Almanac Copilot: Towards Autonomous Electronic Health Record Navigation

TL;DR

Almanac Copilot is an autonomous agent designed to assist clinicians with electronic health record tasks, demonstrating a 74% success rate on a synthetic dataset and showing promise in reducing clinician workload and improving EMR usability.

Contribution

This paper introduces Almanac Copilot, a novel autonomous agent for EMR tasks, showcasing its effectiveness and potential to improve clinician experience and reduce cognitive load.

Findings

74% task success rate on EHR-QA dataset

Mean score of 2.45 over 3 on task completion

Potential to mitigate clinician cognitive load

Abstract

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