Large Language Models’ Clinical Decision-Making on When to Perform a Kidney Biopsy: Comparative Study
The outputs of LLMs demonstrated a modest ability to replicate human clinical decision-making in this study; however, performance varied widely between LLM models. Questions with more uniform human responses produced LLM outputs with higher alignment, whereas questions with lower human consensus showed poorer output alignment. This may limit the practical use of LLMs in real-world clinical practice.
Authors
- Michael Quinn
- Ciarán O’Neill (ORCID: https://orcid.org/0000-0001-7668-3934)
- Michael Toal (ORCID: https://orcid.org/0000-0002-1690-9206)
- Alexander P. Maxwell (ORCID: https://orcid.org/0000-0002-6110-7253)
- Christopher Hill (ORCID: https://orcid.org/0000-0002-1947-8384)
Institutions
- University of Ulster (GB)
- Belfast City Hospital (GB)
- Royal Victoria Hospital (GB)
- Victoria Hospital (GB)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-06-02
- DOI
- https://doi.org/10.2196/73603
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31