Dementia Risk and Machine Learning-Derived Brain Age Index from Sleep Electroencephalography: A Pooled Cohort Analysis of Over 7,000 Individuals Across Five Community Cohorts
Year: 2025
Type: preprint
Abstract: Importance: Sleep electroencephalographic (EEG) microstructures are closely related to cognition and undergo age-dependent changes. However, their multidimensional nature makes them challenging to interpret using conventional approaches. Machine learning-computed EEG brain age index (BAI) represents the difference between the sleep EEG-based brain age and chronological age, quantifying deviations in sleep EEG microstructures from normative patterns. Objective: To determine the association between sleep BAI and incident dementia in community-dwelling populations. Design: Five individual cohorts and random-effects meta-analysis. Setting: This study pooled data from five community-based, methodologically consistent, longitudinal cohorts: MESA, ARIC, FHS-OS, MrOS, and SOF. We used Fine-Gray models to assess the association between BAI and incident dementia within each cohort, accounting for death as a competing risk. Cohort-specific estimates were then pooled using random-effects meta-analyses. Participants: 7,071 participants (MESA 54-94 years old, ARIC 52-75, FHS-OS 40-81, MrOS 67-96, SOF 79-93) without dementia at the time of polysomnography were included. Exposure: The sleep EEG-based BAI was computed using interpretable machine learning, incorporating 13 age-dependent features extracted from central EEG channels in overnight, home-based sleep polysomnography. Main Outcomes and Measures: Incident dementia or probable dementia was determined in each cohort, with death as a competing risk. Results: Across the five cohorts, dementia incidence ranged from 6.6% to 34.3% over a median follow-up of 3.5 to 17.0 years. Across cohorts, each 10-year increase in BAI was associated with a 39% increased risk of incident dementia (hazard ratio: 1.39 [95% confidence interval=1.21-1.59], p<0.001) after adjustment for age, sex, race, education, body mass index, current smoking, sleep medications, and physical activity level. The top feature underlying BAI was waveform kurtosis in N2 with a negative association with incident dementia (p<0.001). The associations remained after additional adjustment for multiple comorbidities, APOE e4 status, and apnea-hypopnea index, and were consistent across sex and age groups. Conclusions and Relevance: A higher sleep EEG-based BAI was associated with a higher risk of incident dementia across five community-based longitudinal cohorts. Future studies are warranted to evaluate the predictive value of BAI as a non-invasive digital biomarker for the early detection of dementia in community settings.
Source: medRxiv
Institutions: Beth Israel Deaconess Medical Center, University of California, San Francisco, University of Southern California, University of California, Los Angeles, University of California, Berkeley, Harvard University, Monash University, Wake Forest University Health Sciences, Wake Forest University, Brigham and Women's Hospital, California Pacific Medical Center, San Francisco VA Medical Center
Language: English
Subfield: Psychiatry and Mental health
Field: Medicine
Domain: Health Sciences
Open Access status: green
Funders: National Science Foundation, American Academy of Sleep Medicine, National Institutes of Health, Medical Research Council, National Health and Medical Research Council, National Institute on Aging, National Heart, Lung, and Blood Institute, National Institute of Neurological Disorders and Stroke, National Institute of Arthritis and Musculoskeletal and Skin Diseases
Awards: G109384441, G1261793039, MESA, G1276754516, Outcomes of Sleep Disorders in Older Men-Minneapolis, Study of Osteoporotic Fractures, Osteoporotic Fractures in Men (MrOS) - Minneapolis, Multimodal Network Connectivity Architecture (MOCA) of the Brain and its Role in the Recovery of Consciousness in Comatose Cardiac Arrest Patients, ASSOCIATION OF SLEEP DISORDERS WITH CARDIOVASCULAR HEALTH ACROSS ETHNIC GROUPS, Sex Hormones, Related Polymorphisms & Cognitive Decline, G1769451082, G1828249618, Wake Forest Clinical and Translational Science Award, Cognitive Benefits of Treating Sleep Apnea in Dementia, Long term fracture risk and change in peripheral bone in the oldest old men: The MrOS study, Sleep Heart Health Study, Study of Osteoporotic Fractures, Osteoporatic Fractures in Men (MrOS), Outcomes of Sleep Disorders in Older Men- Reading Center, G2130630498, G2144938473, G22458031, The Sleep Heart Health Study (SHHS), G237968709, MESA, G2585438117, G2733059257, National Sleep Research Resource (NSRR), MESA, Multidimensional Assessment of Brain Health as A Marker of Dementia Risk and Resilience, G2837638605, G286372155, G2905571579, G290884426, G291913881, SUBCLINICAL CARDIOVASCULAR DISEASE STUDY--EBCT READING, The Sleep Heart Health Study, G3093995152, G3333306818, SCH: INT: Collaborative Research: DeepSense: Interpretable Deep Learning for Zero-effort Phenotype Sensing and Its Application to Sleep Medicine, Osteoporotic Fractures in Men (Mr. Os) Palo Alto, G3705571440, Development of novel polysomnography-based digital biomarkers to predict Alzheimer’s disease and Parkinson’s disease in real world settings, SLEEP HEART HEALTH STUDY, MESA, G3955673373, Longitudinal Relationships Among Sleep, Cognition and Alzheimer's Disease Biomarkers: Discerning Causal Associations, Mediators and Susceptibility, G4222455271, G4249524944, Study of Osteoporotic Fractures, TITLE: MULTI-ETHNIC STUDY OF ATHEROSCLEROSIS (MESA), G4455209252, Osteoporotic Fractures in Men (MrOS) - Administrative Center, ARIC Neurocognitive Study (ARIC-NCS) Renewal UNC 4 of 5, Data Coordinating Center for Sleep Heart Health, Study of Osteoporotic Fractures, Study of Osteoporotic Fractures (SOF)-Pittsburgh Clinic, Sleep Heart Health Study, OPTION 3. 4/1/2014 - 3/31/2015. MULTI-ETHNIC STUDY OF ATHEROSCLEROSIS (MESA) - READING CENTER, NHLBI, MESA, ARIC Neurocognitive Study (ARIC-NCS) Renewal 4 of 5, Temporal Trends, Novel Imaging and Molecular Characterization of Preclinical and Clinical Alzheimer's Disease in the Framingham Cohorts, G5108002584, SUBCLINICAL CARDIOVASCULAR DISEASE STUDY-ULTRASOUND, G5234713383, Preclinical AD: Correlates of Amyloid, Tau PET and fcMRI in Framingham Gen 3 Young Adults, Establishing a Brain Health Index, G562502316, G5654179670, Sleep Heart Health Study (SHHS), G6015457257, Outcomes of Sleep Disorders in Older Men-Portland, Contributions of sleep to preclinical and clinical Alzheimer's disease, MRI, Genetics & Cognitive Precursors of AD and Dementia, Institute for Clinical and Translational Research, The Framingham Heart Study, MESA, Investigation of Sleep, G66341962, Osteoporotic Fractures in Men (Mr.OS), G6742279884, Osteoporotic Fractures in Men (MrOS) - San Francisco Coordinating Center, G676687084, ARIC Neurocognitive Study (ARIC-NCS) Renewal 2 of 5, ARIC Neurocognitive Study (ARIC-NCS), Study of Osteoporotic Fractures, Multiethnic Validation of VCID biomarkers in South Texas, The Sleep Heart Health Study, Osteoporotic Fractures in Men (MrOS) - Portland, Outcomes of Sleep Disorders in Older Men-Palo Alto, MESA, Outcomes of Sleep Disorders in Older Men, G7399262704, Osteoporotic Fractures in Men_MrOS Renewal_Birmingham, G7511203839, Changes in Sleep and Cognition in Older Women, Outcomes of Sleep Disorders in Older Men, G7725905694, Outcomes of Sleep Disorders in Older Men-Birmingham, G78770644, Clinical and Translational Science Award, G8113642496, Integrative Motor Activity Biomarker for the Risk of Alzheimer's Risk, Outcomes of Sleep Disorders in Older Men - Pittsburgh, G8271761265, 4 of 4: Study of Osteoporotic Fractures (SOF), Cognitively Healthy Nonagenarians in the Cross Cohort Collaboration (CCC), Big Data and Deep Learning for the Interictal-Ictal-Injury Contiuum, Epidemiology of Dementia in the Framingham Study, G9000004549, G9000004784, G9000006353, G9000017360, G9000019818, G9000025517, G9000063950, Oregon Clinical and Translational Research Institute, Lifecourse sleep, cognitive decline and risk of Alzheimer's disease: a pooled cohort study., ARIC Neurocognitive Study (ARIC-NCS) Renewal 2023-2028, Precursors of Stroke Incidence and Prognosis, Comparative Safety of Seizure Prophylaxis within the Medicare Program, Research Training in Geriatric Medicine, South Texas Alzheimer's Disease Center, G91634571
OpenAlex ID: W4414461290