Stanford’s AI spots hidden disease warnings that show up while you sleep
- Researchers at Stanford Medicine have developed an artificial intelligence system called SleepFM that estimates a person's risk of developing 130 different medical conditions from a single night of sleep.
- Trained on nearly 600,000 hours of sleep recordings from 65,000 individuals, SleepFM uses a contrastive learning method to understand how brain, heart, and airflow signals interact during rest.
- The model achieved C-index scores above 0.8 for Parkinson's disease, dementia, and hypertensive heart disease, with strong results across cancers and circulatory diseases.
- James Zou, PhD, associate professor of biomedical data science, said the team was "pleasantly surprised" the model makes informative predictions, "essentially learning the language of sleep."
- David Goff, acting director of NIH's National Heart, Lung, and Blood Institute, says future integration into diagnostic tests could screen for cardiovascular outcomes years before clinical symptoms arise.
12 Articles
12 Articles
A recent American study has shown that an analysis of the electrical activity of the heart during sleep using artificial intelligence techniques can help predict the risk of heart disease.
The Independent
The simple sleep test that can predict heart disease risk years in advance
Test can predict heart disease by assessing just one night of sleep
HEART ACTION during sleep could reveal the risk of cardiovascular disease up to ten years in advance.
Stanford’s AI spots hidden disease warnings that show up while you sleep
Stanford researchers have developed an AI that can predict future disease risk using data from just one night of sleep. The system analyzes detailed physiological signals, looking for hidden patterns across the brain, heart, and breathing. It successfully forecast risks for conditions like cancer, dementia, and heart disease. The results suggest sleep contains early health warnings doctors have largely overlooked.
A study published on October 9 by the scientific journal Sleep concluded that electrical activity of the heart during sleep can help to identify the risk of heart failure for the next 10 years.The research was conducted by American researchers who used polysomnography data, tests that record different signs of the body during sleep. Among the information collected is the electrocardiogram, which accompanies electrical activity of the heart throu…
Coverage Details
Bias Distribution
- 67% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
