Multicenter Evaluation of an Interoperable System for Automated Guideline Adherence Monitoring in ICUs
Authors' conclusion
The guideline adherence monitoring system was successfully applied in multiple hospitals, demonstrating higher accuracy and efficiency compared with human review.
Study context
- Population
- ICU episodes in five university hospitals with different clinical information systems, over 3.5 years; six recommendations from 41 intensive care guidelines
- Participants
- 82,000 ICU episodes
- Exposure
- Automated guideline adherence monitoring vs expert human review
- Outcome
- System's accuracy in identifying guideline applicability and adherence vs manual clinician reviews
Methodological detailscomparison against expert human review
- Comparison against expert human review
Main finding
As reported in the abstract
Accuracy in identifying guideline applicability and adherence
P < 0.001
Observational data: associations, not effects.
Secondary outcomes
| Outcome | System | Human reviewers |
|---|---|---|
| Processing speed | 2000 patient days per second | 2 patient days per minute |
- Processing speed: system exceeded 2000 patient days per second
Real-world adherence rates
- Adherence rates varied substantially across sites and over time, reflecting documentation inconsistencies, evolving clinical knowledge and challenges in maintaining strict compliance
Original publication
Multicenter Evaluation of an Interoperable System for Automated Guideline Adherence Monitoring in ICUs. Crit Care Med. Published 25 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →