Comparison of Time Series Prediction of Healthcare Emergency Department Indicators with ARIMA and Prophet

摘要

Predicting emergency department (ED) indicators in time series may benefit hospital planning,improving quality of care and optimising resources. It motivates analysis of models that canforecast relevant KPIs (Key Performance Indicators) for identifying future pressure. This paperanalyses the Autoregressive Integrated Moving Average (ARIMA) method in comparison to theanalysis of Prophet, an autoregressive forecasting model based on Re-current Neural Networks.The dataset analysed is formed by hourly valued hospital indicators, composed by Wait to beSeen Major in ED, Number of Attendances Major in ED, Unallocated Patients in ED with aDTA and Number of Beds Available on Medical Acute Unit. A comparison of predictions modelsARIMA and Prophet is the focus. Each model is designed to provide better predictions fordifferent time series characteristics. Measurements of best prediction for each indicator arebased in accuracy, reliability bands and indicator meta information.