Performance of Plug-In Augmented ChatGPT and Its Ability to Quantify Uncertainty: Simulation Study on the German Medical Board Examination
The high performance of GPTs in answering medical questions positions it well for applications in academia and, potentially, clinical practice. Its capability to quantify uncertainty in answers suggests it could be a valuable artificial intelligence agent within the clinical decision-making loop. Nevertheless, significant challenges must be addressed before artificial intelligence agents can be robustly and safely implemented in the medical domain.
Authors
- Felix Patricius Hans (ORCID: https://orcid.org/0000-0002-7164-7624)
- Mischa Selig
- Leo Benning (ORCID: https://orcid.org/0000-0002-8429-9702)
- Hans-Jörg Busch (ORCID: https://orcid.org/0000-0002-3897-1908)
- Bernd Rolauffs (ORCID: https://orcid.org/0000-0002-3275-8196)
- Julian Madrid (ORCID: https://orcid.org/0000-0001-5135-6873)
- Tobias Scheef
- Philipp Diehl (ORCID: https://orcid.org/0000-0001-5495-8511)
Institutions
- University of Freiburg (DE)
- University Medical Center Freiburg (DE)
- Ortenau Klinikum (DE)
Publication Details
- Journal
- JMIR Medical Education
- Published
- 2024-11-23
- DOI
- https://doi.org/10.2196/58375
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.48