Evaluating ChatGPT-4 for rheumatology patient education: a comparative analysis of readability, reliability, and similarity to the American College of Rheumatology’s fact sheets
Despite the moderate similarity, ChatGPT-generated texts on rheumatic diseases were more complex, less reliable, and longer than ACR fact sheets. These findings highlight the need for improvements in artificial intelligence-driven healthcare tools to ensure readability, accuracy, and reliability, making them more aligned with expert-reviewed resources.
Authors
- Mustafa Hüseyin Temel (ORCID: https://orcid.org/0000-0003-0256-5833)
- Fatih Bağcıer (ORCID: https://orcid.org/0000-0002-6103-7873)
- Yakup Erden (ORCID: https://orcid.org/0000-0003-3742-9903)
Institutions
- University of Health Science (KH)
- Istanbul Metropolitan Municipality (TR)
- Sağlık Bilimleri Üniversitesi (TR)
- Universidad CES (CO)
- Bolu Abant İzzet Baysal University (TR)
- University of Health Sciences Antigua (AG)
Publication Details
- Journal
- Reumatologia/Rheumatology
- Published
- 2025-11-11
- DOI
- https://doi.org/10.5114/reum/207526
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00