ICU readmission and mortality risk prediction: Generalizability of a multi-hospital model
A single, multi-hospital-based model performed comparably on external datasets, especially when cardiac surgery patients were excluded. However, when applied externally, model predictions risk being uncalibrated for specific patient subgroups and require careful calibration before implementation. While external models were more stable than local ones over OOD scores, their performance was comparable after excluding cardiac surgery patients. Although pooling data marginally improved performance on external datasets, the incorporation of data from diverse hospitals is likely to provide greater benefits.
Authors
- Roger M. Crane
- Patrick Thoral (ORCID: https://orcid.org/0000-0001-6140-7195)
- Tariq A. Dam (ORCID: https://orcid.org/0000-0003-1631-2378)
- Giovanni Cinà (ORCID: https://orcid.org/0000-0002-3521-8208)
- Corstiaan A. den Uil (ORCID: https://orcid.org/0000-0003-0635-2843)
- Daniël M. de Bruin (ORCID: https://orcid.org/0000-0003-3047-3637)
- Paul Elbers (ORCID: https://orcid.org/0000-0003-0447-6893)
Institutions
- OLVG (NL)
- Maasstad Ziekenhuis (NL)
- Amsterdam University Medical Centers (NL)
- Vrije Universiteit Amsterdam (NL)
- University of Amsterdam (NL)
Publication Details
- Journal
- Journal of Intensive Medicine
- Published
- 2025-06-13
- DOI
- https://doi.org/10.1016/j.jointm.2025.03.007
- Citations
- 1
- Primary Topic
- Cardiac, Anesthesia and Surgical Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 1.39