Machine learning can unravel heterogeneous patterns of brain aging and neurodegeneration, but existing methods offer limited insights into disease progression due to reliance on cross-sectional data. We introduce Coupled Cross-sectional and Longitudinal Non-negative Matrix Factorization (CCL-NMF) to capture dominant brain aging patterns by simultaneously leveraging cross-sectional and longitudinal neuroimaging data. CCL-NMF allows individuals to co-express multiple patterns, capturing mixed neuropathologic processes. Applied to neuroimaging data from 48,949 individuals from the harmonized iSTAGING study, CCL-NMF identifies seven distinct, reproducible, and biologically relevant neuroanatomical patterns. Subject-specific loading coefficients quantifying the individual expression of these patterns show distinct associations with cognition, genetic, and lifestyle factors. To support broader application, a regression-based tool was developed to estimate loadings in external cohorts without rerunning the full framework. By enabling individualized estimation of distinct brain aging patterns, these findings may improve risk assessment and therapeutic evaluation in neurodegenerative diseases. Although demonstrated using structural MRI, this framework is generalizable to other imaging modalities and biomarker types. A machine-learning framework integrating cross-sectional and longitudinal brain imaging reveals distinct brain aging trajectories in ~49,000 individuals and links them to Alzheimer’s disease biomarkers, cognition, and cardiovascular risk factors.
Skampardoni et al. (2026) studied this question.