Early Warning Software for Emergency Department Crowding

• DOI: 10.1007/s10916-023-01958-9
• Publication Date: 2023-05-26T08:02:26Z
• Authors: Jalmari Tuominen; Teemu Koivistoinen; Juho Kanniainen; Niku Oksala; Ari Palomäki; Antti Roine
• Keywords: Crowding

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 better resource management the potential improve treatment outcomes. This logic motivated an increasing number research articles but there little no effort move these findings from theory practice. In this article, we present first results prospective early warning software, that was integrated hospital databases create real-time predictions every hour over course 5 months in Nordic combined ED using Holt-Winters’ seasonal methods. We show software predict next AUC 0.94 (95% CI: 0.91-0.97) 24 0.79 0.74-0.84) simple statistical models. Moreover, suggest afternoon can be predicted at 1 p.m. 0.84 0.74-0.91).