Simulation Optimization and Efficiency Evaluation of Resource in Healthcare Application


Student thesis: Doctoral Thesis

View graph of relations


  • Hainan GUO


Awarding Institution
Award date2 Dec 2016


Emergency Departments (EDs) play a critical role in the healthcare system. ED patients often visit with various life-threatening conditions that demand instant and efficient medical system performance. Improving EDs operational efficiency by reducing ED overcrowding has become the most urgent issue for healthcare managers. Moreover, due to the limited government financial support, it is important to help ED managers to achieve their goals without adding additional human resource.

Medical staff configuration problem of ED is particularly important in Hong Kong (HK). On one hand, HK government has set up a series of strict requirements on the service quality to evaluate the performance of ED systems. On the other hand, labor cost is always an important issue for EDs in HK. In view of these two factors, given the service requirements by HK government, it is imperative for the hospital managers to develop medical staff configuration in a cost-and-time-effective way. Since EDs are extremely complex systems, analytical formulations and solutions for ED models are typically intractable. So in recent years, integrating simulation and optimization as an analytical aid to decision makers of resource allocation and utilization is growing in acceptance and importance.

However, simulation models of ED are often built based on incomplete data, for example, missing arrival times or service-time durations. The difficulty in collecting reliable and complete data can subsequently lead to invalid simulation results. To tackle this problem, in Chapter 3, we propose a simulation and optimization method to characterize the durations of service times when the process duration data are not available. Since many services in an ED are sequential and dependent on each other, this chapter considers these multiple process steps cooperatively. We first use lognormal distributions to characterize the key service durations (i.e., registration, triage, consultations, and reassessment). Then we propose a new meta-heuristic approach, which combines an Improved Adaptive Genetic Algorithm (AGA) and Simulated Annealing (SA), IAGASA, to search for the optimal set of service time distribution parameters. To address the difficulties of applying IAGASA when noise is involved in the performance measures and to improve simulation efficiency, we jointly apply IAGASA and Optimal Computing Budget Allocation (OCBA) technology. OCBA helps to minimize the total simulation cost for achieving a desired level of probability of correctly selecting the best set of distribution parameters. By integrating the proposed budget allocation rule, the search efficiency significantly improves. The experimental results indicate that our proposed method can find accurate estimates of service time distribution parameters within a relatively short time.

Based on the valid simulation model developed by Chapter 3, in Chapter 4, we formulate the ED problem in HK as a constrained simulation optimization problem, which aims to find the optimal configuration of the medical staff that minimizes the total labor cost while fulfilling the service quality requirements (stochastic constraints) specified by the government. To solve this issue, we propose a highly efficient search method, called random boundary generation with feasibility detection (RBG-FD). The random boundary generation (RBG) is applied to efficiently identify good-quality solutions based on the objective value. The feasibility detection (FD) procedure is used to retain the probability of correct feasibility detection of each sampled solution at the desired level, which intrinsically allocates a reasonable number of simulation replications. By using these two techniques, the efficiency of finding the optimal staff configuration can be significantly improved. A case study is performed in a public hospital in HK. By testing different patient arrival rates and service constraints, the numerical results indicate significantly higher practicability and efficiency of the proposed method.

Hospital Authority (HA) is a statutory body managing all the public hospitals in HK. In Chapter 5, we propose a two-phase method to help HKHA decision makers to control healthcare costs and improve healthcare efficiency under required service quality. Particularly, in Phase I, based on the panel data of HA hospitals from 2000 to 2013, we integrate a new data envelopment analysis (DEA) model and Malmquist productivity change index to prove that the HA indeed exist problems of unfair resource allocation, and bring forth HA managers many suggestions to increase its efficiency. In Phase II, we further explore the impact of some exogenous factors (e.g., population density) on HKHA efficiency by means of the Tobit regression model. The empirical results reveal an interesting phenomenon that the public hospital serving in a richer district has a relatively lower efficiency, which partially reflects the reality in HK that people with higher economic condition prefer accepting higher quality service from the private hospitals.