A study by UC San Francisco and Beth Israel Deaconess Medical Center suggests that a machine-learning analysis of brain waves recorded during sleep may help identify individuals at high risk of developing dementia.
The research found that when a person's "brain age," as estimated from sleep signals using electroencephalogram (EEG), exceeded their chronological age, the risk of dementia increased. For every 10-year increase in brain age compared to actual age, the dementia risk rose by approximately 40%. Conversely, a lower brain age than actual age correlated with a reduced dementia risk.
Methodology
Published in JAMA Network Open on March 19, the study utilized a machine-learning model incorporating 13 microstructural features of brain waves from EEG recordings. Data was gathered from approximately 7,000 participants across five studies.
Participants, aged between 40 and 94, did not have dementia at the study's outset. They were followed for periods ranging from 3.5 to 17 years. During this follow-up, about 1,000 participants developed dementia.
Key Findings
Analysis of fine-scale patterns in sleep brain waves provided insights that conventional sleep metrics, such as time in sleep stages or overall sleep efficiency, often do not capture. Earlier pooled analyses had not found significant links between dementia risk and traditional sleep measures.
Senior author Yue Leng noted that "Broad sleep metrics don't fully capture the complex multidimensional nature of sleep physiology."
Several sleep EEG patterns contributing to brain age, including delta waves (associated with deep sleep) and sleep spindles (linked to memory consolidation), are known to be involved in brain health and memory. A notable finding was that sudden large spikes observed on EEG, known as kurtosis, were associated with a lower risk of dementia.
The link between an "older" brain age and increased dementia risk remained significant even after accounting for various factors such as education, smoking, body mass index, physical activity, other health conditions, and genetic risk factors.
Potential for Early Detection and Intervention
The researchers suggest that because sleep EEG signals can be collected noninvasively, brain age could potentially assist in detecting dementia risk in nonclinical settings, possibly through wearable technologies.
Leng stated, "Brain age is calculated from sleep brain waves. We know that brain activity during sleep provides a measurable window into how well the brain is aging."
The findings also indicate that improving sleep health could influence brain aging. Leng mentioned that previous studies have shown that treating sleep disorders can alter sleep-related brain-wave patterns. First author Haoqi Sun added that "Better body management, such as lowering body mass index and increasing exercise to reduce the likelihood of apnea, may have an impact," while cautioning there is "no magic pill to improve brain health."