External validation of predictive models for diagnosis, management and severity of pediatric appendicitis
While the performance of transferred models was satisfactory, it remained lower than on the original data. This study demonstrates challenges in transferring models between hospitals, especially when clinical practice and demographics differ or in the presence of externalities such as pandemics. We also highlight the limitations of retraining as a potential remedy since it could not restore predictive performance to the initial level.
Authors
- Bertram Reingruber
- Christian Knorr (ORCID: https://orcid.org/0000-0002-7146-780X)
- Julia E. Vogt (ORCID: https://orcid.org/0000-0002-6004-7770)
- Ričards Marcinkevičs (ORCID: https://orcid.org/0000-0001-8901-5062)
- Patricia Reis Wolfertstetter (ORCID: https://orcid.org/0000-0002-5479-469X)
- Sven Wellmann (ORCID: https://orcid.org/0000-0001-9230-6266)
- Kacper Sokol
- Akhil Paulraj
- Melinda A. Hilbert
- Vivien Rimili
Institutions
- University Hospital Regensburg (DE)
- ETH Zurich (CH)
- Düsseldorf University Hospital (DE)
- Nightingale Hospital (IN)
- University of Regensburg (DE)
Publication Details
- Journal
- Frontiers in Pediatrics
- Published
- 2025-08-29
- DOI
- https://doi.org/10.3389/fped.2025.1587488
- Citations
- 1
- Primary Topic
- Appendicitis Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 2.25
Funders
- Eidgenössische Technische Hochschule Zürich