Modernizing evidence generation for clinical artificial intelligence: the case for adaptive platform trials
Traditional diagnostic and prognostic trials cannot keep pace with rapidly evolving clinical artificial intelligence (AI) systems, particularly generative tools and continuously updating models. Adaptive platform trials offer a scalable framework for continuous, comparative, equity-focused evaluation by testing multiple AI tools and updates head-to-head within a master protocol that standardizes populations, endpoints, decision rules, and governance, while allowing dynamic addition or removal of arms and reuse of control groups.
Authors
- Davy van de Sande (ORCID: https://orcid.org/0000-0003-4484-0995)
- Stefan Sleijfer (ORCID: https://orcid.org/0000-0002-0446-9039)
- Michel E. van Genderen (ORCID: https://orcid.org/0000-0001-5668-3435)
- M. Arfan Ikram
- Diederik Gommers
- Lotty Hooft
- Imke Bloemen
Institutions
- Harvard University (US)
- Duke University (US)
- Utrecht University (NL)
- Leiden University Medical Center (NL)
- Erasmus MC (NL)
- University Medical Center Utrecht (NL)
- Erasmus MC Cancer Institute (NL)
- Erasmus University Rotterdam (NL)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-08-20
- DOI
- https://doi.org/10.1038/s41746-026-03154-8
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00