Evaluation of the Performance of Advanced Large Language Models in Laboratory Medicine Using Residency Examinations
LLMs demonstrated substantial potential for integration into laboratory medicine, particularly in clinical chemistry and immunology. Performance inconsistencies (particularly for high-difficulty questions) and knowledge gaps (notably for transfusion medicine) highlight the necessity for further development-potentially including domain-specific fine-tuning and retrieval-augmented generation integration-and robust expert oversight before clinical application.
Authors
- Warren Wei‐Rhen Lee
- Hee Sue Park (ORCID: https://orcid.org/0000-0002-8378-6066)
- Qute Choi (ORCID: https://orcid.org/0000-0002-8520-3119)
- Kiwook Jung (ORCID: https://orcid.org/0000-0001-8411-7473)
- Hyun Jin Kim (ORCID: https://orcid.org/0000-0003-1725-2573)
- Jun Hyung Lee (ORCID: https://orcid.org/0000-0002-8682-3694)
- Sunghwan Shin (ORCID: https://orcid.org/0000-0003-1038-029X)
Institutions
- Pyeongtaek University (KR)
- Yong In University (KR)
- Chungbuk National University (KR)
- Chungnam National University (KR)
- Inje University Ilsan Paik Hospital (KR)
- Chungbuk National University Hospital (KR)
Publication Details
- Journal
- Annals of Laboratory Medicine
- Published
- 2025-11-13
- DOI
- https://doi.org/10.3343/alm.2025.0200
- Citations
- 1
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.81