Ambient Artificial Intelligence Scribes in the Emergency Department: A Scoping Review of Current Evidence.

BACKGROUND

Burnout affects nearly half of physicians in the United States, with emergency physicians (EPs) at particularly high risk. Documentation burden contributes to burnout. Artificial intelligence (AI) ambient scribes have emerged as a potential strategy to reduce documentation workload. While benefits have been reported in outpatient and inpatient settings, impact in the emergency department (ED) remains poorly characterized.

OBJECTIVE

This scoping review aimed to identify reports of ambient AI scribe use in the ED, assess effects on documentation time, and evaluate implementation challenges and physician workload.

METHODS

A scoping review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR). Cochrane Library, PubMed, Embase, Web of Science, and MEDLINE Complete were searched. Data was retrieved on August 31, 2025. Two reviewers independently screened studies, with disagreements resolved by a third reviewer.

RESULTS

Of 521 nonduplicate records screened, six studies met inclusion criteria, with EP sample sizes ranging from 6 to 24. Outcomes included improved cognitive workload, shorter time to first note, and increased patient throughput. One study reported longer charting time with AI scribes compared to human scribes. Reported challenges included fragmented ED workflows, environmental noise, note accuracy, electronic health record integration, and clinician distrust. Despite mixed documentation time effects, several studies reported improvements in perceived workload and provider wellness.

CONCLUSIONS

Evidence on ambient AI scribes in the ED remains limited. Early findings suggest potential benefits in workload and throughput despite technical and workflow barriers. Further studies are needed.