Using secure artificial intelligence agents integrated within the electronic medical record for the evaluation of blood culture appropriateness-Northern California, 2025.

ABSTRACT: 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.

SUBMITTER: Rodriguez-Nava G 

PROVIDER: S-EPMC12926330 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature