Performance of Large Language Models in Analyzing Common Hypertension Scenarios
Among the 3 tested LLMs, GPT-4 demonstrated closer agreement to expert decisions, thereby showing greater potential for supporting hypertension management. Despite their potential, current LLM versions are inferior to expert recommendations. Human-in-the-loop supervision remains essential when deploying LLMs for clinical decision-making.
Authors
- Wisit Cheungpasitporn (ORCID: https://orcid.org/0000-0001-9954-9711)
- Sandra J. Taler (ORCID: https://orcid.org/0000-0003-4149-2278)
- Jing Miao (ORCID: https://orcid.org/0000-0003-0642-9740)
- Peyman Nejat (ORCID: https://orcid.org/0000-0001-9223-7942)
- Jaleh Zand (ORCID: https://orcid.org/0009-0001-9934-385X)
- Vesna D. Garovic (ORCID: https://orcid.org/0000-0001-6891-0578)
- Musab S. Hommos (ORCID: https://orcid.org/0000-0003-2697-4463)
- Ziad Zoghby (ORCID: https://orcid.org/0000-0002-8734-9699)
- Gary L. Schwartz (ORCID: https://orcid.org/0000-0002-3785-6764)
Institutions
- Mayo Clinic (US)
- Mayo Clinic in Arizona (US)
- Mayo Clinic in Florida (US)
Publication Details
- Journal
- Hypertension
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1161/hypertensionaha.125.25492
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65