Researchers at Stanford University have developed an artificial intelligence system capable of predicting the risk of developing certain diseases, or even dying, by analyzing data from a single night’s sleep.
The research team examined the sleep records of more than 65,000 people for the study, showcasing their SleepFM AI tool, which they say can accurately predict the risks of 130 diseases years before diagnosis.
RELATED STORY | National Sleep Foundation Reveals Lack of Sleep Leads to Teen Depression
“We record an incredible number of signals when we study sleep,” said Emmanuel Mignot, a professor of sleep medicine at Stanford University and co-author of the study. study. “It’s a kind of general physiology that we study for eight hours in a completely captive subject. It’s very rich in data.”
The AI analyzed over 585,000 hours of sleep data from participants aged 2 to 96. Researchers said the system exceeded 80% accuracy in identifying potential risks, including cancer, pregnancy complications, circulatory problems, mental disorders, Parkinson’s disease and dementia.
IN CASE YOU MISSED IT | OpenAI collaborates with doctors to improve ChatGPT’s mental health response
“From an AI perspective, sleep is relatively understudied,” said co-author James Zou. “There is a lot of other work in AI that focuses on pathology or cardiology, but relatively little on sleep, even though sleep is such an important part of life.”
Watch the Scripps News interview with Mignot and Zou, co-authors of the study, in the video player above.
WATCH | True or False: Can You Spot AI-Generated Images?