PLANNING THE FUTURE OF EMERGENCY DEPARTMENTS: FORECASTING ED PATIENT ARRIVALS BY USING REGRESSION AND NEURAL NETWORK MODELS

Abstract

Emergency departments (EDs) face high numbers of patient arrivals in comparison to other departments of hospitals because they provide non-stop service. Patient arrivals at these departments mostly do not appear in a steady state. Predicting existing uncertainty contributes to the future planning of these departments. Therefore, forecasting patient arrivals at emergency departments is crucial so as to make short and long term plans for physical capacity requirements, staffing, budgeting and arranging staff schedules. In this paper, variations in annual, monthly and daily ED arrivals are analyzed based on regression and neural network models with the aid of a collected data from a public hospital ED in Istanbul. The results show that ANN-based models have higher model accuracy values and lower values of absolute error in terms of forecasting the ED patient arrivals over the long and medium terms. The paper is also aimed to provide ED management and medical staff a useful guide for future planning of their emergency departments in the light of an accurate forecasting.