A study led by UC San Francisco and Beth Israel Deaconess Medical Center reports on Mar. 19 that machine-learning analysis of brain waves recorded during sleep may help identify people at high risk of developing dementia.
The research suggests that estimating a person's "brain age" from sleep signals using electroencephalogram (EEG) can provide important clues about future dementia risk. When the estimated brain age was higher than the actual age, the risk of developing dementia increased. For every 10-year difference between brain age and actual age, the risk rose by nearly 40%. Conversely, those with a lower brain age compared to their actual age had a reduced risk.
The study, published in JAMA Network Open, used a machine-learning model that integrated 13 microstructural features of brain waves from EEG recordings. Data were collected from about 7,000 participants aged between 40 and 94 who did not have dementia at the start of the study. Over follow-up periods ranging from 3.5 to 17 years, approximately 1,000 participants developed dementia.
Researchers found that analyzing fine-scale patterns in brain waves during sleep provided insights missed by conventional sleep metrics such as time spent in different sleep stages or overall sleep efficiency. "Broad sleep metrics don't fully capture the complex multidimensional nature of sleep physiology," said senior author Yue Leng, MBBS, PhD, associate professor of psychiatry at the UCSF School of Medicine.
Several specific EEG patterns contributed to determining brain age. These included delta waves associated with deep sleep and memory consolidation spindles. Notably, sudden large spikes on EEG known as kurtosis were linked to a lower risk of dementia. The association between older brain age and increased dementia risk remained significant even after accounting for education level, smoking status, body mass index, physical activity, other health conditions, and genetic factors.
Because EEG signals can be collected noninvasively—even potentially through wearable technology—the researchers suggest this approach could eventually help detect dementia risk outside clinical settings. "Brain age is calculated from sleep brain waves," said Leng. "We know that brain activity during sleep provides a measurable window into how well the brain is aging." The findings also raise questions about whether improving sleep health could influence how the brain ages over time.
First author Haoqi Sun, PhD, assistant professor of neurology at Beth Israel Deaconess Medical Center who developed the model with two co-authors*, said: "Better body management, such as lowering body mass index and increasing exercise to reduce the likelihood of apnea, may have an impact. But there's no magic pill to improve brain health."
