Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Impact of Ambient Artificial Intelligence Scribes on Emergency Department Documentation Burden: A Retrospective Cohort Study
ABSTRACT
Background:
Clinician burnout has reached crisis levels in emergency medicine, with clinical documentation burden identified as a central contributing factor. Ambient artificial intelligence (AI) scribes offer a promising approach to reduce documentation burden, but scant quantitative evidence exists on objective time savings in the emergency department (ED) setting.
Objective:
To evaluate the effect of ambient AI scribes on on-shift documentation time in a busy ED during a staged rollout, accounting for physician- and patient-level factors.
Methods:
We conducted a 6-month retrospective cohort study at a tertiary academic ED from February to August 2025. The analytic cohort included 7,640 encounters managed by 87 attending physicians across four ED care settings. We limited our analysis to encounters managed individually by a single physician and excluded cases with human scribes. The primary outcome was on-shift documentation time derived from electronic health record audit logs. We used mixed-effect linear models with physician random intercepts to adjust for patient and encounter characteristics.
Results:
Ambient AI scribes reduced on-shift documentation time by 68.2 seconds per encounter (95% CI [82.9, 53.5]; P<.001). High-utilizing physicians (those with usage rates ≥9.9%, the cohort mean) saved 73.9 seconds per encounter compared to 27.5 seconds for low/moderate utilizers (difference: 46.4 seconds, P=.013). Note character count decreased by 958 characters (95% CI [1757, 158]; P=.019); after-shift documentation time increased modestly by 12.3 seconds (95% CI [1.3, 23.3]; P=.029).
Conclusions:
In this single-center study, ambient AI scribes were associated with a statistically significant reduction in on-shift documentation time, translating to approximately 23 minutes saved over a typical 8-hour shift with 20 patient encounters. These findings support their clinical utility in mitigating documentation burden; however, the effect varies based on physician, patient, and workflow factors.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.