Evaluation of generative AI assistance in clinical nephrology: Assessing GPT-4, GPT-4o, Gemini 1.0 Ultra, and PaLM 2 in patient interaction and renal biopsy interpretation
GPT-4o emerged as the most accurate and consistent model across most evaluation categories, while GPT-4 demonstrated superior empathy and balanced performance. PaLM 2 and Gemini 1.0 Ultra showed strengths in specific areas, highlighting the potential for tailored applications of generative AI in nephrology clinical practice.
Authors
- Chia‐Hung Kao (ORCID: https://orcid.org/0000-0002-6368-3676)
- Che‐Yi Chou (ORCID: https://orcid.org/0000-0003-4029-9097)
- Shih‐Yi Lin (ORCID: https://orcid.org/0000-0002-1901-2656)
- Chu‐Lin Chou (ORCID: https://orcid.org/0000-0002-9695-1067)
- Chien-Hua Chiu
- Min‐Kuang Tsai (ORCID: https://orcid.org/0000-0002-2528-3911)
- Ying-Yu Hsu (ORCID: https://orcid.org/0009-0006-9025-8102)
- Ming-Han Hsieh (ORCID: https://orcid.org/0000-0001-9751-6692)
- Yu-Cyuan Hong
- I‐Kuan Wang (ORCID: https://orcid.org/0000-0001-9435-5213)
- Shu-Woei Ju
- Changcheng Jiang
- Huey‐Liang Kuo (ORCID: https://orcid.org/0000-0002-9225-7334)
- Pei-Wen Lee
- Sung-Lin Hsieh
- Yuwei Chen (ORCID: https://orcid.org/0000-0003-0148-3609)
- Kin-Man Law
- I‐Wen Ting
- Heng-Chih Pan
- Pei-Chun Yeh (ORCID: https://orcid.org/0009-0004-7561-8304)
Institutions
- Asia University (TW)
- National Chung Hsing University (TW)
- Chang Gung University (TW)
- China Medical University (TW)
- Kaohsiung Chang Gung Memorial Hospital (TW)
- Keelung Chang Gung Memorial Hospital (TW)
- China Medical University Hospital (TW)
- Taipei Medical University-Shuang Ho Hospital (TW)
- Taipei Medical University (TW)
- National Changhua University of Education (TW)
Publication Details
- Journal
- Digital Health
- Published
- 2025-05-01
- DOI
- https://doi.org/10.1177/20552076251342067
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31