Forecasting Emergency Department Crowding: A Prospective, Real-time Evaluation

Nathan R. Hoot, Larry J. LeBlanc, Ian Jones, Scott Levin, Chuan Zhou, Cynthia S. Gadd, Dominik Aronsky

Research output: Contribution to journalArticle

Abstract

Objective: Emergency department crowding threatens quality and access to health care, and a method of accurately forecasting near-future crowding should enable novel ways to alleviate the problem. The authors sought to implement and validate the previously developed ForecastED discrete event simulation for real-time forecasting of emergency department crowding. Design and Measurements: The authors conducted a prospective observational study during a three-month period (5/1/07-8/1/07) in the adult emergency department of a tertiary care medical center. The authors connected the forecasting tool to existing information systems to obtain real-time forecasts of operational data, updated every 10 minutes. The outcome measures included the emergency department waiting count, waiting time, occupancy level, length of stay, boarding count, boarding time, and ambulance diversion; each forecast 2, 4, 6, and 8 hours into the future. Results: The authors obtained crowding forecasts at 13,239 10-minute intervals, out of 13,248 possible (99.9%). The R2 values for predicting operational data 8 hours into the future, with 95% confidence intervals, were 0.27 (0.26, 0.29) for waiting count, 0.11 (0.10, 0.12) for waiting time, 0.57 (0.55, 0.58) for occupancy level, 0.69 (0.68, 0.70) for length of stay, 0.61 (0.59, 0.62) for boarding count, and 0.53 (0.51, 0.54) for boarding time. The area under the receiver operating characteristic curve for predicting ambulance diversion 8 hours into the future, with 95% confidence intervals, was 0.85 (0.84, 0.86). Conclusions: The ForecastED tool provides accurate forecasts of several input, throughput, and output measures of crowding up to 8 hours into the future. The real-time deployment of the system should be feasible at other emergency departments that have six patient-level variables available through information systems.

Original languageEnglish (US)
Pages (from-to)338-345
Number of pages8
JournalJournal of the American Medical Informatics Association
Volume16
Issue number3
DOIs
StatePublished - May 2009

Fingerprint

Hospital Emergency Service
Ambulance Diversion
Information Systems
Length of Stay
Confidence Intervals
Health Services Accessibility
Computer Systems
Tertiary Care Centers
ROC Curve
Observational Studies
Outcome Assessment (Health Care)
Prospective Studies

ASJC Scopus subject areas

  • Health Informatics

Cite this

Forecasting Emergency Department Crowding : A Prospective, Real-time Evaluation. / Hoot, Nathan R.; LeBlanc, Larry J.; Jones, Ian; Levin, Scott; Zhou, Chuan; Gadd, Cynthia S.; Aronsky, Dominik.

In: Journal of the American Medical Informatics Association, Vol. 16, No. 3, 05.2009, p. 338-345.

Research output: Contribution to journalArticle

Hoot, Nathan R. ; LeBlanc, Larry J. ; Jones, Ian ; Levin, Scott ; Zhou, Chuan ; Gadd, Cynthia S. ; Aronsky, Dominik. / Forecasting Emergency Department Crowding : A Prospective, Real-time Evaluation. In: Journal of the American Medical Informatics Association. 2009 ; Vol. 16, No. 3. pp. 338-345.
@article{2c35ec7604cb441f9d2724798ea46fcd,
title = "Forecasting Emergency Department Crowding: A Prospective, Real-time Evaluation",
abstract = "Objective: Emergency department crowding threatens quality and access to health care, and a method of accurately forecasting near-future crowding should enable novel ways to alleviate the problem. The authors sought to implement and validate the previously developed ForecastED discrete event simulation for real-time forecasting of emergency department crowding. Design and Measurements: The authors conducted a prospective observational study during a three-month period (5/1/07-8/1/07) in the adult emergency department of a tertiary care medical center. The authors connected the forecasting tool to existing information systems to obtain real-time forecasts of operational data, updated every 10 minutes. The outcome measures included the emergency department waiting count, waiting time, occupancy level, length of stay, boarding count, boarding time, and ambulance diversion; each forecast 2, 4, 6, and 8 hours into the future. Results: The authors obtained crowding forecasts at 13,239 10-minute intervals, out of 13,248 possible (99.9{\%}). The R2 values for predicting operational data 8 hours into the future, with 95{\%} confidence intervals, were 0.27 (0.26, 0.29) for waiting count, 0.11 (0.10, 0.12) for waiting time, 0.57 (0.55, 0.58) for occupancy level, 0.69 (0.68, 0.70) for length of stay, 0.61 (0.59, 0.62) for boarding count, and 0.53 (0.51, 0.54) for boarding time. The area under the receiver operating characteristic curve for predicting ambulance diversion 8 hours into the future, with 95{\%} confidence intervals, was 0.85 (0.84, 0.86). Conclusions: The ForecastED tool provides accurate forecasts of several input, throughput, and output measures of crowding up to 8 hours into the future. The real-time deployment of the system should be feasible at other emergency departments that have six patient-level variables available through information systems.",
author = "Hoot, {Nathan R.} and LeBlanc, {Larry J.} and Ian Jones and Scott Levin and Chuan Zhou and Gadd, {Cynthia S.} and Dominik Aronsky",
year = "2009",
month = "5",
doi = "10.1197/jamia.M2772",
language = "English (US)",
volume = "16",
pages = "338--345",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Forecasting Emergency Department Crowding

T2 - A Prospective, Real-time Evaluation

AU - Hoot, Nathan R.

AU - LeBlanc, Larry J.

AU - Jones, Ian

AU - Levin, Scott

AU - Zhou, Chuan

AU - Gadd, Cynthia S.

AU - Aronsky, Dominik

PY - 2009/5

Y1 - 2009/5

N2 - Objective: Emergency department crowding threatens quality and access to health care, and a method of accurately forecasting near-future crowding should enable novel ways to alleviate the problem. The authors sought to implement and validate the previously developed ForecastED discrete event simulation for real-time forecasting of emergency department crowding. Design and Measurements: The authors conducted a prospective observational study during a three-month period (5/1/07-8/1/07) in the adult emergency department of a tertiary care medical center. The authors connected the forecasting tool to existing information systems to obtain real-time forecasts of operational data, updated every 10 minutes. The outcome measures included the emergency department waiting count, waiting time, occupancy level, length of stay, boarding count, boarding time, and ambulance diversion; each forecast 2, 4, 6, and 8 hours into the future. Results: The authors obtained crowding forecasts at 13,239 10-minute intervals, out of 13,248 possible (99.9%). The R2 values for predicting operational data 8 hours into the future, with 95% confidence intervals, were 0.27 (0.26, 0.29) for waiting count, 0.11 (0.10, 0.12) for waiting time, 0.57 (0.55, 0.58) for occupancy level, 0.69 (0.68, 0.70) for length of stay, 0.61 (0.59, 0.62) for boarding count, and 0.53 (0.51, 0.54) for boarding time. The area under the receiver operating characteristic curve for predicting ambulance diversion 8 hours into the future, with 95% confidence intervals, was 0.85 (0.84, 0.86). Conclusions: The ForecastED tool provides accurate forecasts of several input, throughput, and output measures of crowding up to 8 hours into the future. The real-time deployment of the system should be feasible at other emergency departments that have six patient-level variables available through information systems.

AB - Objective: Emergency department crowding threatens quality and access to health care, and a method of accurately forecasting near-future crowding should enable novel ways to alleviate the problem. The authors sought to implement and validate the previously developed ForecastED discrete event simulation for real-time forecasting of emergency department crowding. Design and Measurements: The authors conducted a prospective observational study during a three-month period (5/1/07-8/1/07) in the adult emergency department of a tertiary care medical center. The authors connected the forecasting tool to existing information systems to obtain real-time forecasts of operational data, updated every 10 minutes. The outcome measures included the emergency department waiting count, waiting time, occupancy level, length of stay, boarding count, boarding time, and ambulance diversion; each forecast 2, 4, 6, and 8 hours into the future. Results: The authors obtained crowding forecasts at 13,239 10-minute intervals, out of 13,248 possible (99.9%). The R2 values for predicting operational data 8 hours into the future, with 95% confidence intervals, were 0.27 (0.26, 0.29) for waiting count, 0.11 (0.10, 0.12) for waiting time, 0.57 (0.55, 0.58) for occupancy level, 0.69 (0.68, 0.70) for length of stay, 0.61 (0.59, 0.62) for boarding count, and 0.53 (0.51, 0.54) for boarding time. The area under the receiver operating characteristic curve for predicting ambulance diversion 8 hours into the future, with 95% confidence intervals, was 0.85 (0.84, 0.86). Conclusions: The ForecastED tool provides accurate forecasts of several input, throughput, and output measures of crowding up to 8 hours into the future. The real-time deployment of the system should be feasible at other emergency departments that have six patient-level variables available through information systems.

UR - http://www.scopus.com/inward/record.url?scp=65349128949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65349128949&partnerID=8YFLogxK

U2 - 10.1197/jamia.M2772

DO - 10.1197/jamia.M2772

M3 - Article

C2 - 19261948

AN - SCOPUS:65349128949

VL - 16

SP - 338

EP - 345

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 3

ER -