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

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.

[1]  S. McMillan,et al.  Predicting patient visits to an urgent care clinic using calendar variables. , 2001, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[2]  Shari J. Welch,et al.  Forecasting daily patient volumes in the emergency department. , 2008, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[3]  Nigel Crook,et al.  Using input parameter influences to support the decisions of feedforward neural networks , 1999, Neurocomputing.

[4]  Armann Ingolfsson,et al.  The application of forecasting techniques to modeling emergency medical system calls in Calgary, Alberta , 2007, Health care management science.

[5]  Alberto Gómez,et al.  Medical doctor rostering problem in a hospital emergency department by means of genetic algorithms , 2009, Comput. Ind. Eng..

[6]  Talal M. Alkhamis,et al.  Simulation optimization for an emergency department healthcare unit in Kuwait , 2009, Eur. J. Oper. Res..

[7]  Andrew H. Sung,et al.  Ranking importance of input parameters of neural networks , 1998 .

[8]  Daniel J Pallin,et al.  Parametric versus nonparametric statistical tests: the length of stay example. , 2010, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[9]  C. Roberts,et al.  Correlating weather and trauma admissions at a level I trauma center. , 2006, The Journal of trauma.

[10]  Yanrong Ni,et al.  A two-stage dynamic sales forecasting model for the fashion retail , 2011, Expert Syst. Appl..

[11]  G. Zhang,et al.  A comparative study of linear and nonlinear models for aggregate retail sales forecasting , 2003 .

[12]  James W. Taylor,et al.  A Comparison of Univariate Time Series Methods for Forecasting Intraday Arrivals at a Call Center , 2008, Manag. Sci..

[13]  Yi-Chang Chiu,et al.  Determinants of guest loyalty to international tourist hotels—a neural network approach , 2002 .

[14]  Uygar Özesmi,et al.  An artificial neural network approach to spatial habitat modelling with interspecific interaction , 1999 .

[15]  E. Ionides,et al.  Forecasting models of emergency department crowding. , 2009, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[16]  Ching-Hsue Cheng,et al.  Forecasting the number of outpatient visits using a new fuzzy time series based on weighted-transitional matrix , 2008, Expert Syst. Appl..

[17]  Ulrike Groemping,et al.  Relative Importance for Linear Regression in R: The Package relaimpo , 2006 .

[18]  Jeffrey E. Jarrett,et al.  Improving forecasting for telemarketing centers by ARIMA modeling with intervention , 1998 .

[19]  W. Baxt,et al.  Effects of neural network feedback to physicians on admit/discharge decision for emergency department patients with chest pain. , 2004, Annals of Emergency Medicine.

[20]  S. Zeger,et al.  The challenge of predicting demand for emergency department services. , 2008, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[21]  John T. Mentzer,et al.  Improving Salesforce Forecasting , 1999 .

[22]  Elizabeth H Bradley,et al.  US emergency department performance on wait time and length of visit. , 2010, Annals of emergency medicine.

[23]  Henry C. Co,et al.  Forecasting Thailand's rice export: Statistical techniques vs. artificial neural networks , 2007, Comput. Ind. Eng..

[24]  R. L. Kennedy,et al.  Artificial neural network models for prediction of acute coronary syndromes using clinical data from the time of presentation. , 2005, Annals of emergency medicine.

[25]  W. Baxt,et al.  A neural computational aid to the diagnosis of acute myocardial infarction. , 2002, Annals of emergency medicine.

[26]  Avishai Mandelbaum,et al.  Workload forecasting for a call center: Methodology and a case study , 2009, 1009.5741.

[27]  Jonathan Weinberg,et al.  Bayesian Forecasting of an Inhomogeneous Poisson Process With Applications to Call Center Data , 2007 .

[28]  James W. Taylor,et al.  Triple seasonal methods for short-term electricity demand forecasting , 2010, Eur. J. Oper. Res..

[29]  Kwai-Sang Chin,et al.  A neural network-based approach of quantifying relative importance among various determinants toward organizational innovation , 2011, Expert Syst. Appl..

[30]  Miao-Sheng Chen,et al.  Forecasting tourist arrivals by using the adaptive network-based fuzzy inference system , 2009, Expert Systems with Applications.

[31]  Karin V Rhodes,et al.  A conceptual model of emergency department crowding. , 2003, Annals of emergency medicine.

[32]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[33]  Ward Whitt,et al.  Coping with Time‐Varying Demand When Setting Staffing Requirements for a Service System , 2007 .

[34]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[35]  Chin-Tsai Lin,et al.  Artificial intelligence diagnosis algorithm for expanding a precision expert forecasting system , 2009, Expert Syst. Appl..

[36]  Yong Yu,et al.  Fashion retail forecasting by evolutionary neural networks , 2008 .

[37]  Spencer S. Jones,et al.  Advanced statistics: developing a formal model of emergency department census and defining operational efficiency. , 2007, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[38]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[39]  Peter Williams,et al.  Simulation based analysis of patient arrival to health care systems and evaluation of an operations improvement scheme , 2010, Ann. Oper. Res..

[40]  B. Gordon,et al.  Developing models for patient flow and daily surge capacity research. , 2006, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[41]  R. E. Abdel-Aal,et al.  Univariate modeling and forecasting of monthly energy demand time series using abductive and neural networks , 2008, Comput. Ind. Eng..

[42]  Peter J. Haug,et al.  A multivariate time series approach to modeling and forecasting demand in the emergency department , 2009, J. Biomed. Informatics.

[43]  W. Baxt,et al.  A neural network aid for the early diagnosis of cardiac ischemia in patients presenting to the emergency department with chest pain. , 2002, Annals of emergency medicine.

[44]  Leena A Nylander-French,et al.  Quantifying the Relative Importance of Predictors in Multiple Linear Regression Analyses for Public Health Studies , 2008, Journal of occupational and environmental hygiene.

[45]  Haipeng Shen,et al.  Interday Forecasting and Intraday Updating of Call Center Arrivals , 2008, Manuf. Serv. Oper. Manag..

[46]  Sungjune Park,et al.  EMS call volume predictions: A comparative study , 2009, Comput. Oper. Res..

[47]  Alain Yee-Loong Chong,et al.  A two-stage analysis of the influences of employee alignment on effecting business-IT alignment , 2012, Decis. Support Syst..

[48]  M. Wargon,et al.  From model to forecasting: a multicenter study in emergency departments. , 2010, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[49]  Tor Guimaraes,et al.  Integrating artificial neural networks with rule-based expert systems , 1994, Decis. Support Syst..

[50]  Eva González Romera,et al.  Forecasting of the electric energy demand trend and monthly fluctuation with neural networks , 2007, Comput. Ind. Eng..

[51]  Shing-Chung Ngan,et al.  Analyzing supply chain operation models with the PC-algorithm and the neural network , 2011, Expert Syst. Appl..

[52]  Chi-Jie Lu,et al.  Combining independent component analysis and growing hierarchical self-organizing maps with support vector regression in product demand forecasting , 2010 .

[53]  Diego J. Pedregal,et al.  An unobserved component model for multi-rate forecasting of telephone call demand: the design of a forecasting support system , 2002 .

[54]  P. Sen,et al.  Introduction to bivariate and multivariate analysis , 1981 .

[55]  J. Hayes,et al.  Local Weather Effects on Emergency Department Visits: A Time Series and Regression Analysis , 2006, Pediatric emergency care.

[56]  Kuan-Yu Chen,et al.  Combining linear and nonlinear model in forecasting tourism demand , 2011, Expert Syst. Appl..

[57]  Wen-Shan Lin,et al.  Using simulation technique and genetic algorithm to improve the quality care of a hospital emergency department , 2007, Expert Syst. Appl..

[58]  Robert Champion,et al.  Forecasting emergency department presentations. , 2007, Australian health review : a publication of the Australian Hospital Association.

[59]  G. David Garson,et al.  Interpreting neural-network connection weights , 1991 .

[60]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .