Shorter waiting time, better emergency healthcare: Forecasting Stockholm’s emergency department visits

Issue title: Special Issue – SAS Global Forum 2018

Guest editors: Jennifer Waller and Tyler Smith

Article type: Research Article

Authors: Ekström, Andreas^a | Nordberg, Martin^{a; b; *} | Eriksson, Oskar^c

Affiliations: [a] Department of Clinical Science and Education, Södersjukhuset, Karolinska Institutet, Stockholm, Sweden | [b] Department of Surgery, Södersjukhuset, Stockholm, Sweden | [c] SAS Institute Inc., Stockholm, Sweden

Correspondence: [*] Corresponding author: Martin Nordberg, Department of Surgery, Södersjukhuset, Sjukhusbacken 10, 118 83 Stockholm, Sweden. Tel.: +46 8 616 10 00; E-mail: [email protected].

Abstract: Emergency department (ED) overcrowding is a problem for EDs world-wide, but first and foremost it is a problem for the patients who are affected from it as ED overcrowding leads to higher morbidity and mortality for the patients. Forecasting of ED inflow for planning ED operations and steering patients streams in a region is an integral part of mitigating the overcrowding issue. In the study at hand, four different forecasting models for ED inflow are developed, validated and tested. Gradient boosting as modelling method yielded the best results for forecasting the coming 72 hours of ED inflow, mean absolute percentage error of 21%. This is a sufficiently accurate model to implement in a new information system for planning ED operations in a health care region.

Keywords: Emergency department, overcrowding, forecasting, autoregressive integrated moving average, machine learning, gradient boosting, neural networks

DOI: 10.3233/MAS-180448

Journal: Model Assisted Statistics and Applications, vol. 13, no. 4, pp. 377-385, 2018