How can decision makers be supported in the improvement of an emergency? A simulation optimization and data mining approach | www.esteco.com

How can decision makers be supported in the improvement of an emergency? A simulation optimization and data mining approach

Author(s): 
Ainhoa Goienetxea Uriarte, Enrique Ruiz Zúñiga, Matías Urenda Moris, Amos H.C. Ng (University of Skövde)

CHALLENGE - In the case of healthcare organizations, the improvement efforts, and therefore the decisions, are focused on a system that aims to offer high-quality care, provide good service times and still be resource efficient. However, designing and operating these systems, especially emergency departments (EDs), is extremely complex, mainly due to: the high number of different resources involved in the activities of providing care, the uncertainty resulting from these activities occurring at different moments and the distinct probability of simultaneously needing resources.

SOLUTION - This paper presents a novel approach in healthcare in which Discrete Event Simulation, Simulation-Based Multi-Objective Optimization and Data Mining techniques are used in combination. This methodology has been applied for a system improvement analysis in a Swedish emergency department. The objective of the optimization was to find an optimal configuration of the Emergency Department (ED) which can achieve the Time to first Meeting with the Doctor (TMD) and Length Of Stay (LOS) levels, defined by the National Board of Health and Welfare (SoS), for all patient categories (medicine, surgery, orthopedics and pediatrics). Three additional objectives were also included, in order to drive the optimization towards resource effective solutions:

  • Minimize the number of reductions of the different process times (RET ): physicians’ administrative tasks (REa), response time for laboratory results (REl) and response time for X-ray results (REx)
  • Minimize the total number of physicians (DT ): the adding up of medicine (Dm), surgery (Ds), orthopedics (Dr ) and pediatrics (Dc ) physicians.
  • Minimize the number of beds (BT ): medicine–pediatrics (Bm) and surgery–orthopedics (Bs) beds.

modeFRONTIER, a commercial software for multi-objective analysis, was combined with FlexSim HC, in order to run the optimization and analyze the results. The chosen optimization algorithm is the NSGA-II, a well-known, efficient multi-objective algorithm that has been proven suitable for this optimization problem. A data mining exercise was performed on the basis of visualization techniques and statistics, in order to gain some insight about the optimization results. As a first step in the process, unfeasible and duplicated solutions were removed from the analysis. Each point in the Scatter 3D charts, presented in Figures 14 and 15, represents a possible configuration of the ED. In each 3D chart, the Pareto-optimal solutions, with respect to three optimization objectives are highlighted as blue stars. They constitute the Pareto front which is the set of optimal solutions for the different combinations of personnel, resources and process times which fulfill the defined conflicting objectives.

BENEFITS - The combined benefits of the use of simulation, multi-objective optimization and data mining offer the decision makers the opportunity to take decisions based on a set of optimal solutions. As a result of the project, the decision makers were provided with a range of nearly optimal solutions and design rules which reduce considerably the length of stay and waiting times for emergency department patients.

LOG IN TO DOWNLOAD