Experimental assessment of the performance of artificial intelligence in solving multiple-choice board exams in cardiology
Overall, the study suggests that most current language-based chatbots have limitations in accurately solving theoretical medical board exams. In general, currently widely available chatbots fell short of achieving a passing score in a theoretical cardiology board exam. Nevertheless, a few showed promising results. Further improvements in artificial intelligence language models may lead to better performance in medical knowledge applications in the future.
Authors
- Christophe Wyss (ORCID: https://orcid.org/0000-0001-8985-8588)
- Luca Oechslin (ORCID: https://orcid.org/0000-0002-4297-3199)
- Felix Christoph Tanner (ORCID: https://orcid.org/0000-0002-4315-2667)
- Patric Biaggi (ORCID: https://orcid.org/0000-0003-3445-7060)
- Jessica Huwiler
Institutions
- University of Zurich (CH)
- Zurich Heart House (CH)
- Swiss Society of Hypertension (CH)
- Dr. A. Ramachandran's Diabetes Hospitals (IN)
- Société Suisse de Dermatologie et Vénéréologie (CH)
Publication Details
- Journal
- Swiss Medical Weekly
- Published
- 2024-10-02
- DOI
- https://doi.org/10.57187/s.3547
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.60