Assessing large language models as assistive tools in medical consultations for Kawasaki disease
This study indicates that LLMs have great potential in providing information about KD, but their use requires caution due to quality inconsistencies and misinformation risks. Significant discrepancies existed across LLMs and prompting strategies. Claude 3.5 Sonnet offered the best response quality and accuracy, while Gemini 1.5 Pro excelled in comprehensibility. PF prompting with Claude 3.5 Sonnet is most recommended for parents seeking KD information. As AI evolves, expanding research and refining models is crucial to ensure reliable, high-quality information.
Authors
- Fan Ma (ORCID: https://orcid.org/0000-0003-1099-3299)
- Chunyi Yan (ORCID: https://orcid.org/0000-0003-1744-6626)
- Shuran Shao (ORCID: https://orcid.org/0000-0002-7960-2068)
- Yunqiang Liang
- Bowen Li (ORCID: https://orcid.org/0000-0003-4893-0525)
- Nanjun Zhang (ORCID: https://orcid.org/0000-0002-6980-4547)
- Chuan Wang (ORCID: https://orcid.org/0000-0001-5165-8273)
- Kaiyu Zhou (ORCID: https://orcid.org/0000-0002-4783-4243)
- Zexi Li (ORCID: https://orcid.org/0000-0001-7943-5215)
Institutions
- Sichuan University (CN)
- West China Second University Hospital of Sichuan University (CN)
- West China Hospital of Sichuan University (CN)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-03-31
- DOI
- https://doi.org/10.3389/frai.2025.1571503
- Citations
- 4
- Primary Topic
- Kawasaki Disease and Coronary Complications
- Type
- article
- Field-Weighted Citation Impact
- 8.03