{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,8]],"date-time":"2026-11-08T05:18:51Z","timestamp":1794115131645,"version":"4.8.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Clinical sleep studies capture multiple physiologic signals, yet interpretation is often reduced to single summary measures of limited prognostic value, such as the apnea\u2013hypopnea index. We present a foundation model that learns rich representations of sleep physiology from more than 10,000 clinical sleep recordings linked to electronic medical records. Here we show that sleep physiology contains latent risk structure invisible to conventional metrics, identifying five patient risk groups with markedly different trajectories for mortality, cardiovascular, and neurological disease. The highest-risk group shows more than double the mortality risk of the lowest, whereas apnea\u2013hypopnea index severity categories show limited predictive value. The framework generalizes to the independent Sleep Heart Health Study, distinguishing high- and low-risk patients despite lower-resolution data. We demonstrate that foundation models recover clinically meaningful risk information embedded in routine sleep recordings that conventional metrics systematically miss, providing a scalable path to precision sleep medicine.<\/jats:p>","DOI":"10.1038\/s41467-026-75326-9","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T09:04:14Z","timestamp":1785747854000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A foundation model for sleep-based risk stratification and clinical outcomes"],"prefix":"10.1038","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0778-6635","authenticated-orcid":false,"given":"Erhan","family":"Bilal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0979-3417","authenticated-orcid":false,"given":"Matheus Lima Diniz","family":"Araujo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4603-0235","authenticated-orcid":false,"given":"Kristen L.","family":"Beck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5407-0296","authenticated-orcid":false,"given":"Catherine M.","family":"Heinzinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5909-605X","authenticated-orcid":false,"given":"Samer","family":"Ghosn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4665-9946","authenticated-orcid":false,"given":"Carl Y.","family":"Saab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8900-3280","authenticated-orcid":false,"given":"Nancy","family":"Foldvary-Schaefer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1071-4504","authenticated-orcid":false,"given":"Jeffrey L.","family":"Rogers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6222-2675","authenticated-orcid":false,"given":"Reena","family":"Mehra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"75326_CR1","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1111\/j.1749-6632.2009.04416.x","volume":"1156","author":"MP Walker","year":"2009","unstructured":"Walker, M. P. The role of sleep in cognition and emotion. Ann. N. Y Acad. Sci. 1156, 168\u2013197 (2009).","journal-title":"Ann. N. Y Acad. Sci."},{"key":"75326_CR2","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/S2213-2600(19)30198-5","volume":"7","author":"AV Benjafield","year":"2019","unstructured":"Benjafield, A. V. et al. Estimation of the global prevalence and burden of obstructive sleep apnoea: a literature-based analysis. Lancet Respir. Med. 7, 687\u2013698 (2019).","journal-title":"Lancet Respir. Med."},{"key":"75326_CR3","doi-asserted-by":"publisher","first-page":"597","DOI":"10.5664\/jcsm.2172","volume":"08","author":"RB Berry","year":"2012","unstructured":"Berry, R. B. et al. Rules for scoring respiratory events in sleep: update of the 2007 AASM manual for the scoring of sleep and associated events. J. Clin. Sleep. Med. 08, 597\u2013619 (2012).","journal-title":"J. Clin. Sleep. Med."},{"key":"75326_CR4","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s11325-022-02592-4","volume":"27","author":"A Bandyopadhyay","year":"2023","unstructured":"Bandyopadhyay, A. & Goldstein, C. Clinical applications of artificial intelligence in sleep medicine: a sleep clinician\u2019s perspective. Sleep. Breath. 27, 39\u201355 (2023).","journal-title":"Sleep. Breath."},{"key":"75326_CR5","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1136\/thoraxjnl-2017-210431","volume":"73","author":"AV Zinchuk","year":"2018","unstructured":"Zinchuk, A. V. et al. Polysomnographic phenotypes and their cardiovascular implications in obstructive sleep apnoea. Thorax 73, 472\u2013480 (2018).","journal-title":"Thorax"},{"key":"75326_CR6","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1164\/rccm.201808-1509OC","volume":"200","author":"DR Mazzotti","year":"2019","unstructured":"Mazzotti, D. R. et al. Symptom subtypes of obstructive sleep apnea predict incidence of cardiovascular outcomes. Am. J. Respir. Crit. Care Med 200, 493\u2013506 (2019).","journal-title":"Am. J. Respir. Crit. Care Med"},{"key":"75326_CR7","first-page":"1993","volume":"39","author":"CB Miller","year":"2016","unstructured":"Miller, C. B. et al. Clusters of insomnia disorder: an exploratory cluster analysis of objective. Sleep. Parameters Reveals Differ. Neurocogn. Functioning, Quant. EEG Heart Rate Variability. Sleep. 39, 1993\u20132004 (2016).","journal-title":"Sleep. Parameters Reveals Differ. Neurocogn. Functioning, Quant. EEG Heart Rate Variability. Sleep"},{"key":"75326_CR8","doi-asserted-by":"crossref","unstructured":"Malhotra, A. et al. Metrics of sleep apnea severity: beyond the apnea-hypopnea index. Sleep 44, 30 (2021).","DOI":"10.1093\/sleep\/zsab030"},{"key":"75326_CR9","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/S2213-8587(18)30051-2","volume":"6","author":"E Ahlqvist","year":"2018","unstructured":"Ahlqvist, E. et al. Novel subgroups of adult-onset diabetes and their association with outcomes: a data-driven cluster analysis of six variables. Lancet Diab. Endocrinol. 6, 361\u2013369 (2018).","journal-title":"Lancet Diab. Endocrinol."},{"key":"75326_CR10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-05892-0","volume":"9","author":"AL Young","year":"2018","unstructured":"Young, A. L. et al. Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference. Nat. Commun. 9, 4273 (2018).","journal-title":"Nat. Commun."},{"key":"75326_CR11","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M. et al. Foundation models for generalist medical artificial intelligence. Nature 616, 259\u2013265 (2023).","journal-title":"Nature"},{"key":"75326_CR12","unstructured":"Vaswani, A. Attention is all you need. Advances in Neural Information Processing Systems (NIPS, 2017)."},{"key":"75326_CR13","doi-asserted-by":"crossref","unstructured":"Thapa, R. et al. A multimodal sleep foundation model developed with 500\u2009K hours of sleep recordings for disease predictions. Nat. Med. 32, 752\u2013762 (2025).","DOI":"10.1038\/s41591-025-04133-4"},{"key":"75326_CR14","doi-asserted-by":"crossref","unstructured":"Vallat, R. & Walker, M. P. An open-source, high-performance tool for automated sleep staging. Elife 10, 70092 (2021).","DOI":"10.7554\/eLife.70092"},{"key":"75326_CR15","first-page":"1077","volume":"20","author":"SF Quan","year":"1997","unstructured":"Quan, S. F. et al. The sleep heart health study: design, rationale, and methods. Sleep 20, 1077\u20131085 (1997).","journal-title":"Sleep"},{"key":"75326_CR16","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1093\/jamia\/ocy064","volume":"25","author":"G-Q Zhang","year":"2018","unstructured":"Zhang, G.-Q. et al. The National Sleep Research Resource: towards a sleep data commons. J. Am. Med. Inform. Assoc. 25, 1351\u20131358 (2018).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"75326_CR17","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1161\/CIRCULATIONAHA.109.901801","volume":"122","author":"DJ Gottlieb","year":"2010","unstructured":"Gottlieb, D. J. et al. Prospective study of obstructive sleep apnea and incident coronary heart disease and heart failure: the sleep heart health study. Circulation 122, 352\u2013360 (2010).","journal-title":"Circulation"},{"key":"75326_CR18","doi-asserted-by":"publisher","first-page":"e1000132","DOI":"10.1371\/journal.pmed.1000132","volume":"6","author":"NM Punjabi","year":"2009","unstructured":"Punjabi, N. M. et al. Sleep-disordered breathing and mortality: a prospective cohort study. PLoS Med. 6, e1000132 (2009).","journal-title":"PLoS Med."},{"key":"75326_CR19","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1164\/rccm.202507-1574ST","volume":"211","author":"TM Tolbert","year":"2025","unstructured":"Tolbert, T. M. et al. Research priorities for translating endophenotyping of adult obstructive sleep apnea to the clinic: an official American Thoracic Society research statement. Am. J. Respir. Crit. Care Med. 211, 1562\u20131583 (2025).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"75326_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-84003-4","volume":"11","author":"EY Ma","year":"2021","unstructured":"Ma, E. Y. et al. Combined unsupervised-supervised machine learning for phenotyping complex diseases with its application to obstructive sleep apnea. Sci. Rep. 11, 4457 (2021).","journal-title":"Sci. Rep."},{"key":"75326_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-70039-5","volume":"10","author":"JW Kim","year":"2020","unstructured":"Kim, J. W. et al. Polysomnographic phenotyping of obstructive sleep apnea and its implications in mortality in Korea. Sci. Rep. 10, 13207 (2020).","journal-title":"Sci. Rep."},{"key":"75326_CR22","doi-asserted-by":"publisher","first-page":"205520762412970","DOI":"10.1177\/20552076241297056","volume":"10","author":"SJ Nelson","year":"2024","unstructured":"Nelson, S. J. et al. Are ICD codes reliable for observational studies? Assessing coding consistency for data quality. Digit Health 10, 20552076241297056 (2024).","journal-title":"Digit Health"},{"key":"75326_CR23","doi-asserted-by":"crossref","unstructured":"Bilal, E., et al. A novel approach for phenotypic characterization of sleep disorders. In: 2024 IEEE International Conference on Digital Health (ICDH) 8\u201313 (IEEE, 2024).","DOI":"10.1109\/ICDH62654.2024.00014"},{"key":"75326_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00630-9","volume":"5","author":"A Brink-Kjaer","year":"2022","unstructured":"Brink-Kjaer, A. et al. Age estimation from sleep studies using deep learning predicts life expectancy. npj Digital Med. 5, 103 (2022).","journal-title":"npj Digital Med."},{"key":"75326_CR25","unstructured":"Kingma, D. P. Adam: a method for stochastic optimization. arXiv Preprint arXiv:1412.6980 (2014)."},{"key":"75326_CR26","unstructured":"Sz\u00e9kely, G. E-statistics: energy of statistical samples (Tech. Rep. No. 02-16). (Bowling Green State University, 2002)."},{"key":"75326_CR27","doi-asserted-by":"crossref","unstructured":"Rubner, Y., Tomasi, C. & Guibas, L. J. A metric for distributions with applications to image databases. in Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271) 59\u201366 (IEEE, 1998).","DOI":"10.1109\/ICCV.1998.710701"},{"key":"75326_CR28","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","volume":"58","author":"JH Ward Jr","year":"1963","unstructured":"Ward, J. H. Jr Hierarchical grouping to optimize an objective function. J. Am. Stat. Assoc. 58, 236\u2013244 (1963).","journal-title":"J. Am. Stat. Assoc."},{"key":"75326_CR29","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1111\/j.1524-4733.2009.00671.x","volume":"13","author":"S Xu","year":"2010","unstructured":"Xu, S. et al. Use of stabilized inverse propensity scores as weights to directly estimate relative risk and its confidence intervals. Value Health 13, 273\u2013277 (2010).","journal-title":"Value Health"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75326-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75326-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75326-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:25:07Z","timestamp":1791825907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-75326-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["75326"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-75326-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6307069\/v1","asserted-by":"object"}]},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"31 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"7603"}}