Let's Have a Chat: How Well Does an Artificial Intelligence Chatbot Answer Clinical Infectious Diseases Pharmacotherapy Questions?
Fewer than 50% of GPT-3.5 responses were considered useful by SMEs. Responses were mostly considered correct and safe but were often incomplete, suggesting that GPT-3.5 responses may not replace an ID pharmacist's responses.
Authors
- Elizabeth W. Covington (ORCID: https://orcid.org/0000-0003-0082-6008)
- Conan MacDougall (ORCID: https://orcid.org/0000-0002-8690-5796)
- Jason C Gallagher (ORCID: https://orcid.org/0000-0001-8532-0887)
- Robert W. Seabury (ORCID: https://orcid.org/0000-0002-0365-6713)
- Rachel S. Britt (ORCID: https://orcid.org/0000-0003-2954-6800)
- Katie A Parsels
- Wesley D. Kufel (ORCID: https://orcid.org/0000-0001-7703-096X)
- Elias B. Chahine (ORCID: https://orcid.org/0000-0003-1775-9497)
- Jeffrey M. Steele (ORCID: https://orcid.org/0000-0003-3138-3609)
- Kathleen D Hanrahan
Institutions
- Binghamton University (US)
- State University of New York (US)
- University of California, San Francisco (US)
- SUNY Upstate Medical University (US)
- Upstate University Hospital (US)
- The University of Texas Medical Branch at Galveston (US)
- Palm Beach Atlantic University (US)
- Auburn University (US)
- Temple University (US)
Publication Details
- Journal
- Open Forum Infectious Diseases
- Published
- 2024-10-25
- DOI
- https://doi.org/10.1093/ofid/ofae641
- Citations
- 11
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.32