Abstract
The number of emergency cases or people making emergency room visit has rapidly increased annually, leading to an imbalance in supply and demand, as well as long-term overcrowding of emergency departments (EDs) in hospitals. However, solutions targeting the increase of medical resources and improving patient needs are not practicable or feasible in the environment in Taiwan. Therefore, under the constraint of limited medical resources, EDs must optimize medical resources allocation to minimize the patient average length of stay (LOS) and medical resource wasted costs (MWCs). This study constructs a mathematical model for medical resource allocation of EDs, according to emergency flow or procedures. The proposed mathematical model is highly complex and difficult to solve because its performance value is stochastic and it considers both objectives simultaneously. Thus, this study postulates a multi-objective simulation optimization algorithm by integrating a non-dominated sorting genetic algorithm II (NSGA II) and multi-objective computing budget allocation (MOCBA), and constructs an ED simulation model to address the challenges of multi-objective medical resource allocation. Specifically, the NSGA II entails investigating plausible solutions for medical resource allocation, and the MOCBA involves identifying effective sets of feasible Pareto medical resource allocation solutions and effective allocation of simulation or computation budgets. Additionally, the discrete simulation model of EDs estimates the expected performance value. Furthermore, based on the concept of private cloud, this study presents a distributed simulation optimization framework to reduce simulation time and subsequently obtain simulation outcomes more rapidly. This framework assigns solutions to different virtual machines on separate computers to reduce simulation time, allowing rapid retrieval of simulation results and the collection of effective sets of optimal Pareto medical resource allocation solutions. Finally, this research constructs an ED simulation model based on the ED of a hospital in Taiwan, and determines the optimal ED resource allocation solution by using the simulation model and algorithm. The effectiveness and feasibility of this method are identified by conducting the experiment, and the experimental analysis proves that the proposed distributed simulation optimization framework can effectively reduce simulation time.
Chapter PDF
Similar content being viewed by others
Keywords
References
Ahmed, M.A., Alkhamis, T.M.: Simulation optimization for an ED healthcare unit in Kuwait. European Journal of Operational Research 198, 936–942 (2009)
Chen, C.H., Lee, L.H.: Stochastic simulation optimization: An Optimal Computing Budget Allocation. World Scientific Publishing Co. (2010)
Hoot, N.R., Aronsky, D.: Systematic Review of ED Crowding: Causes, Effects, and Solutions. Health Policy and Clinical Practice 52(2), 126–136 (2008)
Lee, L.H., Chew, E.P., Teng, S., Goldsman, D.: Finding the non-dominated Pareto set for multi-objective simulation models. IIE Transactions 42(9), 656–674 (2010)
Pitombeira Neto, A.R., Gonçalves Filho, E.V.: A simulation-based evolutionary multiobjective approach to manufacturing cell formation. Computers & Industrial Engineering 59, 64–74 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Chen, TL. (2014). Decision Support System Based on Distributed Simulation Optimization for Medical Resource Allocation in Emergency Department. In: Nah, F.FH. (eds) HCI in Business. HCIB 2014. Lecture Notes in Computer Science, vol 8527. Springer, Cham. https://doi.org/10.1007/978-3-319-07293-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-07293-7_2
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07292-0
Online ISBN: 978-3-319-07293-7
eBook Packages: Computer ScienceComputer Science (R0)