Evaluating the potential of ChatGPT for patient identification in clinical breast cancer trials
While model performance was limited by simplified input data and a small single-center cohort, the results suggest that ChatGPT-4.0, in its current form, is not yet suitable as a stand-alone tool for patient identification in clinical breast cancer trials. To ensure accurate and efficient recruitment, the involvement of a multiprofessional team remains essential. Ongoing model refinement and access to larger, more detailed datasets may enhance the future utility of AI systems in clinical trial screening.
Authors
- Carolin C. Hack (ORCID: https://orcid.org/0000-0002-2426-7020)
- Oliver Schleicher
- Peter A. Fasching (ORCID: https://orcid.org/0000-0003-4885-8471)
- Lothar Häberle (ORCID: https://orcid.org/0000-0003-4019-9328)
- Felix Heindl (ORCID: https://orcid.org/0000-0002-5484-2575)
- Matthias W. Beckmann (ORCID: https://orcid.org/0000-0002-8441-693X)
- Katharina Seitz (ORCID: https://orcid.org/0000-0002-2638-2655)
- Annika Krückel (ORCID: https://orcid.org/0009-0007-3298-9238)
- Julius Emons (ORCID: https://orcid.org/0000-0002-2520-4443)
- Lena Brückner
- Julia Gocke
Institutions
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Universitätsklinikum Erlangen (DE)
- Comprehensive Cancer Center Erlangen (DE)
Publication Details
- Journal
- Digital Health
- Published
- 2025-05-01
- DOI
- https://doi.org/10.1177/20552076251389325
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00