new development artificial intelligence Sleep data may be used to predict disease risk, a new study suggests.
Researchers at Stanford Medicine developed an AI model trained on approximately 600,000 hours of sleep data collected from more than 60,000 participants at various sleep clinics.
The model, called SleepFM, can predict a person’s risk of developing more than 100 health conditions, according to a press release from the university.
Researchers trained SleepFM using comprehensive polysomnography. sleep measurement Track your brain and heart activity, breathing, leg movements, and eye movements. This is considered the “gold standard” in sleep research, they noted.
“Sleep contains more information. future health than we currently use,” Dr. James Zou, associate professor of biomedical data science and co-senior author of the study, told FOX News Digital.
“By learning the language of sleep, our AI model opens new doors for research in the science and medicine of sleep,” he added, noting that humans spend about a third of their lives sleeping.
Study finds lack of sleep is linked to serious hidden health risks
In the study, the team combined sleep data with participants’ sleep data. electronic health recordup to 25 years of data were provided.
The model analyzed 1,000 disease categories in these health records and found 130 diseases that it could predict with “moderate accuracy,” according to the release.
“When we analyzed a night of sleep with powerful AI, we found: sleep patterns We can predict the risk of more than 100 different diseases years before diagnosis,” Zou said.
This includes dementia, heart diseasestroke, kidney disease, and even overall mortality. The model’s predictions were particularly strong for cancer, pregnancy complications, cardiovascular disease, and mental disorders, the researchers noted.
For more health stories, click here
“English can’t explain it,” Zou pointed out. “But we have developed a variety of interpretation techniques to understand what the models are looking at when predicting specific diseases.”
The results of the study, which was partially funded by the National Institutes of Health, were published in the journal Nature Medicine.
Dr. Harvey Castro, Board Certified Physician emergency doctor The Dallas-based national speaker on artificial intelligence commented on Stanford University’s AI sleep tool in a statement to Fox News Digital.
“Significant signals are not equivalent to ready-to-use drugs,” said Castro, who was not involved in the study. “SleepFM is revolutionary, but it’s not yet a bedside tool.”
The expert also stressed that while the tool ranks risks, it does not necessarily predict disease outbreaks. “Risk ranking is not the same as predicting outcomes, and patients live with the consequences,” he said.
Before the tool can be used in “real life,” it must be proven to work outside the lab, Castro said.
Click here to sign up for our health newsletter
Researchers at Stanford University also acknowledged that the study had some limitations.
“There’s still a lot we don’t understand…Most analyzes focus on narrow tasks like sleep staging or apnea detection,” Zou said.
The research team cautioned that this was a research project and was not intended to give specific medical advice other than that “sleep is very important.”
Other limitations include the fact that the team used “multimodal sleep recording,” which captures very strong signals from the brain, heart, and brain. respiratory system.
The researchers hope to expand the study to collect data from patients using wearable devices, which could help pinpoint what the model is interpreting.
Test yourself with our latest lifestyle quiz
For now, the technology is only being tested in a research environment and is not available to consumers.
