A MACHINE LEARNING-derived brain age index is emerging as a powerful predictor of dementia, with large scale evidence showing that higher brain age index scores are strongly associated with increased future dementia risk in older adults.
Brain Age Index and Dementia Risk Background
The brain age index reflects the difference between biological brain ageing and chronological age, derived from sleep electroencephalography data. As interest grows in digital biomarkers, the brain age index offers a noninvasive approach to assess dementia risk and identify individuals at earlier stages of neurodegeneration. In this study, the machine learning–based EEG brain age index (BAI) measures the deviation between sleep EEG-based brain age and chronological age.
Methods and Results
The BAI was computed using interpretable machine learning, incorporating sleep EEG features extracted from central channels in overnight, home-based polysomnography. Fine-Gray models were used to assess the association between BAI and incident dementia within each cohort, accounting for death as a competing risk.
This individual participant data meta-analysis pooled 7105 adults without dementia from five longitudinal cohorts. The analysis revealed that 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 < .001). These associations remained after additional adjustment for comorbidities and apnea-hypopnea index scores (HR, 1.31 [95% CI, 1.14-1.50]; P < .001) and apolipoprotein E ε4 (HR, 1.22 [95% CI, 1.02-1.45]; P = .03), and they were consistent across sex and age groups.
Clinical Implications
These findings position the brain age index as a promising early detection tool for dementia, with potential integration into sleep studies and routine risk assessment. Future work should validate its predictive performance across diverse populations and explore its role alongside imaging and fluid biomarkers. Incorporating the brain age index into clinical pathways could support earlier intervention, improved patient stratification, and more efficient recruitment into preventive trials, ultimately advancing precision medicine approaches in dementia care.
Reference
Sun H et al. Machine learning–based sleep electroencephalographic brain age index and dementia risk: an individual participant data meta-analysis. JAMA Netw Open. 2026;9(3):e261521.
Featured image: Oleg on Adobe Stock
