Evaluating the Ability of Artificial Intelligence to Address Nuanced Cardiology Subspecialty Questions: ChatGPT and CathSAP
The study demonstrates ChatGPT's potential for learning and adapting to medical examination scenarios, with a notable enhancement in performance after exposure to educational materials. However, limitations such as the model's inability to process certain visual materials and potential biases in AI models warrant further consideration. These findings underscore the need for continued research to optimize the use of AI in medical education and assessment.
Authors
- Robert Frankel (ORCID: https://orcid.org/0000-0002-7279-8336)
- Tharun Shyam
- Pan Su Pyae Kyaw (ORCID: https://orcid.org/0009-0008-6783-9720)
- Sahil A. Parikh (ORCID: https://orcid.org/0000-0002-0551-5885)
- Saurav Chatterjee (ORCID: https://orcid.org/0000-0002-1241-5030)
- Partha Sardar (ORCID: https://orcid.org/0000-0001-9647-2819)
- Khaled Abaza
- Saumya Nanda
Institutions
- Maimonides Medical Center (US)
- Hofstra University (US)
- Columbia University Irving Medical Center (US)
- Tisch Hospital (US)
- Vascular Institute of New York (US)
Publication Details
- Journal
- Journal of the Society for Cardiovascular Angiography & Interventions
- Published
- 2025-03-01
- DOI
- https://doi.org/10.1016/j.jscai.2025.102563
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65