The Kaiser Permanente Northern California Advance Alert Monitor Program: An Automated Early Warning System for Adults...

Area of Science:

• Healthcare Informatics
• Clinical Decision Support Systems
• Predictive Analytics in Medicine

Background:

• In-hospital patient deterioration is linked to increased adverse outcomes.
• Kaiser Permanente Northern California (KPNC) developed the Advance Alert Monitor (AAM) in 2013.
• AAM aims to detect and intervene early in patient decline, providing a 12-hour warning.

Purpose of the Study:

• To implement and evaluate a predictive analytics program for early detection of in-hospital patient deterioration.
• To improve patient outcomes by enabling timely, goals-concordant interventions.

Main Methods:

• The AAM system analyzes electronic health record (EHR) data 24/7 across 21 KPNC hospitals.
• High-risk patient alerts are managed by virtual quality nurse consultants (VQNCs).
• VQNCs coordinate with rapid response teams (RRTs) for bedside assessments and interdisciplinary care planning.

Main Results:

• AAM implementation in 19 hospitals showed statistically significant reductions in mortality (9.8% vs. 14.4%).
• The program also decreased hospital and ICU lengths of stay.
• Estimated over 500 deaths were prevented annually due to AAM.

Conclusions:

• Predictive modeling in EHRs, like AAM, enhances patient care and outcomes.
• AAM demonstrates a successful model for clinical decision support and inpatient population management.
• The program standardizes monitoring, rescue protocols, and goal-concordant care, leveraging AI/ML potential.