Developing clinical prediction models: a step-by-step guide
Predicting future outcomes of patients is essential to clinical practice, with many prediction models published each year. Empirical evidence suggests that published studies often have severe methodological limitations, which undermine their usefulness. This article presents a step-by-step guide to help researchers develop and evaluate a clinical prediction model. The guide covers best practices in defining the aim and users, selecting data sources, addressing missing data, exploring alternative modelling options, and assessing model performance. The steps are illustrated using an example from relapsing-remitting multiple sclerosis. Comprehensive R code is also provided.
Authors
- Thomas P. A. Debray (ORCID: https://orcid.org/0000-0002-1790-2719)
- Orestis Efthimiou (ORCID: https://orcid.org/0000-0002-0955-7572)
- Konstantina Chalkou (ORCID: https://orcid.org/0000-0001-9718-021X)
- Matthias Egger (ORCID: https://orcid.org/0000-0001-7462-5132)
- Michael Seo (ORCID: https://orcid.org/0000-0002-5229-590X)
- Georgia Salanti (ORCID: https://orcid.org/0000-0002-3830-8508)
Institutions
- University of Bern (CH)
- Centraal Bureau voor de Statistiek (NL)
- University of Bristol (GB)
- Institute of Social and Preventive Medicine (CH)
Publication Details
- Journal
- BMJ
- Published
- 2024-09-03
- DOI
- https://doi.org/10.1136/bmj-2023-078276
- Citations
- 248
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 86.15
Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung