AI Revolutionizes Health Prognosis Through Sleep Data Analysis

Researchers have created an AI model, 'SleepFM', that predicts health risks across 130 conditions by analyzing sleep data. Developed with six lakh hours of data from 65,000 participants, SleepFM excels in forecasting issues like cancer and mental disorders, offering new potential in early disease detection.

Researchers at Stanford University have unveiled an artificial intelligence model, 'SleepFM', capable of predicting one's risk for over a hundred health conditions using sleep data. This breakthrough leverages more than six lakh hours of sleep information from 65,000 participants.

The AI, highlighted in Nature Medicine, surpasses standard sleep analysis tasks by also predicting disease onset, such as cancer and mental disorders, using comprehensive health records. The method employed includes a novel training technique termed 'leave-one-out' contrastive learning, enhancing its diagnostic accuracy.

Disease prediction success was most notable in severe conditions, with a C-index score above 0.8. The AI's insights into sleep signals present significant advancements in healthcare, opening pathways for early detection and intervention.

(With inputs from agencies.)