Fact · Dictation for work and study
94.7percent of reviewed notes free from significant errors
In a 2024 pilot at UC Davis, 94.7 percent of the 356 AI-generated clinical notes that physicians reviewed were free from significant errors.
Checked against its source on October 16, 2026
In the source's own words
“AI-generated clinical notes were generally of high quality, with 94.7% (337/356) free from significant errors.”
Quality of Clinical Notes Created by Ambient Listening Generative AI: Pragmatic Prospective Pilot Study, Taylor SL et al., JMIR Medical Informatics, 2026, Results.
Open the original (DOI 10.2196/86474)- What it measures
- Physicians reviewed 356 of the 7,545 clinic notes created with an ambient listening scribe during a two-month pilot in July and August 2024.
- What it does not show
- Physicians reviewed only 4.7 percent of the notes they had created with the tool. A high share free of significant errors does not show safety by itself; the next facts give the serious-risk share.
Source
Cited on
- AI Medical Scribes and Ambient Clinical DocumentationGuide
- AI Voice Notes: From Rambling to Summaries and To-DosGuide
- Are AI summaries of voice recordings accurate?Question
- How accurate are AI medical scribes?Question
- Should doctors use an AI scribe or dictation?Question
- What is an ambient AI scribe?Question