Documenting a patient visit in the electronic health record (EHR) is essential to healthcare delivery, but also a major contributor to clinician burnout. Artificial intelligence (AI)-enabled ambient documentation, or "AI scribes," can automatically generate draft clinical notes for review after an appointment. While they have been shown to reduce clinician burnout, large-scale studies examining how these technologies impact clinician workflows are lacking.
A new study, co-led by investigators from Mass General Brigham and the University of California, San Francisco, tracked ambient documentation use across five U.S hospitals for more than two years. The researchers found that AI scribes were associated with modest daily reductions of 13 minutes in EHR usage and 16 minutes in documentation time, representing relative decreases of 3% and 10%, respectively. The findings, published in JAMA , also showed a slight increase in productivity, measured as 0.5 additional patient visits per week. According to the study's authors, these new insights should encourage health systems to better investigate how the new technologies are impacting clinician workflows.
"Previous studies link ambient documentation to a significant decrease in burnout , but the underlying drivers of this reduction have been unclear," said senior author Rebecca G. Mishuris, MD, MS, MPH, Chief Health Information Officer at Mass General Brigham. "The modest reductions in documentation time we observed are unlikely to fully account for changes in burnout, underscoring the need to understand how these tools change how clinicians approach care delivery while using them."
These findings are the first published results of the Ambient Clinical Documentation Collaborative (ACDC), a multi-organizational research effort. More than 1,800 clinicians using AI scribes in the present study were compared with 6,770 control clinicians at the same institutions.
The most pronounced improvements in EHR use and documentation patterns were observed among primary care physicians, advanced practice providers, female clinicians, and those who used ambient documentation in at least half of their patient encounters. Clinicians who used AI scribes for more than 50% of visits experienced twice the reduction in total EHR time and three times the reduction in documentation time, yet only 32% of users adopted the technologies that frequently. Revenue increases associated with seeing more patients were statistically significant, but nominal ($167 per month, per clinician adopting an AI scribe). Time spent using the EHR outside of work hours did not significantly differ between groups. Ongoing studies can determine whether these changes result in increased time spent on other activities, and how this may impact clinician burnout.
"Ambient documentation use is expanding rapidly across U.S. health care, making it essential to study how these technologies are impacting clinicians in real time," said lead and corresponding study author Lisa Rotenstein, MD, MBA , an associate professor of medicine at the UCSF School of Medicine, and director of The Center for Physician Experience and Practice Excellence at Brigham and Women's Hospital. "Our study demonstrates the impact of AI scribes in diverse real-world implementations at multiple sites. It also emphasizes the value of helping clinicians become comfortable with the technology so that they are reaping its full benefits via frequent use."
Authorship: In addition to Mishuris and Rotenstein, study co-authors include A Jay Holmgren, Robert Thombley, Aditi Sriram, Reema H. Dbouk, Melissa Jost, Debbie Aizenberg, Scott MacDonald, Naga Kanaparthy, Brian Williams, Allen Hsiao, Lee Schwamm, Sara Murray, Maria Byron, Hossein Soleimani, Jacqueline G. You, Amanda J. Centi, Christine Iannaccone, Michelle Frits, Adam B. Landman, Karandeep Singh, Ming Tai-Seale, Jie Cao, Katharine Lawrence, Devin Mann, Christopher Holland, Bryan Blanchette, Jesse Ehrenfeld, Edward R. Melnick, David W. Bates, and Julia Adler-Milstein.
Disclosures: Rotenstein reported receiving grants and travel support from FeelBetter Inc., serving on an advisory board for Eko Health, and on an AI advisory board for Augmedix Inc. A full list of disclosures for other co-authors can be found in the paper.
Funding: This research was supported by a grant from the Advancing a Healthier Wisconsin Endowment, a gift from Kathy Hao to establish the Impact Monitoring Platform for AI in Clinical Care at UCSF, and an AHRQ grant R01HS029470.
Paper cited: Rotenstein L, et al. "Changes in Clinician Time Expenditure and Visit Quantity With Adoption of Artificial Intelligence-Powered Scribes: A Multisite Study." JAMA DOI: 10.1001/jama.2026.2253
