摘要
Abstract
Objective The allocation of surgical resources is very complex,taking into account factors such as patients,operating rooms,doctors and time,etc.Traditional scheduling methods are often difficult to cope with emergencies,and at the same time,they are easy to be trapped in the local optimal solution,which cannot realize the optimal and reasonable allocation of resources.This paper proposes a novel and intelligent surgical scheduling method in order to arrange medical resources scientifically and reasonably.Methods Firstly,a mathematical model is established with the objective of minimizing the completion time of all surgeries,then the surgical scheduling problem is solved based on the genetic algorithm(GA),and at the same time,the genetic algorithm is improved by using the double tangent point crossover method and the reversed mutation method,and finally,the improved genetic algorithm(IGA)is simulated and compared with the traditional genetic algorithm and particle swarm optimization(PSO)on MATLAB.Results The IGA has the least number of iterations to obtain the optimal solution in the simulation,which is 149 times,while the traditional GA and the PSO have the optimal solution with 895 and 990 times,moreover,the total duration of the surgery obtained by the IGA is the shortest,which is 562.3 minutes,while that obtained by the traditional genetic algorithm and the PSO are 604.7 and 672.1 minutes.In conclusion,the performance of the proposed algorithm IGA is significantly better than the traditional GA and PSO.Conclusions The improved genetic algorithm can be applied to solve the complex problem of hospital surgical scheduling,taking into account the factors of patients,operating rooms,doctors and time,and breaking the limitations of the traditional scheduling method,which is a method that meets the practical needs.Surgical scheduling based on this method can arrange medical resources more scientifically and reasonably,and improve work efficiency and patient satisfaction.关键词
手术排班/医院管理/遗传算法/粒子群算法/决策Key words
operation scheduling/hospital management/genetic algorithm/particle swarm optimization/decision分类
医药卫生
