Sleep patterns could predict risk of dementia, cancer and stroke, study suggests
NEWNow you can listen to News articles!
New advances in artificial intelligence could use sleep data to predict disease risk, a new study suggests.
Stanford Medicine researchers have developed an AI model trained on nearly 600,000 hours of sleep data collected from more than 60,000 participants across multiple sleep clinics.
According to a university news release, the model, called SleepFM, can predict a person’s risk of developing more than 100 health conditions.
ALZHEIMER’S RISK COULD INCREASE WITH COMMON CONDITION THAT AFFECTS MILLIONS, STUDY FINDS
The researchers trained SleepFM using polysomnography, a comprehensive measure of sleep that tracks brain and heart activity, as well as breathing, leg and eye movements. It is considered the “gold standard” of sleep studies, they noted.
“Sleep contains much more information about future health than we currently use,” James Zou, Ph.D., associate professor of biomedical data science and co-senior author of the study, told News Digital.
The AI model (not pictured) was trained on nearly 600,000 hours of sleep data from 60,000 participants. (iStock)
“By learning the language of sleep, our AI model opens new doors for studying sleep science and medicine,” he added, noting that humans spend about a third of their lives sleeping.
INSUFFICIENT SLEEP IS LINKED TO A MAJOR HIDDEN HEALTH RISK, STUDY REVEALS
In the study, the team compared sleep data with participants’ electronic medical records, which provided up to 25 years of data.
The model analyzed 1,000 disease categories in those medical records and discovered 130 diseases that it could predict with “reasonable accuracy,” according to the release.
CLICK HERE TO DOWNLOAD THE News APP
“By analyzing a single night of sleep with powerful AI, we found that sleep patterns can predict the risk of more than 100 different diseases years before diagnosis,” Zou said.
According to researchers, humans spend about a third of their lives sleeping, making sleep a rich source of data. (iStock)
These include dementia, heart disease, stroke, kidney disease, and even overall mortality. The model’s predictions were particularly strong for cancer, pregnancy complications, circulatory conditions and mental disorders, the researchers noted.
CLICK HERE FOR MORE HEALTH STORIES
“He doesn’t explain that to us in English,” Zou said. “But we have developed different interpretation techniques to find out what the model is looking at when it makes a prediction for a specific disease.”
Findings from the study, funded in part by the National Institutes of Health, were published in the journal Nature Medicine.
Limitations and warnings
Dr. Harvey Castro, a board-certified physician emergency doctor and national speaker on artificial intelligence based in Dallas, commented on Stanford’s AI sleep tool in a statement to News Digital.
“A significant signal does not equate to a ready drug,” said Castro, who was not involved in the study. “SleepFM is a great advance, it is not yet a bedside tool.”
“Classifying risk is not the same as predicting outcomes.”
The expert also emphasized that while the tool classifies risk, it cannot necessarily predict that the disease will occur. “Classifying risk is not the same as predicting outcomes, and patients live by the outcomes,” he said.
Before the tool can be used in “real life,” it must be proven to work outside the lab, according to Castro.
CLICK HERE TO SUBSCRIBE TO OUR HEALTH NEWSLETTER
The Stanford researchers also acknowledged that the study had some limitations.
“There’s still a lot we don’t understand… Most analyzes focus on specific tasks like sleep staging and apnea detection,” Zou noted.
The team cautioned that this is a research project and is not intended to give specific medical advice beyond that “sleep is very important.”
The team hopes to create wearable devices that allow individual and informal use of the technology. (iStock)
Other limitations include the fact that the team used “multimodal sleep recordings” that recover very strong signals from the brain, heart and respiratory system.
The researchers hope to expand the research to collect data from patients using wearable devices, which could help determine exactly what the model is interpreting.
TRY OUR LATEST LIFESTYLE QUIZ
For now, the technology is only being tested in research settings and is not available to consumers.
Khloe Quill is a lifestyle production assistant at News Digital. She and the lifestyle team cover a range of topics including food and drink, travel and health.