Using synthetic data generated via conditioning with disease labels can enhance the pretraining efficiency and generalization of medical foundation models, as shown for the detection of eye diseases via fundus photographs.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Rent or buy this article
Prices vary by article type
from$1.95
to$39.95
Prices may be subject to local taxes which are calculated during checkout
References
Xu, H. et al. Nature 630, 181–188 (2024).
Zhou, Y. et al. Nature 622, 156–163 (2023).
Sun, Y. et al. Nat. Biomed. Eng. https://doi.org/10.1038/s41551-025-01365-0 (2025).
Ma, W. et al. NEJM AI 1, AIp2400289 (2024).
Li, J. et al. Nat. Med. 30, 2886–2896 (2024).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Rights and permissions
About this article
Cite this article
Sheng, B., Keane, P.A., Tham, YC. et al. Synthetic data boosts medical foundation models. Nat. Biomed. Eng 9, 443–444 (2025). https://doi.org/10.1038/s41551-025-01375-y
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s41551-025-01375-y
