What You Should Know
- The Scale of the Study: In the first major multi-site, multi-vendor study of its kind published in JAMA, researchers analyzed data from 8,581 ambulatory clinicians (including 1,809 AI scribe adopters) across five major academic health systems: Mass General Brigham, Emory Healthcare, UCSF, Yale New Haven Health, and UC Davis. The systems utilized tools from Ambience, Nuance DAX Copilot, and Abridge.
- The Baseline ROI: Across the board, AI scribe adoption was associated with 13.4 fewer minutes of total EHR time and 16.0 fewer minutes of documentation time per 8 scheduled patient hours. It also yielded a modest productivity bump of 0.49 additional weekly visits.
The AI Scribe Reality Check: Why 16 Minutes of Saved Time is Just the Beginning
The new study, co-led by investigators from Mass General Brigham and UCSF Health, tracked ambient documentation use across five U.S hospitals for more than two years. Across over 1,800 adopters, the technology was associated with a reduction of 16 minutes in documentation time and 13.4 minutes in total EHR time per 8-hour shift. The findings are a necessary, sobering reality check for the industry. AI scribes are absolutely working, but they are not magic.
As Dr. Rebecca G. Mishuris, Chief Health Information Officer at Mass General Brigham and senior author of the study, aptly noted, these reductions are “modest” and are unlikely to fully account for the massive drops in physician burnout often associated with these tools.
Other key findings of the study include:
No Change in “Pajama Time”: Interestingly, the study found that time spent on the EHR outside of scheduled working hours (often referred to as “pajama time”) did not change significantly with the adoption of AI scribes.
The “Power User” Gap: The benefits were highly dependent on utilization. Clinicians who used the AI scribes for 50% or more of their visits saw massive gains, spending 21.3 fewer minutes in total EHR time and 27.3 fewer minutes on documentation. However, only about 32% of adopters actually used the tool that frequently.
Demographic Variations: The reductions in documentation burden were greatest for primary care specialists, advanced practice clinicians, and female clinicians.
The Financial Impact: While the 1.7% increase in visit volume is notable, the associated marginal Evaluation and Management (E/M) revenue generated was minimal, averaging just $167.37 per clinician, per month.
A Reallocation of Time
As the study authors suggest, clinicians may be reallocating those 16 saved minutes back into other critical patient care activities—like reviewing prior documentation, answering patient messages in their inbox, or simply spending more face-to-face time with the patient in the room.
“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.”
