人工智能可通过脑电波检测脑部衰老速度

加州大学旧金山分校和波士顿贝斯以色列迪康内斯医学中心的研究人员开发了一套机器学习系统，能够通过分析睡眠脑电图来估算人的脑龄。1该系统基于脑电图记录中的13个微观特征，其中包括Delta波和睡眠纺锤波等与记忆健康相关的指标。1

研究团队分析了约7000名年龄在40岁至94岁间的成年人的脑电图数据，监测期从3.5年到17年不等。1结果显示，脑龄高于实际年龄与痴呆症风险显著相关——脑龄每增加10年，痴呆症风险就会上升近40%。1在研究期间，约1000名参与者患上了痴呆症。1这项研究已发表在《JAMA Network Open》2026年第9卷第3期，文章编号e261521。1

Researchers at the University of California, San Francisco and Boston's Beth Israel Deaconess Medical Center have developed a machine learning system capable of estimating brain age from sleep brain wave patterns and assessing dementia risk 1. The model analyzed sleep electroencephalogram recordings from approximately 7,000 adults aged 40 to 94, incorporating 13 microscopic features from the brain wave data 1.

The study, published in JAMA Network Open in 2026 (Volume 9, Issue 3, article e261521), tracked participants over monitoring periods ranging from 3.5 to 17 years 1. Approximately 1,000 participants developed dementia during the study period 1. The findings revealed a significant correlation between elevated brain age relative to chronological age and dementia risk: for every 10-year increase in brain age, dementia risk rose by nearly 40 percent 1. The research identified delta waves and sleep spindles as indicators of memory health 1.