Predicting Emergency Department Admissions Using a Machine-learning Algorithm: a Proof of Concept with Retrospective Study

Overview

Journal BMC Emerg Med

Publisher Biomed Central

Specialty Emergency Medicine

Date 2025 Jan 6

PMID 39762754

Authors

Cyrielle Brossard

Christophe Goetz

Pierre Catoire

Lauriane Cipolat

Christophe Guyeux

Cedric Gil Jardine

Mahuna Akplogan

Laure Abensur Vuillaume

Affiliations

Soon will be listed here.

Abstract

Introduction: Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED.

Aim: The main objective of this study was to build and test a prediction tool for ED admissions using artificial intelligence.

Methods: We performed a retrospective multicenter study in two French ED from January 1st, 2010 to December 31st, 2019.We tested several machine learning algorithms and compared the results.

Results: The arrival and departure times from the ED of 2 hospitals were collected from all consultations during the study period, then grouped into 87 600 one-hour slots. Through the development of two models (one for each location), we found that the XGBoost method with hyperparameter adaptations was the best, suggesting that the studied data could be predicted (mean absolute error) at 2.63 for Hospital 1 and 2.64 for Hospital 2).

Conclusions: This study ran the construction and validation of a powerful tool for predicting ED admissions in 2 French ED. This type of tool should be integrated into the overall organization of an ED, to optimize the resources of healthcare professionals.

References

Stewart J, Sprivulis P, Dwivedi G . Artificial intelligence and machine learning in emergency medicine. Emerg Med Australas. 2018; 30(6):870-874. DOI: 10.1111/1742-6723.13145. View

Jones S, Thomas A, Evans R, Welch S, Haug P, Snow G . Forecasting daily patient volumes in the emergency department. Acad Emerg Med. 2008; 15(2):159-70. DOI: 10.1111/j.1553-2712.2007.00032.x. View

Kuo Y, Chan N, Leung J, Meng H, So A, Tsoi K . An Integrated Approach of Machine Learning and Systems Thinking for Waiting Time Prediction in an Emergency Department. Int J Med Inform. 2020; 139:104143. DOI: 10.1016/j.ijmedinf.2020.104143. View

Schweigler L, Desmond J, McCarthy M, Bukowski K, Ionides E, Younger J . Forecasting models of emergency department crowding. Acad Emerg Med. 2009; 16(4):301-8. DOI: 10.1111/j.1553-2712.2009.00356.x. View

Levin S, Toerper M, Hamrock E, Hinson J, Barnes S, Gardner H . Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index. Ann Emerg Med. 2017; 71(5):565-574.e2. DOI: 10.1016/j.annemergmed.2017.08.005. View

Rauch J, Hubner U, Denter M, Babitsch B . Improving the Prediction of Emergency Department Crowding: A Time Series Analysis Including Road Traffic Flow. Stud Health Technol Inform. 2019; 260:57-64. View

Marcilio I, Hajat S, Gouveia N . Forecasting daily emergency department visits using calendar variables and ambient temperature readings. Acad Emerg Med. 2013; 20(8):769-77. DOI: 10.1111/acem.12182. View

Hoot N, Aronsky D . Systematic review of emergency department crowding: causes, effects, and solutions. Ann Emerg Med. 2008; 52(2):126-36. PMC: 7340358. DOI: 10.1016/j.annemergmed.2008.03.014. View

Kulstad E, Sikka R, Sweis R, Kelley K, Rzechula K . ED overcrowding is associated with an increased frequency of medication errors. Am J Emerg Med. 2010; 28(3):304-9. DOI: 10.1016/j.ajem.2008.12.014. View

10.

Pak A, Gannon B, Staib A . Predicting waiting time to treatment for emergency department patients. Int J Med Inform. 2020; 145:104303. DOI: 10.1016/j.ijmedinf.2020.104303. View

11.

Sun Y, Teow K, Heng B, Ooi C, Tay S . Real-time prediction of waiting time in the emergency department, using quantile regression. Ann Emerg Med. 2012; 60(3):299-308. DOI: 10.1016/j.annemergmed.2012.03.011. View

12.

Institute Of Medicine . IOM report: the future of emergency care in the United States health system. Acad Emerg Med. 2006; 13(10):1081-5. DOI: 10.1197/j.aem.2006.07.011. View

13.

Roussel M, Teissandier D, Yordanov Y, Balen F, Noizet M, Tazarourte K . Overnight Stay in the Emergency Department and Mortality in Older Patients. JAMA Intern Med. 2023; 183(12):1378-1385. PMC: 10628833. DOI: 10.1001/jamainternmed.2023.5961. View

14.

Friedman J, Hastie T, Tibshirani R . Regularization Paths for Generalized Linear Models via Coordinate Descent. J Stat Softw. 2010; 33(1):1-22. PMC: 2929880. View

15.

Kellermann A . Crisis in the emergency department. N Engl J Med. 2006; 355(13):1300-3. DOI: 10.1056/NEJMp068194. View

16.

Bergs J, Heerinckx P, Verelst S . Knowing what to expect, forecasting monthly emergency department visits: A time-series analysis. Int Emerg Nurs. 2013; 22(2):112-5. DOI: 10.1016/j.ienj.2013.08.001. View

17.

Barak-Corren Y, Chaudhari P, Perniciaro J, Waltzman M, Fine A, Reis B . Prediction across healthcare settings: a case study in predicting emergency department disposition. NPJ Digit Med. 2021; 4(1):169. PMC: 8674364. DOI: 10.1038/s41746-021-00537-x. View

18.

Zlotnik A, Gallardo-Antolin A, Cuchi Alfaro M, Perez M, Martinez J . Emergency Department Visit Forecasting and Dynamic Nursing Staff Allocation Using Machine Learning Techniques With Readily Available Open-Source Software. Comput Inform Nurs. 2015; 33(8):368-77. DOI: 10.1097/CIN.0000000000000173. View

19.

Cote M, Smith M, Eitel D, Akcali E . Forecasting emergency department arrivals: a tutorial for emergency department directors. Hosp Top. 2013; 91(1):9-19. DOI: 10.1080/00185868.2013.757962. View

20.

Jang D, Kim J, Jo Y, Lee J, Hwang J, Park S . Developing neural network models for early detection of cardiac arrest in emergency department. Am J Emerg Med. 2019; 38(1):43-49. DOI: 10.1016/j.ajem.2019.04.006. View