Machine Learning-Based Sleep Electroencephalographic Brain Age Index and Dementia Risk: An Individual Participant Data Meta-Analysis

Reviewed as evidence on: Sleep-EEG-derived brain age and dementia risk 1 study (what the news said). Being listed means the study bears on the question, not that it agrees with the news.

Topic: Risk, prevention and care in population studies

Results This meta-analysis included 7105 participants from the MESA (n = 1802; mean [SD] age, 69.3 [9.0] years; 956 females [53.1%]), ARIC (n = 1796; 62.5 [5.7] years; 918 females [51.1%]), FHS-OS (n = 617; 59.5 [8.9] years; 318 females [51.5%]), MrOS (n = 2639 males [100%]; 76.0 [5.3] years), and SOF (n = 251 females [100%]; 82.7 [2.9] years) cohorts. Across the cohorts, each 10-year increase in BAI was associated with a 39% higher risk of incident dementia (hazard ratio [HR], 1.39 [95% CI, 1.21-1.59]; P Conclusions and relevance In this IPD meta-analysis, a higher sleep EEG-based BAI was associated with a higher risk of incident dementia. These findings highlight the need to evaluate the predictive value of the BAI as a noninvasive digital marker for early detection of dementia in community settings.

Key findings

• Results This meta-analysis included 7105 participants from the MESA (n = 1802; mean [SD] age, 69.3 [9.0] years; 956 females [53.1%]), ARIC (n = 1796; 62.5 [5.7] years; 918 females [51.1%]), FHS-OS (n = 617; 59.5 [8.9] years; 318 females [51.5%]), MrOS (n = 2639 males [100%]; 76.0 [5.3] years), and SOF (n = 251 females [100%]; 82.7 [2.9] years) cohorts.
• Across the cohorts, each 10-year increase in BAI was associated with a 39% higher risk of incident dementia (hazard ratio [HR], 1.39 [95% CI, 1.21-1.59]; P Conclusions and relevance In this IPD meta-analysis, a higher sleep EEG-based BAI was associated with a higher risk of incident dementia.
• These findings highlight the need to evaluate the predictive value of the BAI as a noninvasive digital marker for early detection of dementia in community settings.

Why it matters

In this pooled analysis of over 7,000 people, each 10-year increase in a sleep EEG-based brain age index was linked to a 39% higher risk of developing dementia. The authors say this noninvasive digital marker needs further evaluation before it can be used for early detection in the community.

New to this subject? Start with our plain-English guide: Blood tests & biomarkers →

Study details

• Study designmeta-analysis
• Participants7,105
• Effect sizeHazard ratio 1.39 (95% CI 1.21-1.59) for incident dementia per 10-year increase in sleep-EEG brain age index
• Evidence strengthModerate

Limitations

Cohorts differed in age, sex mix and follow-up (3.6 to 16.9 years to dementia); dementia ascertainment varied; the index has not been tested prospectively as a screening tool.

Read the original

• DOI: 10.1001/jamanetworkopen.2026.1521
• PubMed: 41854616
• Original source →
• Free full text: PubMed Central →

Full text: free to read — PubMed Central lists this copy as free to read: the link above (checked 10 Oct 2026).

@article{sun2026-41854616,
  author  = {Sun, Haoqi and Milton, Sasha and Fang, Yi and Taha, Hash Brown and Shiju, Shreya and Thomas, Robert J and Ganglberger, Wolfgang and Pase, Matthew P and others},
  title   = {{Machine Learning-Based Sleep Electroencephalographic Brain Age Index and Dementia Risk: An Individual Participant Data Meta-Analysis}},
  journal = {JAMA network open},
  year    = {2026},
  doi     = {10.1001/jamanetworkopen.2026.1521},
  pmid    = {41854616},
  url     = {https://doi.org/10.1001/jamanetworkopen.2026.1521}
}

Studies this one cites

Referenced by this study and also in the alzhub library, so you can read them here.

• Sleep Architecture, Obstructive Sleep Apnea, and Cognitive Function in Adults JAMA network open · 2023-07-03 · usefulness score 80/100 · Long-term cohort studies
• Association Between Slow-Wave Sleep Loss and Incident Dementia JAMA Neurology · 2023-12-01 · usefulness score 67/100 · Prevention and risk
• Sleep, 24-Hour Activity Rhythms, and Subsequent Amyloid-β Pathology JAMA neurology · 2024-08-01 · usefulness score 67/100 · Biomarkers
• Sleep architecture and dementia risk in adults: an analysis of 5 cohorts from the Sleep and Dementia Consortium SLEEP · 2025-05-16 · usefulness score 64/100 · How common it is
• Diagnostic and Statistical Manual of Mental Disorders 2013-05-22 · usefulness score 16/100 · Getting a diagnosis

In the news

1 news article on alzhub's news page cites this paper.

• AI can tell if your brain is aging faster than you are ScienceDaily · July 31, 2026

Related studies in Biomarkers

• Amyloid PET Quantitation and Centiloid Thresholds in the Diagnosis of Alzheimer Disease: An Individual Participant Data Meta-Analysis Apollo (University of Cambridge) · 2026-07-13 · usefulness score 52/100
• Machine learning prediction of tau-PET in Alzheimer's disease using plasma, MRI, and clinical data Alzheimer's & dementia : the journal of the Alzheimer's Association · 2025-02 · usefulness score 46/100
• Machine Learning Models of Polygenic Risk for Enhanced Prediction of Alzheimer Disease Endophenotypes Neurology. Genetics · 2024-01-10 · usefulness score 51/100
• Consensus Risk Modeling and Uncertainty Quantification of Alzheimer’s Disease Using 5ADCSI Plasma Biomarkers and Multiple External Machine-Learning Frameworks medRxiv · 2026-08-02 · usefulness score 16/100
• A blood-based diagnostic test incorporating plasma Aβ42/40 ratio, ApoE proteotype, and age accurately identifies brain amyloid status: findings from a multi cohort validity analysis Molecular neurodegeneration · 2021-05-01 · usefulness score 48/100
• Deep Learning-Based Screening Test for Cognitive Impairment Using Basic Blood Test Data for Health Examination Frontiers in neurology · 2020-12-14 · usefulness score 48/100

Similar studies

• Early dementia diagnosis, MCI-to-dementia risk prediction, and the role of machine learning methods for feature extraction from integrated biomarkers, in particular for EEG signal analysis 2022 · Digital health tools
• Multidimensional sleep profiles via machine learning and risk of dementia and cardiovascular disease 2025 · Digital health tools
• AI-driven magnetoencephalography biomarkers in dementia risk prediction: current evidence, challenges and future perspectives 2026 · Getting a diagnosis
• Sleep apnea and the risk of dementia: A systematic review and meta-analysis 2022 · Prevention and risk
• Machine learning diagnosis of cognitive impairment and dementia in harmonized older adult cohorts 2025 · Digital health tools
• Classification of Alzheimer's Disease with Respect to Physiological Aging with Innovative EEG Biomarkers in a Machine Learning Implementation 2020 · Digital health tools

More on Biomarkers

• A review that covers this ground Emerging blood exosome-based biomarkers for preclinical and clinical Alzheimer's disease: a meta-analysis and systematic review Neural regeneration research · 2022-11-01 · usefulness score 71/100
• Newest in this subject Longitudinal plasma biomarkers and multimodal PET across APOE ε4 genotypes: a prospective cohort study Research Square · 2026-11-01 · Preprint — not yet peer-reviewed · usefulness score 16/100
• Newest in this subject Concurrent cognitive, behavioral and systemic physiological features mark preclinical Alzheimer's disease bioRxiv · 2026-10-30 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Biomarkers →