Almanac Copilot: Towards Autonomous Electronic Health Record Navigation

• DOI: 10.48550/arxiv.2405.07896
• Publication Date: 2024-04-30
• Authors: Cyril Zakka; Joseph Cho; Gracia Fahed; Rohan Shad; Michael Moor; Robyn Fong; Dhamanpreet Kaur; Vishnu Ravi; Oliver Aalami; Roxana Daneshjou; Akshay Chaudhari; William Hiesinger
• Keywords: Electronic health record

Clinicians spend large amounts of time on clinical documentation, and inefficiencies impact quality care increase clinician burnout. Despite the promise electronic medical records (EMR), transition from paper-based has been negatively associated with wellness, in part due to poor user experience, increased burden alert fatigue. In this study, we present Almanac Copilot, an autonomous agent capable assisting clinicians EMR-specific tasks such as information retrieval order placement. On EHR-QA, a synthetic evaluation dataset 300 common EHR queries based real patient data, Copilot obtains successful task completion rate 74% (n = 221 tasks) mean score 2.45 over 3 (95% CI:2.34-2.56). By automating routine streamlining documentation process, our findings highlight significant potential agents mitigate cognitive load imposed by current EMR systems.