PharmacyGPT: exploration of artificial intelligence for medication management in the intensive care unit
Iterative prompt optimization shows promise as a rapid means to improve LLM functionality to specific tasks, even in highly domain specific areas like medication management in the ICU. Such domain specific engineering may serve as a strategy to develop LLMs as viable CDS tools.
Authors
- Brian Murray (ORCID: https://orcid.org/0000-0001-6660-9749)
- Andrea Sikora (ORCID: https://orcid.org/0000-0003-2020-0571)
- Erin F. Barreto (ORCID: https://orcid.org/0000-0002-0996-1487)
- Zhengliang Liu (ORCID: https://orcid.org/0000-0003-0898-6444)
- Zihao Wu (ORCID: https://orcid.org/0000-0001-7483-6570)
- Xiang Li (ORCID: https://orcid.org/0000-0002-3423-5065)
- Sheng Li (ORCID: https://orcid.org/0000-0003-1205-8632)
- Wei Liu (ORCID: https://orcid.org/0000-0002-3865-8145)
- Tianming Liu
- Shaochen Xu (ORCID: https://orcid.org/0009-0008-0802-9218)
Institutions
- University of North Carolina at Chapel Hill (US)
- Harvard University (US)
- University of Georgia (US)
- Mayo Clinic in Arizona (US)
- Mayo Clinic Hospital (US)
- University of Virginia (US)
- University of Colorado Denver (US)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2025-10-28
- DOI
- https://doi.org/10.1186/s12911-025-03230-1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00