The early warning paradox
Machine learning models in healthcare aim to predict critical outcomes but often overlook existing Early Warning Systems’ impact. Using data from King’s College Hospital, we demonstrate how current evaluation methods can lead to paradoxical results. We discuss challenges in developing ML models from retrospective data and propose a novel approach focused on identifying when patients enter a ‘risk state’ through latent health representations, potentially transforming clinical decision-making.
Authors
- Kenneth J. Rockwood (ORCID: https://orcid.org/0000-0002-6674-995X)
- Zina Ibrahim (ORCID: https://orcid.org/0000-0001-6203-2727)
- James Teo (ORCID: https://orcid.org/0000-0002-6899-8319)
- Edward Palmer (ORCID: https://orcid.org/0000-0002-3548-4282)
- Hugh Logan Ellis (ORCID: https://orcid.org/0000-0002-6428-0158)
- Martin Whyte (ORCID: https://orcid.org/0000-0002-2897-2026)
Institutions
- Dalhousie University (CA)
- King's College London (GB)
- University of Surrey (GB)
- King's College Hospital NHS Foundation Trust (GB)
- King's College School (GB)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2025-02-03
- DOI
- https://doi.org/10.1038/s41746-024-01408-x
- Citations
- 9
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 22.33
Funders
- South London and Maudsley NHS Foundation Trust
- National Institute for Health and Care Research
- King's College London
- University College London
- Dalhousie University
- Faculty of Medicine, Dalhousie University