A multisite study across five academic medical centres (Mass General Brigham, Emory, UCSF, Yale New Haven, UC Davis), published in JAMA, found AI ambient scribes saved about 16 minutes of documentation time per 8 hours of patient care, with 13.4 fewer minutes of total EHR time. The effect concentrated in heavy users: clinicians who used the scribe on at least 50% of their visits saved 27.3 minutes of documentation and 21.3 minutes of total EHR time per 8-hour day.

A separate quality-improvement study of 263 ambulatory clinicians across six health systems, reported in JAMA Network Open, found burnout dropped from 51.9% to 38.8% after 30 days of scribe use. Cognitive task load and time spent on after-hours documentation also fell.

The effect sizes reported are modest in absolute terms. The JAMA authors describe "modest time savings" as the headline finding. STAT's coverage of the study notes that adoption was inconsistent across the included sites, which means the population average understates the time savings reported by clinicians who used the scribe on a majority of visits.