Evaluating the SWIFT algorithm's efficacy in predicting hypoxemia across multiple critical care datasets
The study highlights challenges in generalizing prediction models across diverse ICU populations, emphasizing need for external validation. Further research should focus on improving model adaptability and interpretability, considering the practical application in clinical settings.
Authors
- Ludwig Christian Hinske (ORCID: https://orcid.org/0000-0001-7273-5899)
- Julia Sander (ORCID: https://orcid.org/0000-0002-4159-2351)
- Seyedmostafa Sheikhalishahi (ORCID: https://orcid.org/0000-0002-0121-0160)
- Mathias Kaspar (ORCID: https://orcid.org/0000-0002-6722-766X)
- Lena Pigat (ORCID: https://orcid.org/0009-0007-9199-2242)
- Baocheng Wang
- Leon Schmidt
Institutions
- University Hospital Augsburg (DE)
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- Journal of Critical Care
- Published
- 2025-05-19
- DOI
- https://doi.org/10.1016/j.jcrc.2025.155123
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.48