Advancing AI in radiology: a comparative analysis of ChatGPT-o1-preview and ChatGPT-3.5 in the Polish National Specialization Exam
Despite its high accuracy, the study was based on a relatively small set of questions, which limits the ability to fully assess the model's effectiveness. The results indicate the potential of AI as a tool to support clinical work, but further, more extensive research is necessary to evaluate its applicability and reliability in the medical environment.
Authors
- Miłosz Zbroszczyk (ORCID: https://orcid.org/0009-0003-2537-2695)
- Mikołaj Magiera (ORCID: https://orcid.org/0000-0001-9952-9681)
- Marta Rojek (ORCID: https://orcid.org/0009-0005-0807-5423)
- 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)
- Maja Dreger (ORCID: https://orcid.org/0009-0000-2333-4407)
Institutions
- Medical University of Silesia (PL)
Publication Details
- Journal
- Polish Journal of Radiology
- Published
- 2025-10-21
- DOI
- https://doi.org/10.5114/pjr/208356
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00