Diagnostic performance of multimodal large language models in radiological quiz cases: the effects of prompt engineering and input conditions
Claude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.
Authors
- Woo Kyoung Jeong (ORCID: https://orcid.org/0000-0002-0676-2116)
- Jaeseung Shin (ORCID: https://orcid.org/0000-0002-6755-4732)
- Taewon Han
Institutions
- Samsung Medical Center (KR)
- Sungkyunkwan University (KR)
Publication Details
- Journal
- ULTRASONOGRAPHY
- Published
- 2025-04-16
- DOI
- https://doi.org/10.14366/usg.25012
- Citations
- 4
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 9.92