Sequential sample size calculations and learning curves safeguard the robust development of a clinical prediction model for individuals
For CPM development studies involving prospective data collection, a sequential sample size approach allows users to dynamically monitor individual-level prediction and classification instability. This helps determine when enough participants have been recruited and safeguards against using inaccurate assumptions in a sample size calculation before data collection. Engagement with patients and other stakeholders is crucial to identify sensible context-specific stopping rules for robust individual predictions.
Authors
- Joie Ensor (ORCID: https://orcid.org/0000-0001-7481-0282)
- Rebecca Whittle (ORCID: https://orcid.org/0000-0003-1793-0135)
- Mohsen Sadatsafavi (ORCID: https://orcid.org/0000-0002-0419-7862)
- Evangelia Christodoulou (ORCID: https://orcid.org/0000-0001-7900-5952)
- Richard D Riley (ORCID: https://orcid.org/0000-0001-8699-0735)
- Kym I E Snell (ORCID: https://orcid.org/0000-0001-9373-6591)
- Professor Gary S. Collins (ORCID: https://orcid.org/0000-0002-2772-2316)
- Amardeep Legha (ORCID: https://orcid.org/0000-0001-7389-5384)
- Ben Van Calster (ORCID: https://orcid.org/0000-0003-1613-7450)
- Lucinda Archer (ORCID: https://orcid.org/0000-0003-2504-2613)
Institutions
- University of British Columbia (CA)
- German Cancer Research Center (DE)
- Heidelberg University (DE)
- National Institute for Health and Care Research (GB)
- NIHR Birmingham Biomedical Research Centre (GB)
- KU Leuven (BE)
Publication Details
- Journal
- Journal of Clinical Epidemiology
- Published
- 2025-12-19
- DOI
- https://doi.org/10.1016/j.jclinepi.2025.112117
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- University Hospitals Birmingham NHS Foundation Trust
- National Institute for Health and Care Research
- Department of Health and Social Care
- Medical Research Council
- Engineering and Physical Sciences Research Council