Modeling daily patient arrivals at Emergency Department and quantifying the relative importance of contributing variables using artificial neural network

M. Xu, T.C. Wong, K.S. Chin

Research output: Contribution to journalArticle

36 Citations (Scopus)

Abstract

Emergency Department (ED) plays a critical role in healthcare systems by providing emergency care to patients in need. The quality of ED services, measured by waiting time and length of stay, is significantly affected by patient arrivals. Increased patient arrivals could undermine service timeliness, thus putting patients in severe conditions at risk. These factors lead to the following research questions that have rarely been studied before: What are the variables directly associated with patient arrivals in the ED? What is the nature of association between these variables and patient arrivals? Which variable is the most influential and why? To address the above questions, we proposed a three-stage method in this paper. First, a data-driven method is used to identify contributing variables directly correlated with the daily arrivals of Categories 3 and 4 patients (i.e., non-critical patients). Second, the association between contributing variables and daily patient arrival is modeled by using artificial neural network (ANN), and the modeling ability is compared with that of nonlinear least square regression (NLLSR) and multiple linear regression (MLR) in terms of mean average percentage error (MAPE). Third, four types of relative importance (RI) of input variables based on ANN are compared, and their statistical reliability is tested by the MLR-based RI. We applied this three-stage method to one year of data of patient arrivals at a local ED. The contribution of this paper is twofold. Theoretically, this paper emphasizes the importance of using data-driven selection of variables for complex system modeling, and then provides a comprehensive comparison of RI using different computational methods. Practically, this work is a novel attempt of applying ANN to model patient arrivals, and the result can be used to aid in strategic decision-making on ED resource planning in response to predictable arrival variations.
LanguageEnglish
Pages1488-1498
Number of pages11
JournalDecision Support Systems
Volume54
Issue number3
DOIs
Publication statusPublished - 1 Jan 2013

Fingerprint

Hospital Emergency Service
Neural networks
Linear regression
Computational methods
Large scale systems
Decision making
Planning
Linear Models
Emergency department
Modeling
Artificial neural network
Relative importance
Emergency
Artificial Neural Network
Aptitude
Neural Networks (Computer)
Emergency Medical Services
Least-Squares Analysis
Length of Stay
Decision Making

Keywords

  • multiple linear regression
  • patient arrival
  • emergency department
  • relative importance
  • artificial neural network

Cite this

@article{b76ef364da124de994cf0c0f0bd49d7b,
title = "Modeling daily patient arrivals at Emergency Department and quantifying the relative importance of contributing variables using artificial neural network",
abstract = "Emergency Department (ED) plays a critical role in healthcare systems by providing emergency care to patients in need. The quality of ED services, measured by waiting time and length of stay, is significantly affected by patient arrivals. Increased patient arrivals could undermine service timeliness, thus putting patients in severe conditions at risk. These factors lead to the following research questions that have rarely been studied before: What are the variables directly associated with patient arrivals in the ED? What is the nature of association between these variables and patient arrivals? Which variable is the most influential and why? To address the above questions, we proposed a three-stage method in this paper. First, a data-driven method is used to identify contributing variables directly correlated with the daily arrivals of Categories 3 and 4 patients (i.e., non-critical patients). Second, the association between contributing variables and daily patient arrival is modeled by using artificial neural network (ANN), and the modeling ability is compared with that of nonlinear least square regression (NLLSR) and multiple linear regression (MLR) in terms of mean average percentage error (MAPE). Third, four types of relative importance (RI) of input variables based on ANN are compared, and their statistical reliability is tested by the MLR-based RI. We applied this three-stage method to one year of data of patient arrivals at a local ED. The contribution of this paper is twofold. Theoretically, this paper emphasizes the importance of using data-driven selection of variables for complex system modeling, and then provides a comprehensive comparison of RI using different computational methods. Practically, this work is a novel attempt of applying ANN to model patient arrivals, and the result can be used to aid in strategic decision-making on ED resource planning in response to predictable arrival variations.",
keywords = "multiple linear regression, patient arrival, emergency department, relative importance, artificial neural network",
author = "M. Xu and T.C. Wong and K.S. Chin",
year = "2013",
month = "1",
day = "1",
doi = "10.1016/j.dss.2012.12.019",
language = "English",
volume = "54",
pages = "1488--1498",
journal = "Decision Support Systems",
issn = "0167-9236",
number = "3",

}

TY - JOUR

T1 - Modeling daily patient arrivals at Emergency Department and quantifying the relative importance of contributing variables using artificial neural network

AU - Xu, M.

AU - Wong, T.C.

AU - Chin, K.S.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Emergency Department (ED) plays a critical role in healthcare systems by providing emergency care to patients in need. The quality of ED services, measured by waiting time and length of stay, is significantly affected by patient arrivals. Increased patient arrivals could undermine service timeliness, thus putting patients in severe conditions at risk. These factors lead to the following research questions that have rarely been studied before: What are the variables directly associated with patient arrivals in the ED? What is the nature of association between these variables and patient arrivals? Which variable is the most influential and why? To address the above questions, we proposed a three-stage method in this paper. First, a data-driven method is used to identify contributing variables directly correlated with the daily arrivals of Categories 3 and 4 patients (i.e., non-critical patients). Second, the association between contributing variables and daily patient arrival is modeled by using artificial neural network (ANN), and the modeling ability is compared with that of nonlinear least square regression (NLLSR) and multiple linear regression (MLR) in terms of mean average percentage error (MAPE). Third, four types of relative importance (RI) of input variables based on ANN are compared, and their statistical reliability is tested by the MLR-based RI. We applied this three-stage method to one year of data of patient arrivals at a local ED. The contribution of this paper is twofold. Theoretically, this paper emphasizes the importance of using data-driven selection of variables for complex system modeling, and then provides a comprehensive comparison of RI using different computational methods. Practically, this work is a novel attempt of applying ANN to model patient arrivals, and the result can be used to aid in strategic decision-making on ED resource planning in response to predictable arrival variations.

AB - Emergency Department (ED) plays a critical role in healthcare systems by providing emergency care to patients in need. The quality of ED services, measured by waiting time and length of stay, is significantly affected by patient arrivals. Increased patient arrivals could undermine service timeliness, thus putting patients in severe conditions at risk. These factors lead to the following research questions that have rarely been studied before: What are the variables directly associated with patient arrivals in the ED? What is the nature of association between these variables and patient arrivals? Which variable is the most influential and why? To address the above questions, we proposed a three-stage method in this paper. First, a data-driven method is used to identify contributing variables directly correlated with the daily arrivals of Categories 3 and 4 patients (i.e., non-critical patients). Second, the association between contributing variables and daily patient arrival is modeled by using artificial neural network (ANN), and the modeling ability is compared with that of nonlinear least square regression (NLLSR) and multiple linear regression (MLR) in terms of mean average percentage error (MAPE). Third, four types of relative importance (RI) of input variables based on ANN are compared, and their statistical reliability is tested by the MLR-based RI. We applied this three-stage method to one year of data of patient arrivals at a local ED. The contribution of this paper is twofold. Theoretically, this paper emphasizes the importance of using data-driven selection of variables for complex system modeling, and then provides a comprehensive comparison of RI using different computational methods. Practically, this work is a novel attempt of applying ANN to model patient arrivals, and the result can be used to aid in strategic decision-making on ED resource planning in response to predictable arrival variations.

KW - multiple linear regression

KW - patient arrival

KW - emergency department

KW - relative importance

KW - artificial neural network

UR - http://www.scopus.com/inward/record.url?scp=84875413164&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2012.12.019

DO - 10.1016/j.dss.2012.12.019

M3 - Article

VL - 54

SP - 1488

EP - 1498

JO - Decision Support Systems

T2 - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

IS - 3

ER -