ISE Seminar: Medical Surge Capability: An Intelligent Framework for Managing Hospital Emergency Dept
This event is in the past.
Abstract: Currently, the infrastructure of our healthcare systems is at a tipping point due to the surge of patients as a result of the Omicron variant. 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, staff shortage, long wait times, and unavailability of beds. This project aims to develop computational models that help answer how the constant level of hospital resources and the changing demand for medical care can be modeled. We propose a use-inspired machine/deep learning framework to improve ED operations. To that end, I will present the development of univariate and multivariate forecasting models to forecast daily ED patient visits. The univariate models predict the demand for medical care based on daily patient arrival rates, whereas the multivariate models account for COVID-19 influence and the impact of meteorological factors on patients’ arrival. Next, I will present a machine learning model that utilizes ensemble methods to investigate the prolonged ED length of stay for COVID-19 patients. Health systems have set time-based targets in the past, requiring patients to leave the ED within the first 4 hours of arrival. However, this target has been hard to reach for COVID-19 patients with the ongoing pandemic, leading to operational inefficiencies. The results will help hospital management understand the demand for medical care, efficiently plan and allocate limited ED resources. Finally, I will conclude by providing a glimpse of some of our related ongoing work and future directions.
Bio: Dr. Egbe-Etu Etu is an Assistant Professor of Business Analytics at San Jose State University (SJSU). Before joining SJSU, Dr. Etu received his Ph.D. in Industrial and Systems Engineering from Wayne State University in 2021 and his bachelor’s degree in Civil Engineering from Covenant University, Nigeria, in 2016. His research interest centers on developing use-inspired machine learning models to solve challenging business problems in healthcare, manufacturing, and transportation. His research aims to develop decision-support tools that will help business professionals do their best work, improve resilience and overall system performance while minimizing errors. Dr. Etu is the recipient of the second-place doctoral dissertation presentation award in the 2021 IEOM Annual Conference in Mexico, 2021 ISE second-place excellence in Ph.D. research award, and first place award in the 2020 WSU graduate and postgraduate research symposium. In 2020, he received the IEOM Annual Conference Best Paper Award in the Healthcare Systems track. His research is supported by Blue Cross Blue Shield of Michigan Foundation and the US Department of Transportation (US DOT) grants. He is a member of the Industrial Engineering and Operations Management (IEOM), Institute of Industrial & Systems Engineering (IISE), and SAVE International.