| Title: |
Using secure artificial intelligence agents integrated within the electronic medical record for the evaluation of blood culture appropriateness—Northern California, 2025 |
| Authors: |
Rodriguez-Nava, Guillermo; Keyes, Timothy; Ambers, Nerissa; Miranti, Eugenia; Viana-Cardenas, Erika Paola; Tariq, Wajeeha; Sampson, Mindy Marie; Salinas, Jorge Luis |
| Source: |
Infection Control & Hospital Epidemiology ; volume 47, issue 2, page 206-209 ; ISSN 0899-823X 1559-6834 |
| Publisher Information: |
Cambridge University Press (CUP) |
| Publication Year: |
2025 |
| Description: |
We evaluated large language model (LLM)-based agents integrated with the electronic medical record to assess blood culture appropriateness. While sensitivity was high, specificity remained low. Performance was shaped by prompt phrasing, sycophantic behavior, and semantic triggers, reflecting both the potential and limitations of LLMs in real-world clinical decision support. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| DOI: |
10.1017/ice.2025.10349 |
| Availability: |
https://doi.org/10.1017/ice.2025.10349; https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0899823X25103498 |
| Rights: |
https://creativecommons.org/licenses/by/4.0/ |
| Accession Number: |
edsbas.CA292BCD |
| Database: |
BASE |