Transforming Emergency Care: The Impact of Real-Time and Predictive Analytics on ED Operations - ACHSM Asia-Pacific Health Leadership Congress in Darwin 2025

Abstract

Emergency department (ED) overcrowding is a persistent global issue driven by growing patient volumes, limited hospital bed availability, and inefficient resource allocation. At Sir Charles Gairdner Hospital (SCGH), a 600-beds quaternary centre treating over 75,000 high-acuity patients annually, these pressures have been compounded by reduced access to transitional care. In response, SCGH developed a real-time and predictive analytics system to optimise patient flow and improve operational efficiency.

This study presents the ED BRAG Capacity Escalation System, a data-driven solution integrating real-time monitoring and artificial intelligence (AI) to enhance clinical decision-making. The model is built on three core metrics i.e. presentation numbers, admitted patient count, and waiting room occupancy, used to generate a BRAG (Black-Red-Amber-Green) status to objectively assess ED capacity. By utilising Microsoft Azure AI services, the system forecasts ED trends up to 10 hours in advance and processes over 40 supplementary risk indicators, such as ambulance ramping and mental health presentations.

Post-implementation data indicate notable improvements in performance, including more efficient ambulance transfers, timely triage, and reduced departure delays compared to other tertiary hospitals. These results underscore the transformative potential of real-time and predictive analytics in enhancing emergency care [6]. Future research should explore broader deployment to assess adaptability and long-term impact.