Archive · 13 Jan 2026
AI Model Predicts 130 Diseases from One Night's Sleep
Scientists at Stanford Medicine created an AI called SleepFM that can predict over 130 diseases by analyzing just one night of sleep.
They trained it using sleep data from 65,000 people, including brain activity, heart rate, and breathing.
The AI is good at predicting serious diseases like Parkinson’s, cancer, and heart problems.
The researchers want to make it even better by adding data from wearable devices.
This could help doctors find health issues early, but they are still figuring out exactly how the AI makes its predictions.
Stanford Medicine developed SleepFM, an AI model predicting 130 diseases from one night of sleep data.
Trained on 600,000 hours of sleep data from 65,000 participants, including brain and heart activity.
Achieved high accuracy (C-index > 0.8) in predicting diseases like Parkinson’s, cancer, and heart conditions.
Researchers plan to improve the model by incorporating data from wearable devices.
SleepFM is one of the first AI models to use sleep data for disease prediction.
- Who
- Researchers from Stanford Medicine
- What
- Developed an AI model called SleepFM that predicts disease risk from sleep data
- When
- Data collected between 1999 and 2024, study published in Nature Medicine
- Where
- Stanford Medicine, United States
- Why
- To provide early disease prediction using sleep data
- AI Model Name
- SleepFM
- Developed By
- Stanford Medicine
- Training Data
- 600,000 hours of sleep data from 65,000 participants
- Diseases Predicted
- 130 diseases
- Accuracy Metric
- C-index > 0.8 for many diseases
- Key Predictions
- Parkinson’s, dementia, heart attack, cancers, and more
- Future Improvements
- Adding wearable data to enhance accuracy