Predicting Patient Admission From the Emergency Department Using Administrative and Diagnostic Data

David Savage, Douglas Woolford, Mackenzie Simpson, David Wood, Robert Ohle

OAI: oai:igi-global.com:260724 • DOI: 10.4018/IJEACH.2020070101

Emergency department (ED) overcrowding is a growing problem in Canada. Many interventions have been proposed to increase patient flow. The objective of this study was to predict patient admission early in the visit with the goal of reducing waiting time in ED for admitted patients. ED data for a one-year period from Thunder Bay, Canada was obtained. Initial logistic regression models were developed using age, sex, mode of arrival, and patient acuity as explanatory variables and admission yes or no as the outcome. A second stage prediction was made using the diagnostic tests ordered to further refine the predictive models. Predictive accuracy of the logistic regression model was adequate. The AUC was approximately 81%. By summing the probabilities of patients in the ED, the hourly prediction improved. This study has shown that the number of hospital beds required on an hourly basis can be predicted using triage administrative data.

Health Information Systems Medical, Healthcare, and Life Sciences Medical Technologies