Forecasting hourly emergency department arrival using time series analysis

Background/aims The stochastic arrival of patients at hospital emergency
departments complicates their management. More than 50% of a
hospital's emergency department tends to operate beyond its normal
capacity and eventually fails to deliver high-quality care. To address
this concern, much research has been carried out using yearly, monthly and
weekly time-series forecasting. This article discusses the use of hourly
time-series forecasting to help improve emergency department management by
predicting the arrival of future patients. Methods Emergency department
admission data from January 2014 to August 2017 was retrieved from a
hospital in Iowa. The auto-regressive integrated moving average (ARIMA),
Holt–Winters, TBATS, and neural network methods were implemented and
compared as forecasters of hourly patient arrivals. Results The
auto-regressive integrated moving average (3,0,0) (2,1,0) was selected as
the best fit model, with minimum Akaike information criterion and Schwartz
Bayesian criterion. The model was stationary and qualified under the
Box–Ljung correlation test and the Jarque–Bera test for normality. The
mean error and root mean square error were selected as performance
measures. A mean error of 1.001 and a root mean square error of 1.55 were
obtained. Conclusions The auto-regressive integrated moving average can be
used to provide hourly forecasts for emergency department arrivals and can
be implemented as a decision support system to aid staff when scheduling
and adjusting emergency department arrivals.