Confidence-linked and uncertainty-based staged framework for phenotype validation using large language models
This framework demonstrates the effective integration of LLMs into clinical workflows while ensuring human oversight, enhancing both accuracy and efficiency.
Authors
- Hokyou Lee (ORCID: https://orcid.org/0000-0002-5034-8422)
- Minsung Cho (ORCID: https://orcid.org/0009-0002-4496-8489)
- Jaewon Khil (ORCID: https://orcid.org/0000-0001-8651-1896)
- Hyeok‐Hee Lee (ORCID: https://orcid.org/0000-0002-2895-6835)
- Seng Chan You (ORCID: https://orcid.org/0000-0002-5052-6399)
- Kyu Sun Yum (ORCID: https://orcid.org/0000-0001-9815-7652)
- Hyeon Chang Kim (ORCID: https://orcid.org/0000-0001-7867-1240)
- Jae Yong Lee (ORCID: https://orcid.org/0000-0002-4967-911X)
- Sumin Lee (ORCID: https://orcid.org/0000-0001-6782-7457)
- Sojung Shin
- Jang-Hyun Baek
- Na Yeon Ahn
Institutions
- Beth Israel Deaconess Medical Center (US)
- Harvard University (US)
- Yonsei University (KR)
- Kangbuk Samsung Hospital (KR)
- Chungbuk National University Hospital (KR)
- Deaconess Hospital (US)
- Sungkyunkwan University (KR)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-06-17
- DOI
- https://doi.org/10.1093/jamia/ocaf099
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- Korea Disease Control and Prevention Agency
- National IT Industry Promotion Agency
- Korea Health Industry Development Institute
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea