No change in primary outcome
Displaying AI deterioration-risk scores on a cardiology ward did not improve patient outcomes across 10,422 admissions.
A cluster-randomized trial at UVA (Scientific Reports, Feb 2026) showed CoMET risk trajectories on screens for intervention beds; event-free hours did not differ, and clinicians moved 11% of patients into or out of display beds, undermining the design.
Sources
- primaryScientific Reports: A randomized controlled trial of AI-based analytics for clinical deteriorationnature.com
History
- Added.
Cite this entry
Permalink https://becauseofai.org/entry/uva-comet-deterioration-null
“Displaying AI deterioration-risk scores on a cardiology ward did not improve patient outcomes across 10,422 admissions.” Because of AI, updated Oct 22, 2026. https://becauseofai.org/entry/uva-comet-deterioration-null@misc{becauseofai_uva_comet_deterioration_null,
title = {Displaying AI deterioration-risk scores on a cardiology ward did not improve patient outcomes across 10,422 admissions.},
howpublished = {\url{https://becauseofai.org/entry/uva-comet-deterioration-null}},
note = {Because of AI registry, updated Oct 22, 2026},
year = {2026}
}