Multicenter Evaluation of an Interoperable System for Automated Guideline Adherence Monitoring in ICUs

Objective: To develop, apply, and validate a system for evaluating critical care guideline adherence, and to identify factors influencing real-world adherence across hospitals. Design: Retrospective, multicenter observational study evaluating guideline adherence over 3.5 years and comparing automated adherence monitoring against expert human review. Setting: Five university hospitals with different clinical information systems and data infrastructures. Patients: A total of 82,000 intensive care episodes (2.2 million patient days). Six representative recommendations were selected from 41 intensive care guidelines and translated into a standardized digital format. Expert review encompassed more than 18,000 patient days. Interventions: An automated system that applies digitally encoded guideline recommendations to standardized patient data extracted from hospital information systems. Measurements and Main Results: The system determined, for each patient and recommendation, whether the recommendation applied (applicability) and whether treatment followed it (adherence). The primary outcome was the system’s accuracy in identifying guideline applicability and adherence compared with manual clinician reviews. The secondary outcome was an analysis of how adherence to these recommendations varied and which factors influenced their real-world implementation. The system achieved 97.0% accuracy in identifying guideline applicability and adherence, significantly outperforming human reviewers (86.6% accuracy, p < 0.001; McNemar’s test). The processing speed of the system exceeded 2000 patient days per second, compared with manual review at 2 patient days per minute. Adherence rates varied substantially across participating sites and over time, reflecting documentation inconsistencies, evolving clinical knowledge, and challenges in maintaining strict compliance. Conclusions: The guideline adherence monitoring system was successfully applied in multiple hospitals, demonstrating higher accuracy and efficiency compared with human review. Limitations of the system included dependence on consistent and structured documentation, as inconsistencies significantly complicate adherence monitoring. As the system is designed to support any guideline in the digital format used here, it provides a scalable solution for automated quality management in critical care.