Artificial intelligence may help detect whether a personโs brain is aging faster than their actual age by analyzing brain activity during sleep.
Researchers from UC San Francisco and Beth Israel Deaconess Medical Center developed a machine-learning method that estimates a personโs โbrain ageโ from sleep brain wave recordings. Their findings suggest that an older-than-expected brain age may be linked to a higher risk of developing dementia.
The study, published in JAMA Network Open, used electroencephalography, or EEG, to examine electrical activity in the brain during sleep.
The researchers analyzed EEG data from about 7,000 adults who took part in five separate studies. Participants were between 40 and 94 years old, and none had dementia at the beginning of the studies. They were then followed for periods ranging from 3.5 to 17 years.
During the follow-up period, about 1,000 participants developed dementia.
The AI model examined 13 detailed features within sleep EEG signals. These microscopic brain wave patterns provided information that common sleep measurements may miss.
Traditional sleep measures, such as time spent in different sleep stages or overall sleep efficiency, have not consistently shown strong links with dementia risk. However, the new findings suggest that more detailed brain activity during sleep may reveal hidden signs of brain aging.
The study found that when a personโs estimated brain age was older than their actual age, their risk of dementia increased. For every additional 10 years of brain aging beyond chronological age, the likelihood of developing dementia rose by nearly 40%.
In contrast, people whose estimated brain age was younger than their actual age had a lower risk of dementia.
Several of the EEG features used in the model are already known to support memory and cognitive health. These include delta waves, which are slow brain waves linked with deep sleep, and sleep spindles, short bursts of brain activity thought to help strengthen and store memories.
One notable signal, called kurtosis, involved large sudden spikes in EEG activity. This feature was associated with a lower risk of developing dementia.
The link between older brain age and higher dementia risk remained significant even after researchers accounted for other factors, including education, smoking, body mass index, physical activity, medical conditions, and genetic risk.
Because EEG is non-invasive, the researchers believe sleep-based brain age testing could one day become a useful tool for early dementia risk assessment. In the future, wearable devices may be able to collect brain wave data during sleep and help identify people who may need closer monitoring.
The findings also raise the possibility that improving sleep health could influence brain aging. Previous research has shown that treating sleep disorders can change brain wave activity, suggesting that better sleep and healthier lifestyle habits may support long-term brain health.
The researchers caution that there is no simple cure or โmagic pillโ for brain aging. However, managing health factors such as body weight, physical activity, and sleep disorders like sleep apnea may help protect the brain.
The study shows that the sleeping brain may carry important clues about future dementia risk long before memory problems appear.
Journal Reference:
Sun, H., Milton, S., Fang, Y., Taha, H. B., Shiju, S., Thomas, R. J., Ganglberger, W., Pase, M. P., Hughes, T., Purcell, S., Redline, S., Stone, K. L., Yaffe, K., Westover, M. B., & Leng, Y. (2026). Machine LearningโBased Sleep Electroencephalographic Brain Age Index and Dementia Risk. JAMA Network Open, 9(3), e261521. https://doi.org/10.1001/jamanetworkopen.2026.1521