Ambient artificial intelligence effectively reduced work exhaustion among healthcare providers
1. Afshar and colleagues evaluated an artificial intelligence (AI) scribe’s ability to produce clinical documentation and alleviate work exhaustion.
2. Ambient AI use had a significant reduction in work exhaustion but did not significantly improve professional fulfillment.
Evidence Rating Level: 1 (Excellent)
Study Rundown: Electronic health record (EHR) documentation is a significant contributor to healthcare provider burnout. Ambient AI scribes can passively capture clinical conversations and draft visit notes in real time, but their evidence for improving provider wellness has been limited. Afshar and colleagues conducted a randomized controlled trial to assess whether AI can improve professional fulfillment and lower work exhaustion. A cohort of 66 healthcare providers was recruited and randomly assigned in a 1:1:1 ratio into three 6-week waves of a 24-week schedule. Providers in the experimental group would use AI scribe to generate clinical notes as opposed to their usual workflow. The study found that ambient AI use had a non-significant increase of 0.14 points in professional fulfillment (95% confidence interval (CI), 0.004 to 0.28, p = 0.04) and a significant decrease of 0.44 points in work exhaustion (95% CI, -0.62 to -0.25, p < 0.001). Additionally, the AI-generated notes displayed good thoroughness and accuracy. This study demonstrated that ambient AI scribes may reduce the documentation burden and work exhaustion, but have a limited impact on positive effects, such as professional fulfillment.
Click here to read the study in NEJM AI
Relevant Reading: Use of Ambient AI Scribes to Reduce Administrative Burden and Professional Burnout
In-Depth [randomized controlled trial]: A cohort of 66 healthcare providers was randomly assigned in a 1:1:1 ratio into three 6-week waves of a 24-week schedule. Stratified permuted-block randomization balanced specialty type, and each wave transitioned from practice-as-usual to the ambient AI intervention at 6-week intervals. The two coprimary outcomes were professional fulfillment (six-item subscale, scores from 6 to 30; higher = better) and work exhaustion (10-item composite, scores from 10 to 50; higher = worse). Secondary measures included task load, impact of work on personal relationships, and perceived efficiency. A random sample of AI-generated notes was assessed for documentation quality. Transcripts were used as reference documents, and the notes’ accuracy, thoroughness, and usefulness were assessed on five-point Likert scales. In terms of the primary outcomes, ambient AI use had a non-significant increase of 0.14 points in professional fulfillment (95% confidence interval (CI), 0.004 to 0.28, p = 0.04) and a significant decrease of 0.44 points in work exhaustion (95% CI, -0.62 to -0.25, p < 0.001). 7966 randomly sampled notes underwent quality assessment. They had an accuracy score of 4.44 (standard deviation (SD) 0.93), a thoroughness score of 4.57 (SD 0.68), and a usefulness score of 4.83 (SD 0.51). Additionally, AI use reduced the week-averaged time spent on notes by 0.36 hours (95% CI, -0.55 to -0.17). AI use was also associated with reduced task load, a decrease in the negative impact of work on personal relationships, and improved perceived efficiency. Overall, this study provided more rigorous evidence that ambient AI scribes may reduce healthcare practitioner work exhaustion without compromising documentation quality.
Image: PD
©2026 2 Minute Medicine, Inc. All rights reserved. No works may be reproduced without expressed written consent from 2 Minute Medicine, Inc. Inquire about licensing here. No article should be construed as medical advice and is not intended as such by the authors or by 2 Minute Medicine, Inc.
