Optimizing patient education for radioactive iodine therapy and the role of ChatGPT incorporating chain-of-thought technique: ChatGPT questionnaire
The results suggest that ChatGPT can furnish generally appropriate and helpful answers to frequently asked questions in radioactive iodine treatment, yet citation accuracy remains limited, underscoring the need for clinician oversight. GPT-4o and GPT-4 demonstrated comparable performance, indicating that model selection within this family has minimal impact under the controlled conditions studied.
Authors
- Chia‐Hung Kao (ORCID: https://orcid.org/0000-0002-6368-3676)
- Jing-Uei Hou
- Yi-Ching Lin (ORCID: https://orcid.org/0000-0002-5166-1330)
- Chiou‐Sheng Tsai (ORCID: https://orcid.org/0000-0003-3258-3805)
- Shih‐Chuan Tsai (ORCID: https://orcid.org/0000-0002-9147-2120)
- Pei-Chun Yeh (ORCID: https://orcid.org/0009-0004-7561-8304)
Institutions
- Asia University (TW)
- China Medical University (TW)
- Taichung Veterans General Hospital (TW)
- China Medical University Hospital (TW)
Publication Details
- Journal
- Digital Health
- Published
- 2025-05-01
- DOI
- https://doi.org/10.1177/20552076251357468
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00