A Data-driven Decision Making Approach for Emergency Department Operations

Nilay Tanık Argon, University of North Carolina at Chapel Hill

Abstract

Long waits and congestion at emergency departments (EDs) have long been recognized as a challenging problem to tackle. One of the main reasons behind ED crowding is the long boarding times for patients who are admitted to a hospital unit after their ED stay. In this presentation, I will discuss a research project that aims at reducing boarding times by predicting, at the time of triage, whether or not a patient will eventually be admitted to the hospital. The idea is that if the prediction turns out to be “admit,” the ED can start preparations for the patient’s transfer to the main hospital early in the ED visit. However, it is not clear whether or not an estimate for the probability of admit would be considered high enough to request a bed early, whether this determination should depend on ED census, and what the potential benefits of adopting such a policy would be. The methodology we propose first estimates hospital admission probabilities using standard logistic regression techniques. To determine whether or not a given probability of admission is high enough to qualify a bed request early, we develop and analyze a mathematical decision model. This model is a highly simplified representation of the actual system, and thus, do not lead to directly implementable policies. However, building on the solution to the simplified model, we propose two policies that can be used in practice. Using data from an academic hospital ED in Southeastern United States, we develop a simulation model to test the proposed policies and find that both policies can bring modest to substantial benefits especially when the ED experiences more than usual levels of patient demand, e.g., during an influenza pandemic.

Short Bio

Nilay Tanık Argon is a Professor in the Department of Statistics and Operations Research at the University of North Carolina at Chapel Hill. She holds a PhD degree in Industrial and Systems Engineering from Georgia Institute of Technology. Her research interests are in stochastic modeling and analysis of service and manufacturing systems, healthcare operations with an emphasis on emergency care and management, and statistical output analysis for computer simulations. She currently serves on the editorial boards of Health Care Management Science, IISE Transactions, and Operations Research.

Venue

Friday, January 7, 2022, 4.00 pm - Zoom Meeting