Improving Emergency Department Patient Flow Through Near Real-Time Analytics

IMPROVING EMERGENCY DEPARTMENT PATIENT FLOW THROUGH NEARREAL-TIME ANALYTICSbySHANSHAN QIUAugust 2014 Advisor: Dr. Ratna Babu ChinnamCo-Advisor: Dr. Alper MuratMajor: Industrial EngineeringDegree: Doctor of Philosophy This dissertation research investigates opportunities for developing effective decisionsupport models that exploit near real-time (NRT) information to enhance the “operationalintelligence” within hospital Emergency Departments (ED). Approaching from a systemsengineering perspective, the study proposes a novel decision support framework for streamliningED patient flow that employs machine learning, statistical and operations research methods tofacilitate its operationalization. ED crowding has become the subject of significant public and academic attention, and itis known to cause a number of adverse outcomes to the patients, ED staff as well as hospitalrevenues. Despite many efforts to investigate the causes, consequences and interventions for EDovercrowding in the past two decades, scientific knowledge remains limited in regards tostrategies and pragmatic approaches that actually improve patient flow in EDs. Motivated by the gaps in research, we develop a near real-time triage decision supportsystem to reduce ED boarding and improve ED patient flow. The proposed system is a novelvariant of a newsvendor modeling framework that integrates patient admission probability