A new machine-learning method that analyzes brain activity during sleep may help identify people at greater risk of dementia, according to ScienceDaily. The research was led by scientists at UC San Francisco and Beth Israel Deaconess Medical Center in Boston.
The system estimates a person’s “brain age” by studying EEG recordings taken while they sleep. Researchers found that dementia risk increased when the brain looked older than the person’s chronological age, with the likelihood rising by nearly 40% for every 10-year gap.
To build the model, the researchers combined 13 tiny features found in EEG brain wave patterns and tested it on information from about 7,000 people across five studies. The participants were ages 40 to 94 at the start of the studies, did not have dementia at that time, and were followed for 3.5 to 17 years. About 1,000 of them developed dementia during that period.
The study suggests that detailed patterns in sleep brain waves may reveal information not captured by standard sleep measurements, such as time spent in different sleep stages or how efficiently someone stays asleep. Senior author Yue Leng of UCSF said broad sleep metrics do not fully capture the complexity of sleep physiology.
Researchers say the findings could eventually help assess dementia risk outside a traditional clinic, since EEG signals can be collected without invasive procedures. They also noted that improving sleep health may influence brain aging, although first author Haoqi Sun said there is “no magic pill” to improve brain health.
