Because of AI, 284 UCLA clinicians reported modestly lower task load and burnout from a chart summarizer — while saving no time and mostly not recommending it.
Lower task load, zero time savedAchievedFeb–May 2026Published
A pragmatic RCT (Feb–May 2026) of Epic's generative chart summarization tool among 284 ambulatory clinicians found modestly reduced physician task load and lower burnout, no time savings, declining engagement, and a net promoter score of −22.
Preprint (medRxiv, Aug 2026), self-reported outcomes, three-month window, one health system.
- Compared with
- Tool access vs usual pre-charting workflow, 1:1 randomization for 90 days
- Effect
- Modest task-load reduction (primary endpoint met)
- Reach
- 284 clinicians, UCLA Health
- Domain
- Work · Generative
- Conflicts
- Epic's tool evaluated by its customer; no vendor funding reported — verify.
Sources
- primarymedRxiv: A pragmatic randomized trial of an EHR-integrated generative AI chart summarization tool (medrxiv.org)
- primaryClinicalTrials.gov NCT07438743 (clinicaltrials.gov)
Editor's notes
Included as the honest floor for generative AI in clinical workflow.
Related
History
- Added.
Cite this entry
Permalink https://becauseofai.org/entry/ucla-chart-summarizer-rct
“Because of AI, 284 UCLA clinicians reported modestly lower task load and burnout from a chart summarizer — while saving no time and mostly not recommending it.” Because of AI, updated Oct 22, 2026. https://becauseofai.org/entry/ucla-chart-summarizer-rct