- NEWS AND VIEWS
From a single night of sleep, AI tools can uncover physiological patterns linked to disease and mortality that are missed by conventional sleep measures.
By
-
Rachel K. Rowe
-
Rachel K. Rowe is in the Department of Integrative Physiology, University of Colorado Boulder, Boulder, Colorado 80301, USA.
-
Sleep is essential for health, and disrupted sleep is a common feature of many diseases1. Growing evidence suggests that changes in sleep can emerge before a disease is diagnosed2,3, raising the possibility that sleep contains early signals of future health. Two publications from this year — one in Nature Communications by Bilal et al.4 and one in Nature Medicine by Thapa et al.5 — suggest that sleep data hold substantially more information about health than clinicians and researchers currently extract from them.
doi: https://doi.org/10.1038/d41586-026-03207-8
References
Shah, A. S. et al. Am. J. Lifestyle Med. https://doi.org/10.1177/15598276251346752 (2025).
Ramos, A. R., Wheaton, A. G. & Johnson, D. A. Prev. Chronic Dis. 20, E77 (2023).
Mannino, G. S., Baumann, C. R., Opp, M. R. & Rowe, R. K. Neurotrauma Rep. 6, 482–490 (2025).
Bilal, E. et al. Nature Commun. 17, 7603 (2026).
Thapa, R. et al. Nature Med. 32, 752–762 (2026).
Rundo, J. V. & Downey, R. III Handb. Clin. Neurol. 160, 381–392 (2019).
Schalkamp, A. K., Peall, K. J., Harrison, N. A. & Sandor, C. Nature Med. 29, 2048–2056 (2023).
Zheng, N. S. et al. Nature Med. 30, 2648–2656 (2024).
Competing Interests
The author declares no competing interests.
Related Articles
-
Read the paper: A foundation model for sleep-based risk stratification and clinical outcome
-
Read the paper: A multimodal sleep foundation model for disease prediction
-
Data from smart watches reveal early signs of insulin resistance
Deep sleep helps the heart to heal
