A comparison of modeling approaches for static and dynamic prediction of central line-associated bloodstream infections using electronic health records (part 2): random forest models
In the absence of censoring, complex modelling choices do not considerably improve the predictive performance compared to a binary model for CLABSI prediction in our studied settings. Survival models censoring the competing events at their time of occurrence should be avoided.
Authors
- Frank Rademakers (ORCID: https://orcid.org/0000-0002-7786-4179)
- Pieter Stijnen (ORCID: https://orcid.org/0000-0002-3047-6902)
- Yves Debaveye (ORCID: https://orcid.org/0000-0003-1784-8297)
- Shan Gao (ORCID: https://orcid.org/0000-0003-0871-1694)
- Laure Wynants (ORCID: https://orcid.org/0000-0002-3037-122X)
- Veerle Cossey (ORCID: https://orcid.org/0000-0001-6900-1974)
- Ben Van Calster (ORCID: https://orcid.org/0000-0003-1613-7450)
- Elena Albu (ORCID: https://orcid.org/0000-0003-2602-0918)
- Christel Janssens
Institutions
- Maastricht University (NL)
- KU Leuven (BE)
Publication Details
- Journal
- Diagnostic and Prognostic Research
- Published
- 2025-07-21
- DOI
- https://doi.org/10.1186/s41512-025-00194-8
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- Vlaams Supercomputer Centrum
- Fonds Wetenschappelijk Onderzoek
- KU Leuven
- Vlaamse regering