Assessing the feasibility of ChatGPT-4o and Claude 3-Opus in thyroid nodule classification based on ultrasound images
While LLMs such as ChatGPT-4o and Claude 3-Opus show promise for future applications in medical imaging, their current use in clinical diagnostics should be approached cautiously due to their limited accuracy.
Authors
- Jingguo Qu (ORCID: https://orcid.org/0000-0003-4780-4316)
- Nonhlanhla Chambara (ORCID: https://orcid.org/0000-0002-3183-883X)
- Fei Chen (ORCID: https://orcid.org/0000-0001-7891-6519)
- Ziman Chen
- Xina Lo (ORCID: https://orcid.org/0000-0002-3107-4155)
- Simon Takadiyi Gunda (ORCID: https://orcid.org/0000-0002-0461-5139)
- Xinyang Han (ORCID: https://orcid.org/0000-0003-1469-0754)
- Shirley Yuk‐Wah Liu (ORCID: https://orcid.org/0000-0003-3882-8885)
- Chaoqun Wu (ORCID: https://orcid.org/0000-0003-0110-5990)
- Michael Tin Cheung Ying
Institutions
- Hong Kong Polytechnic University (HK)
- Sun Yat-sen University (CN)
- Chinese University of Hong Kong (HK)
- Wenzhou Medical University (CN)
- First Affiliated Hospital of Wenzhou Medical University (CN)
- Fifth Affiliated Hospital of Sun Yat-sen University (CN)
- Prince of Wales Hospital (CN)
- Cardiff University (GB)
Publication Details
- Journal
- Endocrine
- Published
- 2024-10-11
- DOI
- https://doi.org/10.1007/s12020-024-04066-x
- Citations
- 34
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 12.16
Funders
- Hong Kong Polytechnic University