A multi-method patient arrival forecasting outline for hospital emergency departments

Abstract

Patient arrivals at the emergency department (ED) of hospitals has an unpredictable behavior. So that, adequate forecasting of this process can serve a management baseline to better allocate ED human resources and medical equipment. In this paper, a multi-method patient arrival forecasting outline for EDs is developed. The methods followed within this study include single methods as linear regression (LR), autoregressive integrated moving average (ARIMA), artificial neural network (ANN), exponential smoothing and hybrid methods as ARIMA-ANN and ARIMA-LR. As the subject of the study, a private hospital ED case in Turkey is carried out. Data of ED patient arrivals for the year of 2016 was used to set up models. Forecasting performance of the multi-method outline was measured using mean absolute percentage error. The ARIMA-ANN hybrid model is shown to outperform in terms of forecasting accuracy. In order to contribute to the current knowledge, this paper is a novel attempt of applying these methods to model ED patient arrivals and making an overall assessment among them. The results can be used to aid in strategic decision-making on ED staffing and scheduling policy planning in response to predictable arrival variations.