Dự báo lượng bệnh nhân cấp cứu hàng ngày tại bệnh viện: Một nghiên cứu tình huống

Abstract

The goal of this study is to analyze the performance of three forecasting models in predicting daily patient arrivals in the emergency department (ED). Due to the fact that emergency patient flow is highly uncertain and dynamic, this forecasting problem is a challenging task. We tested different time series models to forecast ED daily patient arrivals at General Hospital of Cu Chi Area in Ho Chi Minh city, Vietnam. Forecasting models tested in this work are seasonal multiplicative Holt-Winters (HW), autoregressive integrated moving average (ARIMA) and seasonal artificial neural network (SANN).  The experimental results show that all the three models bring out acceptable predictive accuracy and SANN is the best model for forecasting emergency patient arrivals in the selected hospital. The MAPE of SANN model is 12.74 %.