Comparative evaluation of six large language models in transfusion medicine: Addressing language and domain‐specific challenges
GPT-4 and GPT-4o exhibited robust and reliable performance across a range of transfusion medicine topics. Nonetheless, inter-model and inter-language variability highlights the need for targeted fine-tuning, particularly in the context of local regulatory and ethical frameworks, to support safe and context-appropriate implementation in clinical practice.
Authors
- Jong Kwon Lee (ORCID: https://orcid.org/0000-0002-6230-1242)
- Duck Cho (ORCID: https://orcid.org/0000-0001-6861-3282)
- Sholhui Park (ORCID: https://orcid.org/0000-0002-6467-427X)
- Sooin Choi (ORCID: https://orcid.org/0000-0003-4746-4809)
- Jaejoon Lee
- Sang‐Hyun Hwang (ORCID: https://orcid.org/0000-0003-3201-5728)
Institutions
- Ulsan College (KR)
- Ewha Womans University (KR)
- Soonchunhyang University (KR)
- Asan Medical Center (KR)
- Samsung Medical Center (KR)
- University of Ulsan (KR)
- Bucheon University (KR)
- Sungkyunkwan University (KR)
Publication Details
- Journal
- Vox Sanguinis
- Published
- 2025-05-23
- DOI
- https://doi.org/10.1111/vox.70050
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31