An artificial intelligence (AI)-assisted analysis of genetic, neurological, cardiovascular and other data from multiple studies revealed three distinct patterns of brain aging and dementia risk. Researchers have recently identified a normal trajectory and two subgroups presenting accelerated brain aging. Published in JAMA PsychiatryThese results suggest a pathway to improve the prediction of people at risk of developing Alzheimer’s disease or vascular dementia and could lead to greater efficacy in future studies of brain aging and dementia.
The study was conducted by an international collaborative team including NIA-funded researchers at the University of Pennsylvania as well as scientists from the NIA Intramural Research Program. Investigators used AI and machine learning methods to analyze more than two decades of neuroimaging, clinical, and cognitive data from more than 27,000 participants from various studies collected in the International Coordinate System-Based Consortium. imaging for aging and neurodegenerative diseases (iSTAGING). Researchers studied how structural changes in the brain were associated with multiple factors, including genetics, cardiovascular risk, beta-amyloid, cognitive decline, smoking, and white matter hyperintensity (WMH), which are lesions associated with Alzheimer’s disease and cognitive disorders.
The team identified three distinct patterns of brain aging: typical aging (A1); and two accelerated aging subgroups (A2 and A3) which were particularly visible after age 65. The A1 group tended to have minor brain atrophy, fewer cardiovascular genetic risk factors, and normal amounts of WMH. The A1 group’s average brain age – a measure of typical age-related physical brain changes – was a few years younger than the participants’ chronological age.
The A2 subgroup had the highest and fastest growing levels of WMH, as well as a higher incidence of genetic risk factors associated with cardiovascular disease and amyloid plaques in the brain. The brain age of participants in the A2 subgroup was two to three years ahead of their chronological age. The A3 subgroup had more widespread brain atrophy, more rapid progression of cognitive decline, more moderate cardiovascular risk factors, and a brain age three to five years above chronological age.
The investigators saw these results as a step toward future systems to better predict and classify trajectories of brain aging and cognitive decline related to Alzheimer’s disease in research trials and precision medicine. They hope to extend this work to more diverse samples of participants and over longer periods of time to allow additional tracking on physical and cognitive outcomes.
This research was supported by NIA grants P30 AG066444, K23 AG063993, P01 AG003991, P01 AG026276, R01 AG080635, R35 AG071916, R01 AG063887, and P30 AG072947.
These activities relate to the implementation of NIH AD+ADRD research. Milestone 9M: Dementia with multiple etiologies: establishing presymptomatic diagnoses and biomarkers.
Reference: Skampardoni Ioanna, et al. Genetic and clinical correlates of AI-based models of brain aging in cognitively healthy individuals. JAMA Psychiatry. 2024; 81(5):456-467. doi:10.1001/jamapsychiatry.2023.5599.
