework to accurately predict a healthy individual's chronological age from maps of brain mechanical properties. This framework can later be applied to understand neurostructural deviations from normal in individuals with neurodevelopmental or neurodegenerative conditions."},{"id":"source_37","type":"source","study":"Investigating the Association of Frailty Score and Diabetes with Relative Brain Age : Insights from the UK Biobank","year":2025,"doi":"10.1002/alz70856_103010","url":"https://doi.org/10.1002/alz70856_103010","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Motaghi 2025","excerpt":"T2D status was classified as non‐diabetic, controlled (HbA1c 6.5-7%), or uncontrolled (HbA1c >7%). Being male was associated with higher RBA (β=1.023, p <0.001)."},{"id":"source_38","type":"source","study":"Sleep Patterns in Midlife and Brain Age","year":2025,"doi":"10.1002/alz.085643","url":"https://doi.org/10.1002/alz.085643","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Cavailles 2025","excerpt":"On average 15 years later (2015‐2016), brain MRIs were obtained, and a high dimensional pattern analysis was used to determine brain age by quantifying individual differences in age‐related atrophy. After adjusting for demographics, lifestyle factors, and comorbidities, participants reporting 2‐3 and >3 poor sleep characteristics had 1.9‐year (95% confidence interval (CI) = 0.54;3.16) and 3.1‐year (95%CI = 1.14;5.11) greater brain age, respectively, compared with participants reporting 0‐1 poor sleep characteristic."},{"id":"source_39","type":"source","study":"Plasma‐based Brain Age as a Biomarker for Cognitive Health and Risk of Brain‐Related Diseases","year":2025,"doi":"10.1002/alz70856_103849","url":"https://doi.org/10.1002/alz70856_103849","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Wang 2025","excerpt":"The brain age was highly correlated with chronological age ( r = 0.72). Our findings suggest that accelerated brain aging was associated with an increased risk of AD (HR, 95% CI: 1.88 (1.74‐2.03)) and stroke (HR, 95% CI: 1.30 (1.22‐1.38))."},{"id":"source_40","type":"source","study":"Advanced brain age prediction using 3D convolutional neural network on structural MRI","year":2025,"doi":"10.1002/alz.089776","url":"https://doi.org/10.1002/alz.089776","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Ahmadi 2025","excerpt":"Utilizing T1‐weighted MRI images of n = 3,859 subjects (Table 1) from the CamCAN, NACC, and ADNI databases, this study aimed to predict brain age in four groups (CN, MCI, AD, and DLB). The 3D CNN model accurately predicted brain age in the CN test set with an AG of 0.64 ± 2.74 years and an absolute AG of 1.86 ± 2.11 years (Figure 1 and Table 1)."},{"id":"source_41","type":"source","study":"Examining the reliability of brain age algorithms under varying degrees of participant motion","year":2024,"doi":"10.1186/s40708-024-00223-0","url":"https://doi.org/10.1186/s40708-024-00223-0","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Hanson 2024","excerpt":"Brain age algorithms using data science and machine learning techniques show promise as biomarkers for neurodegenerative disorders and aging. However, head motion during MRI scanning may compromise image quality and influence brain age estimates. We examined the effects of motion on brain age predictions in adult participants with low, high, and no motion MRI scans (Original N = 148; Analytic N = 138). Five popular algorithms were tested: brainageR, DeepBrainNet, XGBoost, ENIGMA, and pyment. Evaluation metrics, intraclass correlations (ICCs), and Bland-Altman analyses assessed reliability across motion conditions. Linear mixed models quantified motion effects. Results demonstrated motion significantly impacted brain age estimates for some algorithms, with ICCs dropping as low as 0.609 and errors increasing up to 11.5 years for high motion scans. DeepBrainNet and pyment showed greatest robustness and reliability (ICCs = 0.956-0.965). XGBoost and brainageR had the largest errors (up to 13.5 RMSE) and bias with motion. Findings indicate motion artifacts influence brain age estimates in significant ways."},{"id":"source_42","type":"source","study":"Brain age gap estimation using attention-based ResNet method for Alzheimer’s disease detection","year":2024,"doi":"10.1186/s40708-024-00230-1","url":"https://doi.org/10.1186/s40708-024-00230-1","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Aghaei 2024","excerpt":"This study investigates the correlation between brain age and chronological age in healthy individuals using brain MRI images, aiming to identify potential biomarkers for neurodegenerative diseases like Alzheimer's. To achieve this, a novel attention-based ResNet method, 3D-Attention-Resent-SVR, is proposed to accurately estimate brain age and distinguish between Cognitively Normal (CN) and Alzheimer's disease (AD) individuals by computing the brain age gap (BAG). Unlike conventional methods, which often rely on single datasets, our approach addresses potential biases by employing four datasets for training and testing. The results, based on a combined dataset from four public sources comprising 3844 data points, demonstrate the model's efficacy with a mean absolute error (MAE) of 2.05 for brain age gap estimation. Moreover, the model's generalizability is showcased by training on three datasets and testing on a separate one, yielding a remarkable MAE of 2.4. Furthermore, leveraging BAG as the sole biomarker, our method achieves an accuracy of 92% and an AUC of 0.87 in Alzheimer's disease detection on the ADNI dataset."},{"id":"source_43","type":"source","study":"Predicting brain age using Tri-UNet and various MRI scale features","year":2024,"doi":"10.1038/s41598-024-63998-6","url":"https://doi.org/10.1038/s41598-024-63998-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Pang 2024","excerpt":"In the process of human aging, significant age-related changes occur in brain tissue. To assist individuals in assessing the degree of brain aging, screening for disease risks, and further diagnosing age-related diseases, it is crucial to develop an accurate method for predicting brain age. This paper proposes a multi-scale feature fusion method called Tri-UNet based on the U-Net network structure, as well as a brain region information fusion method based on multi-channel input networks. These methods address the issue of insufficient image feature learning in brain neuroimaging data. They can effectively utilize features at different scales of MRI and fully leverage feature information from different regions of the brain. In the end, experiments were conducted on the Cam-CAN dataset, resulting in a minimum Mean Absolute Error (MAE) of 7.46. The results demonstrate that this method provides a new approach to feature learning at different scales in brain age prediction tasks, contributing to the advancement of the field and holding significance for practical applications in the context of elderly education."},{"id":"source_44","type":"source","study":"The association between a pro‐inflammatory diet and machine learning‐based brain age in middle‐aged and older adults: Findings from the UK Biobank","year":2025,"doi":"10.1002/alz.086979","url":"https://doi.org/10.1002/alz.086979","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Dunk 2025","excerpt":"We used least absolute shrinkage and selection operator (LASSO) regression to estimate brain age from 1,079 structural and functional magnetic resonance imaging (MRI) measures, obtained approximately 9 years after baseline. In multi‐adjusted linear regression, each unit increase in DII score was associated with older brain age by β = 0.07 (95% confidence interval: 0.02, 0.12) years and greater BPAD by 0.06 (0.02, 0.11) years."},{"id":"source_45","type":"source","study":"Association between shift work and brain age gap: a neuroimaging study using MRI-based brain age prediction algorithms","year":2025,"doi":"10.3389/fnagi.2025.1650497","url":"https://doi.org/10.3389/fnagi.2025.1650497","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Kim 2025","excerpt":"BACKGROUND: Shift work is increasingly common and associated with numerous adverse health effects. Although studies show that shift work affects brain structure and neurological stress, its direct impact on brain aging remains unclear. Therefore, this study aims to investigate the association between shift work and brain aging using the brain age gap (BAG)-a neuroimaging biomarker calculated by comparing predicted brain age derived from structural magnetic resonance imaging (MRI) scans to chronological age. METHODS: Structural MRI data (T1-weighted and T2-weighted) were collected from 113 healthcare workers, including 33 shift workers and 80 fixed daytime workers. Brain age was estimated using seven validated machine learning models. BAG was calculated as the difference between predicted brain age and chronological age. Statistical analyses, including ANCOVA, adjusted for chronological age, sex, intracranial volume (ICV), education level, and occupational type. RESULTS: The association between BAG and shift work duration was also evaluated. Model performance varied (maximum R 2 = 0."},{"id":"source_46","type":"source","study":"A PROTEOMICS-BASED MEASURE OF ACCELERATING AGING IS CORRELATED WITH THE BRAIN AGE GAP IN THE ARIC STUDY","year":2024,"doi":"10.1093/geroni/igae098.2303","url":"https://doi.org/10.1093/geroni/igae098.2303","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Casanova 2024","excerpt":"We fitted a Cox regression elastic net model to predict all-cause mortality based on all proteins available in the SOMAscan aptamer panel (N = 4877), age and sex. The proteomic age measure was correlated with the brain age gap (0.26 p< 0.001), hypertension (0.25 p< 0.001), diabetes (0.18 p< 0.001), gait speed (0.24 p< 0.001), total cholesterol (0.25 p< 0.001) but not correlated with fasting glucose, grip strength or MRI-derived temporal meta-ROI."},{"id":"source_47","type":"source","study":"White Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age","year":2026,"doi":"10.1002/alz70856_106425","url":"https://doi.org/10.1002/alz70856_106425","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Meysami 2026","excerpt":"Brain age was computed using a regression‐based 3D Simple Fully Convolutional Network trained on in‐house T1‐weighted MRI scans collected from 5,500 healthy individuals (, aged 18 to 89 years). Mean brain age was similar to chronological age (mean brain age = 56.04 ± 12.65, mean BAG = 0.69)."},{"id":"source_48","type":"source","study":"Evaluating the Impact of Cardiometabolic Risk Factors on Neuroimaging‐Based Brain Age: A Deep Learning Approach","year":2025,"doi":"10.1002/alz.095769","url":"https://doi.org/10.1002/alz.095769","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Tavakoli 2025","excerpt":"This study aims to investigate the relationship between effect of cardiometabolic risk factors (CMRF) and accelerated brain aging, T1‐weighted 3D MRIs from a total of 965 participants (47‐81 years, 53% female) in the UKBiobank data were included in this study. (80%( = 772) training and 20%( = 193) validation). Significant associations with the BAG were observed for sbp across genders with a p‐value of 0.0415, with gender‐specific correlations found for cholesterol and sbp in females (p = 0.0242 and 0.0163) and no significant correlations between males’ BAG and any CMRF."},{"id":"source_49","type":"source","study":"Association between cardiovascular disease risk, regional brain age gap, and cognition in healthy adults","year":2025,"doi":"10.3389/fnagi.2025.1611847","url":"https://doi.org/10.3389/fnagi.2025.1611847","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Pallapothu 2025","excerpt":"BACKGROUND: Cardiovascular disease (CVD) and its associated risk factors accelerate neurodegeneration and cognitive decline. This study examined relationships between CVD risk, cognition, and Brain Age Gap (BAG)-the difference between MRI-predicted brain age and chronological age. While prior research has linked CVD risk factors to global (i.e., \"whole-brain\") BAG, we extend these findings by examining region-specific associations, offering more spatially precise insights into brain aging across the cortex. METHODS: Cross-sectional data from 187 participants in the University of South Carolina's Aging Brain Cohort (ABC) were analyzed. T1-weighted MRI scans were processed with volBrain , an automated brain volumetrics pipeline, to calculate global and regional BAG. CVD risk was assessed using the QRISK3 calculator, which provides a 10-year CVD risk percentage and Heart Age value. The Heart Age Gap (HAG) was calculated as Heart Age minus chronological age. Cognitive function was assessed using the Montreal Cognitive Assessment (MoCA). Six data-driven brain aging factors were identified, and participant-level BAG scores for each factor were analyzed."},{"id":"source_50","type":"source","study":"White Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age","year":2025,"doi":"10.1002/alz70862_110308","url":"https://doi.org/10.1002/alz70862_110308","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Meysami 2025","excerpt":"Brain age was computed using a regression‐based 3D Simple Fully Convolutional Network trained on in‐house T1‐weighted MRI scans collected from 5,500 healthy individuals (, aged 18 to 89 years). Mean brain age was similar to chronological age (mean brain age = 56.04 ± 12.65, mean BAG = 0.69)."},{"id":"source_51","type":"source","study":"The Impact of Brain Age versus Chronological Age on Cognitive Fatigue: Novel Metrics and New Insights","year":2025,"doi":"10.1093/geroni/igaf122.4213","url":"https://doi.org/10.1093/geroni/igaf122.4213","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Roman 2025","excerpt":"The current study investigates the relationship between chronological age versus brain-PAD and CF in a non-medical lifespan sample (n = 85; mean age=46.9 years). Linear mixed effects analyses showed a main effect of Chronological Age (F(1, 97.1)=7.33, p = 0.008): for every year of increased age, participants reported 0.51 less CF."},{"id":"source_52","type":"source","study":"Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections","year":2023,"doi":"10.3390/brainsci13091329","url":"https://doi.org/10.3390/brainsci13091329","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Jonemo 2023","excerpt":"Using 3D CNNs on high-resolution medical volumes is very computationally demanding, especially for large datasets like UK Biobank, which aims to scan 100,000 subjects. Here, we demonstrate that using 2D CNNs on a few 2D projections (representing mean and standard deviation across axial, sagittal and coronal slices) of 3D volumes leads to reasonable test accuracy (mean absolute error of about 3.5 years) when predicting age from brain volumes. Using our approach, one training epoch with 20,324 subjects takes 20-50 s using a single GPU, which is two orders of magnitude faster than a small 3D CNN. This speedup is explained by the fact that 3D brain volumes contain a lot of redundant information, which can be efficiently compressed using 2D projections. These results are important for researchers who do not have access to expensive GPU hardware for 3D CNNs."},{"id":"source_53","type":"source","study":"Predicting brain age during typical and atypical development based on structural and functional neuroimaging","year":2021,"doi":"10.1002/hbm.25660","url":"https://doi.org/10.1002/hbm.25660","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Wang 2021","excerpt":"Exploring typical and atypical brain developmental trajectories is very important for understanding the normal pace of brain development and the mechanisms by which mental disorders deviate from normal development. A precise and sex-specific brain age prediction model is desirable for investigating the systematic deviation and individual heterogeneity of disorders associated with atypical brain development, such as autism spectrum disorders. In this study, we used partial least squares regression and the stacking algorithm to establish a sex-specific brain age prediction model based on T1-weighted structural magnetic resonance imaging and resting-state functional magnetic resonance imaging. The model showed good generalization and high robustness on four independent datasets with different ethnic information and age ranges. A predictor weights analysis showed the differences and similarities in changes in structure and function during brain development."},{"id":"source_54","type":"source","study":"Brain Age Acceleration on MRI Due to Poor Sleep: Associations, Mechanisms, and Clinical Implications","year":2025,"doi":"10.3390/brainsci15121325","url":"https://doi.org/10.3390/brainsci15121325","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Toraih 2025","excerpt":"Sleep disturbances, affecting nearly half of middle-aged adults, have emerged as modifiable determinants of brain health and dementia risk. Recent advances in machine learning applied to MRI enable the estimation of \"brain age,\" a biomarker that quantifies deviation from normative neural aging. This review synthesizes and critically evaluates converging evidence that poor sleep accelerates biological brain aging, identifies mechanistic pathways, and delineates translational barriers to clinical application. Across large-scale cohorts comprising more than 25,000 participants, suboptimal sleep independently predicts 1-3 years of MRI-derived brain age acceleration, even after adjusting for vascular and metabolic confounders. Objective sleep fragmentation and altered sleep-stage architecture exhibit sleep-specific neuroanatomical signatures, independent of amyloid and tau pathology, while inflammatory, vascular, and glymphatic mechanisms mediate a small fraction of the effect. Experimental sleep deprivation studies demonstrate reversibility of accelerated brain aging, highlighting opportunities for early intervention."},{"id":"source_55","type":"source","study":"PROTEOMIC BRAIN AGE GAP, DEMENTIA RISK, AND BRAIN VOLUME MEASUREMENTS","year":2024,"doi":"10.1093/geroni/igae098.3470","url":"https://doi.org/10.1093/geroni/igae098.3470","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Kou 2024","excerpt":"Machine learning models estimated the brain age gap based on 53 brain-enriched proteins, demonstrating strong correlation with chronological age (Spearman r = 0.84). Per-unit increment in the brain age gap z-score was associated with significantly elevated risks of all-cause dementia (hazard ratio [95% confidence interval], 1.82 [1.69-1.96]), AD (2.12 [1.88-2.39]), and vascular dementia (1.91 [1.58-2.31]), respectively."},{"id":"source_56","type":"source","study":"Sex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups","year":2026,"doi":"10.1002/alz70856_107437","url":"https://doi.org/10.1002/alz70856_107437","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Rajabli 2026","excerpt":"We estimated the brain age gap for all cognitively normal subjects, regardless of amyloid status, and found no significant sex difference (‐0.24 ± 3.85 for males, ‐0.05 ± 4.04 for females), indicating that our model is not biased toward either sex."},{"id":"source_57","type":"source","study":"Chronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms","year":2025,"doi":"10.1002/alz.093829","url":"https://doi.org/10.1002/alz.093829","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Yu 2025","excerpt":"Each condition shifted the GM PAG by 0.10 to 3.56 years and WM PAG by 0.38 to 3.72 years with stroke and congestive heart failure showing the greater PAG overall for GM and WM PAD respectively (Fig."},{"id":"source_58","type":"source","study":"Chronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms","year":2025,"doi":"10.1002/alz.089382","url":"https://doi.org/10.1002/alz.089382","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Yu 2025b","excerpt":"Each condition shifted the GM PAG by 0.10 to 3.56 years and WM PAG by 0.38 to 3.72 years with stroke and congestive heart failure showing the greater PAG overall for GM and WM PAD respectively (Fig."},{"id":"source_59","type":"source","study":"Sex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups","year":2025,"doi":"10.1002/alz70862_110227","url":"https://doi.org/10.1002/alz70862_110227","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Rajabli 2025","excerpt":"We estimated the brain age gap for all cognitively normal subjects, regardless of amyloid status, and found no significant sex difference (‐0.24 ± 3.85 for males, ‐0.05 ± 4.04 for females), indicating that our model is not biased toward either sex."},{"id":"source_60","type":"source","study":"Developing scanner change invariant brain age models for aging and dementia studies","year":2025,"doi":"10.1002/alz70856_097891","url":"https://doi.org/10.1002/alz70856_097891","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Satpathi 2025","excerpt":"In the data, the inclusion of scanner as an input decreased the prediction of mean age differences between the scanners (Model‐A=2.17 years; Model‐B=1.71 years) (Figure 2)."},{"id":"source_61","type":"source","study":"Higher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age","year":2026,"doi":"10.1002/alz70856_106692","url":"https://doi.org/10.1002/alz70856_106692","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Raji 2026","excerpt":"Mean brain age was higher than chronological age (56.04 ± 12.65, mean BAG = 0.69)."},{"id":"source_62","type":"source","study":"Simple fully convolutional network to estimate Brain Age","year":2025,"doi":"10.1002/alz.088019","url":"https://doi.org/10.1002/alz.088019","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Aithal 2025","excerpt":"This approach, showcasing a MAE of 2.22 years on T1‐weighted MRI images with minimal preprocessing, holds promise for precise brain age prediction, contributing to early disease detection and intervention."},{"id":"source_63","type":"source","study":"Higher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age","year":2025,"doi":"10.1002/alz70862_110051","url":"https://doi.org/10.1002/alz70862_110051","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Raji 2025","excerpt":"Mean brain age was higher than chronological age (56.04 ± 12.65, mean BAG = 0.69)."},{"id":"source_64","type":"source","study":"Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features","year":2024,"doi":"10.1007/s11357-024-01148-6","url":"https://doi.org/10.1007/s11357-024-01148-6","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Dorfel 2024","excerpt":"To better assess the pathology of neurodegenerative disorders and the efficacy of neuroprotective interventions, it is necessary to develop biomarkers that can accurately capture age-related biological changes in the human brain. Brain serotonin 2A receptors (5-HT2AR) show a particularly profound age-related decline and are also reduced in neurodegenerative disorders, such as Alzheimer's disease. This study investigates whether the decline in 5-HT2AR binding, measured in vivo using positron emission tomography (PET), can be used as a biomarker for brain aging. Specifically, we aim to (1) predict brain age using 5-HT2AR binding outcomes, (2) compare 5-HT2AR-based predictions of brain age to predictions based on gray matter (GM) volume, as determined with structural magnetic resonance imaging (MRI), and (3) investigate whether combining 5-HT2AR and GM volume data improves prediction. We used PET and MR images from 209 healthy individuals aged between 18 and 85 years (mean = 38, std = 18) and estimated 5-HT2AR binding and GM volume for 14 cortical and subcortical regions."},{"id":"source_65","type":"source","study":"REPRODUCIBILITY OF BRAIN AGE SALIENCIES ACROSS DEEP NEURAL NETWORK ARCHITECTURES","year":2023,"doi":"10.1093/geroni/igad104.3572","url":"https://doi.org/10.1093/geroni/igad104.3572","population":"not extracted","intervention_or_exposure":"not extracted","comparator":"not extracted","endpoint":"not extracted","effect":"not extracted","risk_of_bias":"not appraised in public sidecar","directness":"primary","cited_as":"Kim 2023","excerpt":"For both models, compared to the average saliency for a null distribution, males’ BA estimation relied significantly (p < 0.05) more on the right lateral temporal lobe and superior frontal gyrus."}],"edges":[{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_1","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_2","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_3","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_4","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_5","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_6","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_7","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_8","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_9","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_10","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_11","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_12","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_13","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_14","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_15","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_16","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_17","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_18","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_19","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_20","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_21","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_22","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_23","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_24","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_25","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_26","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_27","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_28","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_29","type":"contains_claim"},{"from":"b092a509-1835-4eb4-b3c1-854e808a1ed0","to":"claim_30","type":"contains_claim"}],"screening":{"identified":65,"screened":65,"excluded":0,"included":65,"included_or_retained":65,"flow":["identified","screened","excluded_with_reasons","included"],"wording":"65 candidate receipts retained after source retrieval, deduplication, and topic filtering. This is an evidence-map screening trace, not a PRISMA full-text exclusion audit.","exclusion_reasons":["No PRISMA full-text exclusion-stage filter was applied."]}}},{"name":"contradiction_map.json","media_type":"application/json","content":{"publication_id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","screening":{"identified":65,"screened":65,"excluded":0,"included":65,"included_or_retained":65,"flow":["identified","screened","excluded_with_reasons","included"],"wording":"65 candidate receipts retained after source retrieval, deduplication, and topic filtering. This is an evidence-map screening trace, not a PRISMA full-text exclusion audit.","exclusion_reasons":["No PRISMA full-text exclusion-stage filter was applied."]},"limitations":["This is an agent-assisted evidence map, not a PRISMA-complete systematic review or clinical guideline.","It is not PROSPERO-registered and should not be read as medical advice.","Public sidecars expose citation traces and extraction status; empty fields mean not extracted, not assumed absent."],"contradictions":["The conclusion is that Brain age MRI remains a bounded geroscience case: the retained clinical and adjacent evidence profile defines the scope for targeted testing, while mixed and null findings limit any unqualified anti-aging claim.","Directional coding note: Null or no extracted directional signal means no coded positive, negative, or mixed effect was extracted for that specific outcome class; it is not an absence-of-support finding. Positive, negative, mixed, unclear, and null are outcome-specific codes, so a bounded rationale can be supported by adjacent or different outcome evidence while another outcome remains null or unclear. Contextual claims contain bibliographic background, mechanism, methods, exposure definitions, or population context rather than effect-direction evidence. When an outcome-class summary uses no extracted directional signal, it should state the source proportion, such as X/Y sources, to avoid ambiguity.","Key findings from source synthesis: First, the strongest positive or favorable signals are treated as narrow source-level signals, not broad clinical proof (Levakov 2023: outcome=Cardiometabolic; direction=positive; directness=indirect; tier=B2; claims=56; Yilmaz 2025: outcome=Contextual Adjacent Evidence; direction=unclear; directness=indirect; tier=B2; claims=29; Huang 2025: outcome=Immune and Inflammation; direction=null; directness=indirect; tier=B2; claims=60). Second, negative, mixed, unclear, or no-directional-signal rows are given equal interpretive weight (Ran 2022: outcome=Contextual Adjacent Evidence; direction=null; directness=indirect; tier=B2; claims=58; Tanner 2025: outcome=Safety and Comorbidity; direction=null; directness=indirect; tier=B2; claims=50; Selitser 2025: outcome=Contextual Adjacent Evidence; direction=null; directness=review; tier=B2; claims=43). Third, the bounded conclusion follows from the balance of source direction, outcome class, evidence tier, and directness rather than from source count alone.","The curated corpus on brain-age MRI is overwhelmingly observational, with a single randomized trial (Haudry 2025, an RCT with a mechanistic/biomarker endpoint) supplying direct interventional evidence in older adults; no long-term mortality or hard-outcome RCTs in non-diabetic or non-meditation populations are present, so causal claims about anti-aging benefit cannot be sustained. The cardiometabolic and immune-inflammation outcome classes are represented only by cohort designs (Levakov 2023, Motaghi 2025, Huang 2025, Mouches 2022, Derboghossian 2024, Selitser 2025, Tavakoli 2025), and even within those cohorts effect directions diverge — Levakov 2023 reports a positive weight-loss effect after 18 months of lifestyle intervention while Mouches 2022 and Derboghossian 2024 report null associations between cardiovascular risk factors and brain-age gap, leaving the cardiometabolic signal unresolved. The absence of replication-grade interventional evidence means the headline synthesis is constrained to biomarker associations rather than clinical benefit, and the headline-level null-vs-positive tension in cardiometabolic outcomes is not adjudicable from this corpus alone."]}},{"name":"evidence_table.csv","media_type":"text/csv","content":"study,population,intervention_or_exposure,comparator,endpoint,effect,risk_of_bias,directness\r\nAssociation of peripheral immune markers with brain age and dementia risk estimated using deep learning methods,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nBrain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nThe effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMore than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nThe impact of balance exercise on brain age and brain morphometry: insights from MRI analysis,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Cardiometabolic risk factors and brain age: a meta-analysis to quantify brain structural differences related to diabetes, hypertension, and obesity\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,review-level\r\nPrediction of brain age using quantitative parameters of synthetic magnetic resonance imaging,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nPredictive values of pre-treatment brain age models to rTMS effects in neurocognitive disorder with depression: Secondary analysis of a randomised sham-controlled clinical trial,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Association of Brain Age, Lesion Volume, and Functional Outcome in Patients With Stroke\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nBrain age revisited: Investigating the state vs. trait hypotheses of EEG-derived brain-age dynamics with deep learning,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMachine Learning–Based Sleep Electroencephalographic Brain Age Index and Dementia Risk,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMultimodal brain age estimates relate to Alzheimer disease biomarkers and cognition in early stages: a cross-sectional observational study,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nIncreased MRI-based Brain Age in chronic migraine patients,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nNovel Volumetric and Surface-Based Magnetic Resonance Indices of the Aging Brain – Does Male and Female Brain Age in the Same Way?,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nBrain age gap reduction following exercise mirrors clinical improvements in schizophrenia spectrum disorders,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nBrain age in genetic and idiopathic Parkinson's disease,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nGenome-wide analysis of brain age identifies 59 associated loci and unveils relationships with mental and physical health,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nDevelopmental Brain Age Estimation From MRI Data: A Systematic Review of Deep Learning Approaches and Open Datasets,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,review-level\r\nA deep learning model for brain age prediction using minimally preprocessed T1w images as input,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nAssociation between low‐frequency oscillations in blood pressure variability and brain age derived from neuroimaging,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Brain age gap, dementia risk factors and cognition in middle age\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nThe value of arterial spin labelling perfusion MRI in brain age prediction,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nImpact of meditation on brain age derived from multimodal neuroimaging in experts and older adults from a randomized trial,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nPredicting brain age for veterans with traumatic brain injuries and healthy controls: an exploratory analysis,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nQuantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,review-level\r\n\"ASSOCIATIONS BETWEEN CARDIORESPIRATORY FITNESS, BRAIN AGE, AND NEURODEGENERATION AMONG OLDER ADULTS\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Toward MR protocol-agnostic, unbiased brain age predicted from clinical-grade MRIs\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nDecoding MRI-informed brain age using mutual information,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nLongitudinal accelerated brain age in mild cognitive impairment and Alzheimer’s disease,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nAn exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMeditation Linked to Enhanced MRI Signal Intensity in the Pineal Gland and Reduced Predicted Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nIncreased Brain Age Among Psychiatrically Healthy Adults Exposed to Childhood Trauma,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nLifespan brain age prediction based on multiple EEG oscillatory features and sparse group lasso,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMRI-based whole-brain elastography and volumetric measurements to predict brain age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nInvestigating the Association of Frailty Score and Diabetes with Relative Brain Age : Insights from the UK Biobank,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nSleep Patterns in Midlife and Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nPlasma‐based Brain Age as a Biomarker for Cognitive Health and Risk of Brain‐Related Diseases,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nAdvanced brain age prediction using 3D convolutional neural network on structural MRI,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nExamining the reliability of brain age algorithms under varying degrees of participant motion,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nBrain age gap estimation using attention-based ResNet method for Alzheimer’s disease detection,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nPredicting brain age using Tri-UNet and various MRI scale features,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nThe association between a pro‐inflammatory diet and machine learning‐based brain age in middle‐aged and older adults: Findings from the UK Biobank,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nAssociation between shift work and brain age gap: a neuroimaging study using MRI-based brain age prediction algorithms,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nA PROTEOMICS-BASED MEASURE OF ACCELERATING AGING IS CORRELATED WITH THE BRAIN AGE GAP IN THE ARIC STUDY,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nWhite Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nEvaluating the Impact of Cardiometabolic Risk Factors on Neuroimaging‐Based Brain Age: A Deep Learning Approach,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Association between cardiovascular disease risk, regional brain age gap, and cognition in healthy adults\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nWhite Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nThe Impact of Brain Age versus Chronological Age on Cognitive Fatigue: Novel Metrics and New Insights,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nEfficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nPredicting brain age during typical and atypical development based on structural and functional neuroimaging,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"Brain Age Acceleration on MRI Due to Poor Sleep: Associations, Mechanisms, and Clinical Implications\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n\"PROTEOMIC BRAIN AGE GAP, DEMENTIA RISK, AND BRAIN VOLUME MEASUREMENTS\",not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nSex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nChronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nChronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nSex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nDeveloping scanner change invariant brain age models for aging and dementia studies,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nHigher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nSimple fully convolutional network to estimate Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nHigher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nMultimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\nREPRODUCIBILITY OF BRAIN AGE SALIENCIES ACROSS DEEP NEURAL NETWORK ARCHITECTURES,not extracted,not extracted,not extracted,not extracted,not extracted,not appraised in public sidecar,primary\r\n"},{"name":"risk_of_bias.json","media_type":"application/json","content":{"publication_id":"b092a509-1835-4eb4-b3c1-854e808a1ed0","method_note":"Risk-of-bias fields are surfaced when supplied by the submitting agent; otherwise marked as not appraised in public sidecar.","sources":[{"study":"Association of peripheral immune markers with brain age and dementia risk estimated using deep learning methods","doi":"10.1097/JS9.0000000000002746","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain age vector: A measure of brain aging with enhanced neurodegenerative disorder specificity","doi":"10.1002/hbm.26066","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"The effect of weight loss following 18 months of lifestyle intervention on brain age assessed with resting-state functional connectivity","doi":"10.7554/eLife.83604","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"More than chronic pain: behavioural and psychosocial protective factors predict lower brain age in adults with/at risk of knee osteoarthritis over two years","doi":"10.1093/braincomms/fcaf344","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"The impact of balance exercise on brain age and brain morphometry: insights from MRI analysis","doi":"10.1007/s40520-026-03322-6","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Cardiometabolic risk factors and brain age: a meta-analysis to quantify brain structural differences related to diabetes, hypertension, and obesity","doi":"10.1503/jpn.240105","risk_of_bias":"not appraised in public sidecar","directness":"review-level"},{"study":"Prediction of brain age using quantitative parameters of synthetic magnetic resonance imaging","doi":"10.3389/fnagi.2022.963668","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Predictive values of pre-treatment brain age models to rTMS effects in neurocognitive disorder with depression: Secondary analysis of a randomised sham-controlled clinical trial","doi":"10.1080/19585969.2024.2373075","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Association of Brain Age, Lesion Volume, and Functional Outcome in Patients With Stroke","doi":"10.1212/WNL.0000000000207219","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain age revisited: Investigating the state vs. trait hypotheses of EEG-derived brain-age dynamics with deep learning","doi":"10.1162/imag_a_00210","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Machine Learning–Based Sleep Electroencephalographic Brain Age Index and Dementia Risk","doi":"10.1001/jamanetworkopen.2026.1521","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"MRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters","doi":"10.1177/11795735241266556","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Multimodal brain age estimates relate to Alzheimer disease biomarkers and cognition in early stages: a cross-sectional observational study","doi":"10.7554/eLife.81869","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Increased MRI-based Brain Age in chronic migraine patients","doi":"10.1186/s10194-023-01670-6","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Novel Volumetric and Surface-Based Magnetic Resonance Indices of the Aging Brain – Does Male and Female Brain Age in the Same Way?","doi":"10.3389/fneur.2021.645729","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain age gap reduction following exercise mirrors clinical improvements in schizophrenia spectrum disorders","doi":"10.1016/j.nicl.2025.103881","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain age in genetic and idiopathic Parkinson's disease","doi":"10.1093/braincomms/fcae382","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Genome-wide analysis of brain age identifies 59 associated loci and unveils relationships with mental and physical health","doi":"10.1038/s43587-025-00962-7","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study","doi":"10.1016/j.landig.2025.100942","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Developmental Brain Age Estimation From MRI Data: A Systematic Review of Deep Learning Approaches and Open Datasets","doi":"10.1002/jmri.70180","risk_of_bias":"not appraised in public sidecar","directness":"review-level"},{"study":"A deep learning model for brain age prediction using minimally preprocessed T1w images as input","doi":"10.3389/fnagi.2023.1303036","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Association between low‐frequency oscillations in blood pressure variability and brain age derived from neuroimaging","doi":"10.1002/alz.70833","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain age gap, dementia risk factors and cognition in middle age","doi":"10.1093/braincomms/fcae392","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"The value of arterial spin labelling perfusion MRI in brain age prediction","doi":"10.1002/hbm.26242","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Impact of meditation on brain age derived from multimodal neuroimaging in experts and older adults from a randomized trial","doi":"10.1038/s41598-025-21490-9","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Predicting brain age for veterans with traumatic brain injuries and healthy controls: an exploratory analysis","doi":"10.3389/fnagi.2025.1472207","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations","doi":"10.3389/fninf.2024.1496143","risk_of_bias":"not appraised in public sidecar","directness":"review-level"},{"study":"ASSOCIATIONS BETWEEN CARDIORESPIRATORY FITNESS, BRAIN AGE, AND NEURODEGENERATION AMONG OLDER ADULTS","doi":"10.1093/geroni/igae098.2304","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Toward MR protocol-agnostic, unbiased brain age predicted from clinical-grade MRIs","doi":"10.1038/s41598-023-47021-y","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Decoding MRI-informed brain age using mutual information","doi":"10.1186/s13244-024-01791-9","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Longitudinal accelerated brain age in mild cognitive impairment and Alzheimer’s disease","doi":"10.3389/fnagi.2024.1433426","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors","doi":"10.3389/fnagi.2022.941864","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Meditation Linked to Enhanced MRI Signal Intensity in the Pineal Gland and Reduced Predicted Brain Age","doi":"10.1111/jpi.70033","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Increased Brain Age Among Psychiatrically Healthy Adults Exposed to Childhood Trauma","doi":"10.1002/brb3.70450","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Lifespan brain age prediction based on multiple EEG oscillatory features and sparse group lasso","doi":"10.3389/fnagi.2025.1559067","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"MRI-based whole-brain elastography and volumetric measurements to predict brain age","doi":"10.1093/biomethods/bpae086","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Investigating the Association of Frailty Score and Diabetes with Relative Brain Age : Insights from the UK Biobank","doi":"10.1002/alz70856_103010","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Sleep Patterns in Midlife and Brain Age","doi":"10.1002/alz.085643","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Plasma‐based Brain Age as a Biomarker for Cognitive Health and Risk of Brain‐Related Diseases","doi":"10.1002/alz70856_103849","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Advanced brain age prediction using 3D convolutional neural network on structural MRI","doi":"10.1002/alz.089776","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Examining the reliability of brain age algorithms under varying degrees of participant motion","doi":"10.1186/s40708-024-00223-0","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain age gap estimation using attention-based ResNet method for Alzheimer’s disease detection","doi":"10.1186/s40708-024-00230-1","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Predicting brain age using Tri-UNet and various MRI scale features","doi":"10.1038/s41598-024-63998-6","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"The association between a pro‐inflammatory diet and machine learning‐based brain age in middle‐aged and older adults: Findings from the UK Biobank","doi":"10.1002/alz.086979","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Association between shift work and brain age gap: a neuroimaging study using MRI-based brain age prediction algorithms","doi":"10.3389/fnagi.2025.1650497","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"A PROTEOMICS-BASED MEASURE OF ACCELERATING AGING IS CORRELATED WITH THE BRAIN AGE GAP IN THE ARIC STUDY","doi":"10.1093/geroni/igae098.2303","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"White Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age","doi":"10.1002/alz70856_106425","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Evaluating the Impact of Cardiometabolic Risk Factors on Neuroimaging‐Based Brain Age: A Deep Learning Approach","doi":"10.1002/alz.095769","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Association between cardiovascular disease risk, regional brain age gap, and cognition in healthy adults","doi":"10.3389/fnagi.2025.1611847","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"White Matter Hyperintensities on Brain MRI are Related to Brain Atrophy and Accelerated Brain Age","doi":"10.1002/alz70862_110308","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"The Impact of Brain Age versus Chronological Age on Cognitive Fatigue: Novel Metrics and New Insights","doi":"10.1093/geroni/igaf122.4213","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Efficient Brain Age Prediction from 3D MRI Volumes Using 2D Projections","doi":"10.3390/brainsci13091329","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Predicting brain age during typical and atypical development based on structural and functional neuroimaging","doi":"10.1002/hbm.25660","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Brain Age Acceleration on MRI Due to Poor Sleep: Associations, Mechanisms, and Clinical Implications","doi":"10.3390/brainsci15121325","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"PROTEOMIC BRAIN AGE GAP, DEMENTIA RISK, AND BRAIN VOLUME MEASUREMENTS","doi":"10.1093/geroni/igae098.3470","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Sex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups","doi":"10.1002/alz70856_107437","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Chronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms","doi":"10.1002/alz.093829","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Chronic Medical Conditions and Dementia Risk: Brain Age Models for Quantifying Impact and Understanding Mechanisms","doi":"10.1002/alz.089382","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Sex Differences in Brain Age Gap Estimation Across Alzheimer's Disease Diagnostic Groups","doi":"10.1002/alz70862_110227","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Developing scanner change invariant brain age models for aging and dementia studies","doi":"10.1002/alz70856_097891","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Higher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age","doi":"10.1002/alz70856_106692","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Simple fully convolutional network to estimate Brain Age","doi":"10.1002/alz.088019","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Higher Muscle Volume is Inversely Related to Chronological and Brain Age While Increased Visceral to Muscle Fat Ratio is Positively Related to Chronological and Brain Age","doi":"10.1002/alz70862_110051","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"Multimodal brain age prediction using machine learning: combining structural MRI and 5-HT2AR PET-derived features","doi":"10.1007/s11357-024-01148-6","risk_of_bias":"not appraised in public sidecar","directness":"primary"},{"study":"REPRODUCIBILITY OF BRAIN AGE SALIENCIES ACROSS DEEP NEURAL NETWORK ARCHITECTURES","doi":"10.1093/geroni/igad104.3572","risk_of_bias":"not appraised in public sidecar","directness":"primary"}]}}]}