Crossmark

Multi-source data integration through pooling and transfer learning improves generalizability and specialization of deep learning models for ICU mortality and length of stay prediction: a four-database external validation study

Crossref DOI link: https://doi.org/10.1186/s13054-026-06034-5

Published Online: 2026-05-18

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Allyn, Jerome

Oliver, Matthieu

Cerveau, Raphaël

Allou, Nicolas

Barennes, Tristan

Ferdynus, Cyril
Funding

Funding for this research was provided by:

feder, region REUNION, European Union
License Information

Text and Data Mining valid from 2026-05-18

Version of Record valid from 2026-07-10
More Information

Article History

Received: 11 February 2026

Accepted: 12 April 2026

First Online: 18 May 2026

Declarations

:

: The institutional review boards of the Beth Israel Deaconess Medical Center granted a waiver of informed consent and approved the sharing of the research resource.

: Not applicable. The individual data presented in this article were anonymized and not identifiable.

: The authors declare no competing interests.

Document is current

Any future updates will be listed below