An AI Can Now Tell If Your Brain Is Aging Faster 

While you sleep, your brain produces electrical signals. Those signals carry far more information than scientists previously realized — and now an AI developed by researchers at UC San Francisco and Beth Israel Deaconess Medical Center can read those signals and estimate how fast your brain is actually aging. The study, published in JAMA Network Open, analyzed EEG recordings from approximately 7,000 adults aged 40 to 94, followed for between 3.5 and 17 years. Around 1,000 developed dementia during that time. The machine-learning model analyzed 13 microscopic features within brain wave patterns during sleep and used them to calculate a "brain age" — an estimate of how old the brain behaves, distinct from how old the person actually is. When a person's estimated brain age was older than their chronological age, their dementia risk rose significantly. Every additional 10 years of brain aging raised the likelihood of developing dementia by nearly 40%. People whose estimated brain age was younger than their actual age had a lower risk.

EEG recordings are non-invasive and relatively accessible, and the researchers believe the technology could eventually work in wearable devices that monitor brain waves during sleep at home, allowing doctors to assess dementia risk years before symptoms appear. The findings also point to something hopeful: previous research has shown that treating sleep disorders can alter brain wave patterns, meaning improving sleep health may actually influence the rate at which a brain ages. "Brain age is calculated from sleep brain waves," said senior author Yue Leng of UCSF. "Brain activity during sleep provides a measurable window into how well the brain is aging." For the first time, we have a way to look through it.

Source:https://www.sciencedaily.com/releases/2026/07/260729051540.htm