EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Forecasting emergency department waiting time using a state space representation

Kelly Trinh iD, Andrew Staib, Anton Pak

Statistics in Medicine · 30.10.2023 · 42 (24) · 4458-4483

DOI: 10.1002/sim.9870 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, online erschienen am 09.08.2023. Verfasst von Kelly Trinh und 2 weiteren Autor:innen. Beteiligte Einrichtung: Data61, The Commonwealth Scientific and Industrial Research Organisation, Clayton, Victoria, Australia. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Waiting Lists, Models, Statistical. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: The Emergency Medicine Foundation (Australasia) Queensland Program, University of Queensland Health and Behavioural Science Faculty Early Career Academic Research Accelerator Award.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The provision of waiting time information in emergency departments (ED) has become an increasingly popular practice due to its positive impact on patient experience and ED demand management. However, little scientific attention has been given to the quality and quantity of waiting time information presented to patients. To improve both aspects, we propose a set of state space models with flexible error structures to forecast ED waiting time for low acuity patients. Our approach utilizes a Bayesian framework to generate uncertainties associated with the forecasts. We find that the state‐space models with flexible error structures significantly improve forecast accuracy of ED waiting time compared to the benchmark, which is the rolling average model. Specifically, incorporating time‐varying and correlated error terms reduces the root mean squared errors of the benchmark by 10%. Furthermore, treating zero‐recorded waiting times as unobserved values improves forecast performance. Our proposed model has the ability to provide patient‐centric waiting time information. By offering more accurate and informative waiting time information, our model can help patients make better informed decisions and ultimately enhance their ED experience.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Emergency Service, HospitalWaiting ListsModels, StatisticalHumansBayes TheoremForecastingTime Factors

Stichwörter der Autor:innen

Bayesian state space modelMCMCemergency department waiting time

Autor:innen und Institutionen

  • Data61, The Commonwealth Scientific and Industrial Research Organisation, Clayton, Victoria, Australia.
  • College of Science and Engineering, James Cook University, Douglas, Queensland, Australia.
  • Faculty of Medicine, University of Queensland, Brisbane, Woolloongabba, Queensland, Australia.
  • Emergency Department, Princess Alexandra Hospital, Woolloongabba, Queensland, Australia.
  • Centre for the Business and Economics of Health, The University of Queensland, Brisbane, Queensland, Australia.
  • Australian Institute of Tropical Health and Medicine, James Cook University, Douglas, Queensland, Australia.

ORCID-Profile: Kelly Trinh

Förderung

  • The Emergency Medicine Foundation (Australasia) Queensland Program
  • University of Queensland Health and Behavioural Science Faculty Early Career Academic Research Accelerator Award

Zitieren

APA

Trinh, K., Staib, A., & Pak, A. (2023). Forecasting emergency department waiting time using a state space representation. Statistics in Medicine, 42(24), 4458-4483. https://doi.org/10.1002/sim.9870

Vancouver

Trinh K, Staib A, Pak A. Forecasting emergency department waiting time using a state space representation. Statistics in Medicine. 2023;42(24):4458-4483. doi:10.1002/sim.9870

BibTeX
@article{Trinh2023,
  author = {Trinh, Kelly and Staib, Andrew and Pak, Anton},
  title = {Forecasting emergency department waiting time using a state space representation},
  journal = {Statistics in Medicine},
  year = {2023},
  volume = {42},
  number = {24},
  pages = {4458--4483},
  doi = {10.1002/sim.9870}
}
Kostenlos starten →