Leveraging Individualized Electronic Health Record Learner Analytics to Improve Resident Inbasket Management

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Abstract Background Electronic health record (EHR) inbasket management is a large contributor to burnout among residents. Data-driven, personalized approaches may improve performance and reduce burnout; however, there are few published studies with objective resident outcomes. Objective To evaluate how inbasket EHR metrics change longitudinally among residents stratified by baseline inbasket performance after spaced, analytics-informed coaching. Design Using a stratified longitudinal analysis of EHR metrics along with pre- and post-intervention surveys, we conducted an evaluation of our inbasket coaching curriculum. Participants Postgraduate year (PGY)-2 and PGY-3 internal medicine residents and continuity clinic attendings at a single, large Mid-Atlantic academic center. Interventions Our redesigned curriculum integrated individualized EHR resident analytic reports summarizing efficiency and practice-based quality metrics into structured, one-on-one feedback sessions using the Relationship, Reaction, Content, and Coaching (R2C2) model. Main Measures Primary outcomes included measured change in “time in inbasket” and “turnaround time” across two training periods. Secondary outcomes included resident-reported confidence in managing inbasket tasks, perceived efficiency, and inbasket-related burnout. We also evaluated acceptability and perceived usefulness of the curriculum among residents and faculty. Key Results Residents significantly reduced their turnaround time for patient calls by 2.2 days ( p < 0.001). The mean time spent in patient calls significantly decreased (0.99 ± 0.53 to 0.74 ± 0.38 min/day, p = 0.03). Resident perceptions of inbasket-related burnout did not significantly change ( p = 0.09). Neither perceived inbasket confidence ( p = 0.18) nor efficiency ( p = 0.56) improved after the intervention. Most faculty (6/7) felt EHR analytics data were at least moderately useful in helping coach residents and improved the quality of semiannual feedback. Conclusions Integrating individualized EHR learning analytics into longitudinal coaching improves objective efficiency metrics and improves feedback quality. This model offers a structured approach to supervising inbasket management and promoting competency-based EHR education.