Hospital Emergency Department Layout Using Multi-objective Evolutionary Algorithm

With the rapid development of science and technology and high-speed progress of the society in recent years,medical industry occupies an increasingly important role in people's lives,and more comfortable and effective medical experience are becoming the major goal of the hospitals.Emergency department is an important section of hospital,patients in it often have serious and emergency conditions,and the amount of the patients are also huge.Therefore,enhancing the quality and experience of emergency medical service has important significance for patients and hospitals.There are a variety of ways to enhance the quality of medical services.In this paper,we will improve the quality of medical services by optimizing the layout of the emergency department,making departments layout more reasonable,thus reduce patients' travel time,increase the efficiency of health care workers and improve the quality of hospital services.The purpose of hospital emergency department is to optimize the layout of the original layout by certain methods.This not only need to take into account the factor of patient flow,but also need to consider the closeness of the departments and rearrangement cost.Therefore,in order to solve the layout problem,three objectives are simultaneously optimized,namely patient flow cost,the closeness of the departments and rearrangement cost.In this paper,the work focus on the three tasks are as below.(1)In this paper,the emergency department layout problem is both discrete and continuous,and a multi-objective optimization algorithm--MOEA/D is used to solve the problem.MOEA/D uses mathematical programming to decompose a multi objective problem into multiple single objective sub-problems,and then uses evolutionary algorithm to optimize these sub-problems simultaneously to optimize the whole miulti-objective problem.The algorithm combines the problem constraints can deal with the constrained multi-objective optimization problem.(2)When comes to the design of MOEA/D,coding and genetic operators are needed.Therefore,according to the actual problem,the method of integer coding and real coding will be involved in the layout of the emergency department and corridors coding,partial mapped crossover(PMX)and swap mutation methods are used as the department genetic operator,and arithmetic crossover and mutation step method are used as the aisle genetic operator.(3)There are constraint conditions in the emergency department layout problem,thus,a penalty function is used and applied to the MOEA/D algorithm to handle constraint conditions.In order to control the population size,a crowding distance computation is used to exclude those crowding individuals from external population.(4)In order to test the effectiveness of the MOEA/D algorithm,the local search algorithm LS is used in this paper to solve the layout problem of the emergency department,and the results of the two algorithms are compared.(5)In order to further verify the effectiveness of the algorithm,this paper uses Medmodel simulation software to simulate the original layout and optimized layout.Medmodel is a simulation software specifically used in medical system,in the simulation system,clinics or workstation are seen as locations,the medical processes are running between these locations.The simulation results showed that the optimized layout has indeed upgraded than the original layout.In this paper,experiments show that compared with the original department layout,the approach can effectively solve the problem of hospital emergency department layout.Patients' moving time and the time to see the doctor are decreased in the optimized layout,and the quality of hospital services is improved.