Physician Edits to AI-Drafted Patient Messages and Their Impact on Clinical Workload

AI systems capable of drafting replies to patient messages are widely implemented within electronic health records (EHRs) to reduce physician workload. Prior studies have shown limited time savings, and little is known about what content physicians edit and how these edits affect response time.

In this quality improvement study at UC San Diego Health (April 2024-August 2025), we analyzed physician edits to AI-generated draft responses integrated in the EHR. A 15-category taxonomy of edits was developed using a large language model with iterative expert review. Response time was used as a proxy for clinical workload and examined in relation to edit categories with mixed-effects regression, adjusting for message complexity and temporal factors.

We identified 14,350 AI-assisted responses across 1131 physicians. The most frequent edits involved scheduling appointments and providing lifestyle advice. Most edits were moderate in extent, altering message meaning without changing care plans. All 15 edit categories were associated with longer response times; the largest marginal increases were observed for interpreting radiology results (+70.1%), clarifying or ruling out diagnosis (+63.9%), and interpreting laboratory results (+60.8%). The greatest cumulative editing burden was associated with scheduling, lifestyle advice, and referral coordination.

Response times varied by both the frequency and complexity of edit categories. This study provides empirical evidence of physicians' roles as humans-in-the-loop within a large-scale implementation of generative AI and offers a framework for targeting prompt engineering and AI optimization efforts toward the edit categories with the greatest impact on physician time and effort. (Funded by the UC San Diego Rady School of Management and others.).