Probabilistic forecasting of hourly Emergency Department arrivals

Rostami-Tabar, Bahman ORCID: https://orcid.org/0000-0002-3730-0045, Browell, Jethro and Svetunkov, Ivan 2023. Probabilistic forecasting of hourly Emergency Department arrivals. Health Systems 10.1080/20476965.2023.2200526 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 1 May 2024 due to copyright restrictions. Download (929kB)

Abstract

An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients’ demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. This can have many advantages for healthcare staff and the quality of care delivered to patients. In this study, we develop an innovative model based on Generalised Additive Models and an advanced dynamic model based on exponential smoothing to generate an hourly probabilistic forecast of ED arrivals for a prediction window of 48 hours. We compare the forecast accuracy of these models against appropriate benchmarks, including TBATS, Poisson Regression, Prophet, and simple empirical distribution. We use Root Mean Squared Error (RMSE) to examine the point forecast accuracy and assess the forecast distribution accuracy using Quantile Bias, PinBall Score and Pinball Skill Score. Our results indicate that the proposed models outperform their benchmarks for point and probabilistic forecasts. Our developed models can also be generalised to forecast hourly arrivals in other services such as hospitals, ambulances, or clinical desk services.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Business (Including Economics)
Publisher:	Palgrave Macmillan
ISSN:	2047-6965
Date of First Compliant Deposit:	8 March 2023
Date of Acceptance:	6 March 2023
Last Modified:	07 Nov 2023 18:53
URI:	https://orca.cardiff.ac.uk/id/eprint/157566

Actions (repository staff only)

Edit Item