AI models developed to map brain aging and dementia risk

Researchers are utilizing artificial intelligence to develop more precise methods for mapping brain aging and assessing dementia risk.

At the University of Southern California, scientists led by Associate Professor Andrei Irimia have created a deep-learning AI system that generates detailed maps of the brain. Unlike previous methods that provided a single “brain age” for the entire organ, this model uses MRI scans to identify specific regions that appear older or younger than expected. The study, published in PNAS, utilized data from over 14,000 adults to understand how structural changes vary across different brain areas.

In a separate approach, researchers from the University of California, San Francisco, and Beth Israel Deaconess Medical Center have developed a machine-learning model that analyzes electrical activity during sleep. By examining EEG recordings, the system calculates a “brain age” based on microscopic characteristics of brain waves. The study found that a 10-year gap between estimated brain age and chronological age correlates with a nearly 40% increase in dementia risk. This method focuses on specific signals, such as delta waves and sleep spindles, which may reveal cognitive changes that traditional sleep measurements miss.