health 🧠 AI uncovers hidden health risks in sleep studies
AI analyzing sleep study data revealed biomarkers predicting broader health risks beyond what doctors usually spot. Researchers examined over 10,000 full-night sleep studies to link patterns with long-term medical outcomes. The AI identified five distinct patient subtypes with sharply varied health risks, detailed in Nature. For instance, the highest-risk group had twice the odds of death in five years compared to the lowest-risk group. This shows AI can move beyond summary measures to learn from the full richness of sleep physiology. 🩺