Journal article · 2026 · Open access

A multimodal sleep foundation model for disease prediction

Rahul Thapa, Magnus Ruud Kjær, Bryan Dawei He, Ian Covert, Hyatt E. Moore, Umaer Hanif, Gauri Ganjoo, Michael Brandon Westover, P. Jennum, Andreas Brink-Kjær, Emmanuel Jean-Marie Mignot, James Zou

Nature Medicine, 32(2), 752–762 · Published 6 January 2026 · DOI 10.1038/s41591-025-04133-4

Open full textCite this paper

In brief

“A multimodal sleep foundation model for disease prediction” is a 2026 journal article by Rahul Thapa and 11 co-authors, published in Nature Medicine. OpenAlex counts 100 citations as of 16 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Nature Medicine.

Citations
100
Most cited in
2026 (92)
Field-weighted impact
382.48
References
85
Authors
12

Abstract

Sleep is a fundamental biological process with broad implications for physical and mental health, yet its complex relationship with disease remains poorly understood. Polysomnography (PSG)—the gold standard for sleep analysis—captures rich physiological signals but is underutilized due to challenges in standardization, generalizability and multimodal integration. To address these challenges, we developed SleepFM, a multimodal sleep foundation model trained with a new contrastive learning approach that accommodates multiple PSG configurations. Trained on a curated dataset of over 585,000 hours of PSG recordings from approximately 65,000 participants across several cohorts, SleepFM produces latent sleep representations that capture the physiological and temporal structure of sleep and enable accurate prediction of future disease risk. From one night of sleep, SleepFM accurately predicts 130 conditions with a C-Index of at least 0.75 (Bonferroni-corrected P < 0.01), including all-cause mortality (C-Index, 0.84), dementia (0.85), myocardial infarction (0.81), heart failure (0.80), chronic kidney disease (0.79), stroke (0.78) and atrial fibrillation (0.78). Moreover, the model demonstrates strong transfer learning performance on a dataset from the Sleep Heart Health Study—a dataset that was excluded from pretraining—and performs competitively with specialized sleep-staging models such as U-Sleep and YASA on common sleep analysis tasks, achieving mean F 1 scores of 0.70–0.78 for sleep staging and accuracies of 0.69 and 0.87 for classifying sleep apnea severity and presence. This work shows that foundation models can learn the language of sleep from multimodal sleep recordings, enabling scalable, label-efficient analysis and disease prediction.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Thapa, R., Kjær, M. R., He, B. D., Covert, I., Moore, H. E., Hanif, U., Ganjoo, G., Westover, M. B., Jennum, P., Brink-Kjær, A., Mignot, E. J.-M., & Zou, J. (2026). A multimodal sleep foundation model for disease prediction. Nature Medicine, 32(2), 752–762. https://doi.org/10.1038/s41591-025-04133-4

MLA 9

Thapa, Rahul, et al. “A multimodal sleep foundation model for disease prediction.” Nature Medicine, vol. 32, no. 2, 2026, pp. 752–762. https://doi.org/10.1038/s41591-025-04133-4.

Chicago

Thapa, Rahul, Magnus Ruud Kjær, Bryan Dawei He, Ian Covert, Hyatt E. Moore, Umaer Hanif, Gauri Ganjoo, et al. 2026. “A multimodal sleep foundation model for disease prediction.” Nature Medicine 32 (2): 752–762. https://doi.org/10.1038/s41591-025-04133-4.

Harvard

Thapa, R. et al. (2026) ‘A multimodal sleep foundation model for disease prediction’, Nature Medicine, 32(2), pp. 752–762. doi:10.1038/s41591-025-04133-4.

IEEE

R. Thapa et al., “A multimodal sleep foundation model for disease prediction,” Nature Medicine, vol. 32, no. 2, pp. 752–762, 2026, doi: 10.1038/s41591-025-04133-4.

BibTeX

@article{thapa2026multimodal,
  title     = {{A multimodal sleep foundation model for disease prediction}},
  author    = {Thapa, Rahul and Kjær, Magnus Ruud and He, Bryan Dawei and Covert, Ian and Moore, Hyatt E. and Hanif, Umaer and Ganjoo, Gauri and Westover, Michael Brandon and Jennum, P. and Brink-Kjær, Andreas and Mignot, Emmanuel Jean-Marie and Zou, James},
  journal   = {Nature Medicine},
  year      = {2026},
  volume    = {32},
  number    = {2},
  pages     = {752--762},
  doi       = {10.1038/s41591-025-04133-4},
  url       = {https://doi.org/10.1038/s41591-025-04133-4}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Social Sciences › Psychology › Experimental and Cognitive Psychology › Sleep and related disorders

  • polysomnography
  • disease risk prediction
  • contrastive learning
  • sleep stage classification
  • sleep apnea detection
  • all-cause mortality
  • dementia
  • myocardial infarction

Work with this paper

Most-cited papers in Psychology

All highly cited Psychology papers

Questions about this paper

How do I cite this paper in APA style?

Thapa, R., Kjær, M. R., He, B. D., Covert, I., Moore, H. E., Hanif, U., Ganjoo, G., Westover, M. B., Jennum, P., Brink-Kjær, A., Mignot, E. J.-M., & Zou, J. (2026). A multimodal sleep foundation model for disease prediction. Nature Medicine, 32(2), 752–762. https://doi.org/10.1038/s41591-025-04133-4

How many times has this paper been cited?

100 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Nature Medicine: sign in and open the full text from this page.

Who wrote this paper?

Rahul Thapa, Magnus Ruud Kjær, Bryan Dawei He, Ian Covert, Hyatt E. Moore, Umaer Hanif, Gauri Ganjoo, Michael Brandon Westover, P. Jennum, Andreas Brink-Kjær, Emmanuel Jean-Marie Mignot, James Zou.

What is the DOI of this paper?

10.1038/s41591-025-04133-4, permanently at https://doi.org/10.1038/s41591-025-04133-4. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.