Using secure artificial intelligence agents integrated within the electronic medical record for the evaluation of blood culture appropriateness—Northern California, 2025
Year: 2025
Type: article
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.
Institutions: Stanford Medicine, Stanford University, Stanford Health Care
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $3,550
OpenAlex ID: W4416133526