Early Warning Software for Emergency Department Crowding

TL;DR

This study presents a real-time early warning software for ED crowding, demonstrating high predictive accuracy for short-term and daily crowding using simple statistical models over a 5-month period.

Contribution

It introduces a practical, real-time crowding prediction tool integrated into hospital systems, moving beyond theoretical models to real-world application.

Findings

Predicted next hour crowding with AUC of 0.98

Forecasted 24-hour crowding with AUC of 0.79

Predicted afternoon crowding at 1 p.m. with AUC of 0.84

Abstract

Emergency department (ED) crowding is a well-recognized threat to patient safety and it has been repeatedly associated with increased mortality. Accurate forecasts of future service demand could lead to better resource management and has the potential to improve treatment outcomes. This logic has motivated an increasing number of research articles but there has been little to no effort to move these findings from theory to practice. In this article, we present first results of a prospective crowding early warning software, that was integrated to hospital databases to create real-time predictions every hour over the course of 5 months in a Nordic combined ED using Holt-Winters' seasonal methods. We showed that the software could predict next hour crowding with a nominal AUC of 0.98 and 24 hour crowding with an AUC of 0.79 using simple statistical models. Moreover, we suggest that afternoon crowding can be predicted at 1 p.m. with an AUC of 0.84.