Track: Doctoral Dissertation Competition

Abstract

Health systems are faced with significant challenges during and after natural or human-caused disasters. Surge planning is a critical component of every healthcare facility’s emergency plan and response system. The process of managing and allocating scarce resources by tackling the vulnerability inherent to patients means that defining improvement priorities is one of the main challenges healthcare systems face when responding to a medical surge event (e.g., influenza, COVID-19). The consequences of these challenges include increased patient mortality, ambulance diversion, long wait times, and unavailability of beds. Although previous efforts in hospital operations management have been modestly successful in applying operations research techniques to analyze and optimize ED operations during a standard operating capacity and, literature provides a vast number of resources on surge response planning for hospital administrators, most of the planning guidelines are not suitable for the current pandemic scale. This project aims to develop computational models that help to answer how the constant level of hospital resources and the changing demand for medical care can be modeled. We propose an intelligent framework to improve ED operations following a four-stage process. Stage one – develop univariate and multivariate forecasting models to forecast daily ED patient arrivals, which will help hospital management efficiently plan and allocate limited ED resources. Stage two – investigate the current prolonged ED length of stay for COVID-19 patients, using ensemble methods. Stage three – developing a multi-scale simulation-optimization framework to investigate how resource allocation affects the ED’s performance during a surge. The simulation model combines agent-based, discrete event, and system dynamics, where system dynamics address the spread of disease, agent-based models the behavior of patients and resources (i.e., doctors and nurses), and discrete event models the processes within the hospital emergency departments. The expected outcomes of the study are the multi-objective combination of indicators to optimize ED performance and studying the interactions between the different ED operations to improve service capacity. Our proposed activity will assist hospital administrators, and clinicians plan effectively to ramp up capacity in response to the current and future pandemic.