Journal article
A head-to-head comparison of the accuracy of commercially available large language models for infection prevention and control inquiries, 2024
Infection control and hospital epidemiology, Vol.46(3), pp.309-311
03/2025
DOI: 10.1017/ice.2024.205
PMCID: PMC11883648
PMID: 39664019
Appears in UI Libraries Support Open Access
Abstract
We investigated the accuracy and completeness of four large language model (LLM) artificial intelligence tools. Most LLMs provided acceptable answers to commonly asked infection prevention questions (accuracy 98.9%, completeness 94.6%). The use of LLMs to supplement infection prevention consults should be further explored.
Details
- Title: Subtitle
- A head-to-head comparison of the accuracy of commercially available large language models for infection prevention and control inquiries, 2024
- Creators
- Oluchi J. Abosi - University of IowaTakaaki Kobayashi - University of IowaNatalie Ross - University of Iowa Health CareAlexandra Trannel - University of IowaGuillermo Rodriguez Nava - Stanford UniversityJorge L. Salinas - Stanford UniversityKaren Brust - University of Iowa, Internal Medicine
- Resource Type
- Journal article
- Publication Details
- Infection control and hospital epidemiology, Vol.46(3), pp.309-311
- DOI
- 10.1017/ice.2024.205
- PMID
- 39664019
- PMCID
- PMC11883648
- NLM abbreviation
- Infect Control Hosp Epidemiol
- ISSN
- 0899-823X
- eISSN
- 1559-6834
- Publisher
- Cambridge University Press
- Number of pages
- 3
- Language
- English
- Electronic publication date
- 12/12/2024
- Date published
- 03/2025
- Academic Unit
- Infectious Diseases; Internal Medicine
- Record Identifier
- 9984769792102771
Metrics
25 Record Views