Extracting Clinical Guideline Information Using Two Large Language Models: Evaluation Study
These findings suggest that using 2 LLMs can effectively streamline PGx guideline integration into clinical decision support systems while maintaining high performance and minimal cost. Although selective manual review remains necessary, this approach offers a practical and scalable solution for PGx guideline classification in clinical workflows.
Authors
- Hsing-Yu Hsu (ORCID: https://orcid.org/0000-0003-4424-9476)
- Shih‐Sheng Chang (ORCID: https://orcid.org/0000-0002-1664-4818)
- Wen−Lian Hsu (ORCID: https://orcid.org/0000-0001-6358-999X)
- Li Wei Chen (ORCID: https://orcid.org/0000-0003-2878-8613)
- Yow‐Wen Hsieh (ORCID: https://orcid.org/0000-0002-0523-3482)
Institutions
- National Taiwan University (TW)
- China Medical University (TW)
- China Medical University Hospital (TW)
- National Yang Ming Chiao Tung University (TW)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-06-16
- DOI
- https://doi.org/10.2196/73486
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00