How AI can detect health risks — just from the way you sleep – DW – 01/11/2026
All it takes is one night's sleep in a laboratory, during which physiological signals are recorded, for a new artificial intelligence model to be able estimate a person's risk for about 130 diseases later in life. That includes risks for Parkinson's disease, dementia, heart disease, and cancers of the prostate and breast.
SleepFM can make these predictions years before the first symptoms become evident, said James Zou, a Stanford University professor of biomedical data science and a co-senior author of the the SleepFM study, published in early January in the journal Nature Medicine.
SleepFM was fed nearly 600,000 hours of sleep data collected from 65,000 sleepers. The study and measurement of sleep is called polysomnography and it uses various sensors to measure brain waves, heart activi...