ArticleCJEM2026
Human vs. artificial intelligence in medical charting: a comparative study in the simulated emergency medicine context.
Article in CJEM, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
objectivesThe increasing administrative burden associated with electronic health records has contributed to reduced efficiency and rising burnout among physicians, particularly in high-volume environments like Emergency Departments (EDs). Ambient artificial intelligence (AI) scribes offer a potential solution by generating clinical documentation in real-time using ambient listening. This study aimed to evaluate the efficiency of an AI scribe compared to traditional voice dictation in simulated ED encounters, assess user satisfaction, and analyze the types and extent of edits required in AI-generated notes.
methodsWe conducted a mixed methods simulated study using standardized patient encounters with Emergency Medicine physicians and residents at the Ottawa Hospital. Participants completed three scripted clinical scenarios. Each interaction was recorded using an AI scribe (Mutuo) and participants subsequently documented the encounter using Dragon voice dictation. The AI-generated note was then edited by the participant, with time tracked for both dictation and editing. Quantitative analysis included a paired t-test for time comparison and Wilcoxon rank sum test for note preference. Qualitative feedback was collected via structured surveys and open-ended questions.
resultsSixteen participants completed the study, with 81% being attending physicians. Mean dictation time was 2:05 min compared to 1:15 min for AI note editing, representing a 39% time savings (p < 0.0001). Of 240 total note sections, 69% required no edits; edits were most common in the "History" and "Plan" sections. Most edits (76%) were minor, involving only a few words or a single sentence. Sixty-three percent of participants preferred the AI-generated note (p < .001).
conclusionIn a simulated ED setting, ambient AI scribe technology significantly reduced documentation time with minimal required editing. These findings support the potential clinical utility of AI scribes in improving physician efficiency, warranting further evaluation in real-world ED environments.
Indexed as
Identifiers
41917375What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.