A Stacked ensemble method for forecasting influenza-like illness visit volumes at emergency departments

Abstract

Accurate and reliable short-term forecasts of influenza-like illness (ILI) visit volumes at the emergency departments can improve staffing and resource allocation decisions in each hospital. In this paper, we developed a stacked ensemble model that averages the predictions from various competing methodologies in the current frontier for ILI-related forecasts. We also constructed a back-of-the-envelope prediction interval for the stacked ensemble, which provides a conservative characterization of the uncertainty in the stacked ensemble predictions. We assessed the reliability and accuracy of our models 1 to 4 weeks ahead forecasts using real-time hospital-level data on weekly ILI visit volumes during the 2012-2018 flu seasons in the Alberta Childrens Hospital, located in Calgary, Alberta, Canada. Over this time period, our models prediction deviated from the realized ILI visit volume by an average of 12% for 1 week ahead forecasts, with a 90% prediction interval having coverage rates ranging from 90.7 to 97.7%.