ChatGPT-3.5 and the Polish thoracic surgery specialty examination: a performance evaluation
The result obtained by ChatGPT-3.5 is equivalent to a failing score on the examination. The confidence of responses correlated with their correctness, whereas limitations in clinical knowledge and consistency indicate the need for caution when using this model to assess specialized knowledge.
Authors
- Mikołaj Magiera (ORCID: https://orcid.org/0000-0001-9952-9681)
- Aleksandra Gaweł
- Jakub Kufel (ORCID: https://orcid.org/0000-0001-7633-3600)
- Michał Bielówka (ORCID: https://orcid.org/0009-0007-0609-1678)
- Dominika Kaczyńska
- Adam Mitręga (ORCID: https://orcid.org/0009-0004-3383-6477)
- Natalia Denisiewicz (ORCID: https://orcid.org/0009-0008-3921-0239)
- Anna Kożuch
- Miłosz Korbaś
Institutions
- Medical University of Silesia (PL)
Publication Details
- Journal
- Polish Journal of Cardio-Thoracic Surgery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.5114/kitp.2025.154986
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00