Background: Crowding in emergency departments (EDs) is a challenge globally. To counteract crowding in day-today\noperations, better tools to improve monitoring of the patient flow in the ED is needed. The objective of this\nstudy was the development of a continuously updated monitoring system to forecast emergency department (ED)\narrivals on a short time-horizon incorporating data from prehospital services.\nMethods: Time of notification and ED arrival was obtained for all 191,939 arrivals at the ED of a Norwegian university\nhospital from 2010 to 2018. An arrival notification was an automatically captured time stamp which indicated the first\ntime the ED was notified of an arriving patient, typically by a call from an ambulance to the emergency service\ncommunication center. A Poisson time-series regression model for forecasting the number of arrivals on a 1-, 2- and 3-\nh horizon with continuous weekly and yearly cyclic effects was implemented. We incorporated time of arrival\nnotification by modelling time to arrival as a time varying hazard function. We validated the model on the last full year\nof data.\nResults: In our data, 20% of the arrivals had been notified more than 1 hour prior to arrival. By incorporating time of\nnotification into the forecasting model, we saw a substantial improvement in forecasting accuracy, especially on a one hour\nhorizon. In terms of mean absolute prediction error, we observed around a six percentage-point decrease\ncompared to a simplified prediction model. The increase in accuracy was particularly large for periods with large inflow.\nConclusions: The proposed model shows increased predictability in ED patient inflow when incorporating data on\npatient notifications. This approach to forecasting arrivals can be a valuable tool for logistic, decision making and ED\nresource management.
Loading....