基于LSTM-GA混合模型的患者预约排队策略优化

doi:10.12005/orms.2022.0072

运筹与管理 ›› 2022, Vol. 31 ›› Issue (3): 17-23.DOI: 10.12005/orms.2022.0072

基于LSTM-GA混合模型的患者预约排队策略优化

魏若楠¹, 江驹¹, 徐海燕²

1.南京航空航天大学自动化学院,江苏南京 211106;
2.南京航空航天大学经济与管理学院,江苏南京 211106

收稿日期:2020-11-02 出版日期:2022-03-25 发布日期:2022-04-12
通讯作者: 江驹(1963-),男,江苏扬州人,教授,博士,研究方向:智能控制与优化。
作者简介:魏若楠(1996-),女,重庆人,硕士研究生,研究方向:智能优化;徐海燕(1963-),女,江苏扬州人,教授,博士,研究方向:冲突决策分析与优化。
基金资助:
国家自然科学基金资助项目(71971115,61673209,71471087);南京航空航天大学基本业务费(NG2020004);南京航空航天大学基本业务费培育基金(NG2020004)

Optimization of Patient Reservation Queuing Policy Based on LSTM-GA Hybrid Model

WEI Ruo-nan¹, JIANG Ju¹, XU Hai-yan²

1. School of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. School of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China

Received:2020-11-02 Online:2022-03-25 Published:2022-04-12

摘要/Abstract

摘要： 在医疗运作管理领域,合理的资源分配能够帮助更多的患者尽早就医,降低患者病情恶化和死亡的风险。本文设计了预约排队策略对患者占有资源的顺序进行分配,建立了基于长短时记忆(Long Short Term-Memory, LSTM)神经网络和遗传算法(Genetic Algorithm, GA)的混合模型以优化排队策略。首先利用大数据和深度学习分析患者到达和医院服务情况,建立LSTM神经网络学习数据特征并预测未来数据,相比于排队论常用的随机分布方法取得了更好的效果.其次设计了基于排队系统仿真的排队策略优化算法,利用改进GA得到最优排队策略。实证研究表明,文本的方法可以明显降低患者的等待时间,最高可达59%。最后对排队策略进行敏感性分析,结果表明排队策略有效作用于仿真的各个时段。

关键词: 系统优化, 运作管理, 排队策略, 遗传算法, 长短时记忆神经网络

Abstract: In the field of medical operation and management, a reasonable allocation of resources is conducive to more patients to seek medical treatment as soon as possible and reduce the risk of patients' disease deterioration and death. Reservation queuing policy is designed to allocate the order of patients' occupying resources. A hybrid model based on long Short Term Memory(LSTM)neural network and genetic algorithm(GA)is established to optimize the queuing policy. First, big data and deep learning are used to analyze patient arrival and hospital service, and LSTM neural network is established to learn data features and predict future data. Compared with the random distribution method commonly used in queuing theory, it has achieved better results. Secondly, a queuing policy optimization algorithm based on queuing system simulation is designed to obtain the optimal queuing policy by using improved GA. The empirical studies show that the method of text can significantly reduce the patient's waiting time, which lowers the target function by 59%. Finally, the sensitivity of the queuing policy is analyzed, and the results show that the queuing policy is effective in each period of the simulation.

Key words: system optimization, operation management, queuing strategy, genetic algorithm, long short-term memory neural network

中图分类号:

TP391.9

魏若楠, 江驹, 徐海燕. 基于LSTM-GA混合模型的患者预约排队策略优化[J]. 运筹与管理, 2022, 31(3): 17-23.

WEI Ruo-nan, JIANG Ju, XU Hai-yan. Optimization of Patient Reservation Queuing Policy Based on LSTM-GA Hybrid Model[J]. Operations Research and Management Science, 2022, 31(3): 17-23.

参考文献

[1] 余幸.大医院“检查排队”考验“分级诊疗”制度[N].经济日报,2019-03-29(012).
[2] Chakraborty S, Muthuraman K, Lawley M. Sequential clinical scheduling with patient no-shows and general service time distributions [J]. IIE Transactions, 2010, 42(5): 354-366.
[3] 郑宇飞.让急诊姓“急”不能止于分级[N].北京日报,2019-04-26(007).
[4] 卢林发,牛瑛.一种优化的预约排队算法分析及实现[J].现代医院,2009,9(11):92-96.
[5] 刘鹏.改进加权补偿优先双轮询调度算法在医院预约分诊排队管理中的应用[J].中国数字医学,2017,12(3):70-72.
[6] Wang G L. Revenue management for a primary-care clinic in the presence of patient choice[J]. Operations Research, 2008, 56(3): 576-592.
[7] He Q M, Xie J, Zhao X. Priority queue with customer upgrades[J]. Naval Research Logistics, 2012, 59(5): 362-375.
[8] Jiang Y. Data-driven analytics to support scheduling of multi-priority multi-class patients with wait targets[D]. Waterloo University, 2016.
[9] Kopach R, Delaurentis P C, Lawley M, et al. Effects of clinical characteristics on successful open access scheduling[J]. Health Care Management Science, 2007, 10(2): 111-124.
[10] Crowther M J, Riley R D, Staessen J A, et al. Individual patient data meta-analysis of survival data using poisson regression models[J]. BMC Medical Research Methodology, 2012, 12(1): 34.
[11] 任宗伟,郭海妮.考虑患者回诊情况下的门诊科室调度优化[J].运筹与管理,2018,27(04):39-49.
[12] Bockstal E V, Maenhout B. A study on the impact of prioritising emergency department arrivals on the patient waiting time[J]. Health Care Management Science, 2018: 1-26.
[13] 周杰,李军,郭鹏,余玅妙.急诊非强占优先权下Geom/NB/1排队系统常规病人等待时间及损失率[J].系统工程理论与实践,2016,36(8):2135-2143.
[14] 章顺悦,杨扬,吴家利,等.排队论G/Ek/c模型及其在医院眼科专家门诊中的应用[J].中国卫生统计,2012,29(4):484-486,489.
[15] Lv Y, Duan Y, Kang W, et al. Traffic flow prediction with big data: a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 865-873.
[16] Chen H, Canizares C A, Singh A. ANN-based short-term load forecasting in electricity markets[C]. Power Engineering Society Winter Meeting. IEEE, 2001. 411-415.
[17] Shi H, Xu M H, Li R. Deep learning for household koad forecasting-a novel pooling deep RNN[J]. IEEE Transactions on Smart Grid, 2018, 9(5): 5271-5280.
[18] Yin Z, Zhu J, Zhang X. Forecast customer flow using long short-term memory networks[C]. 2017 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC). IEEE, 2018. 61-66.
[19] Chen Y, Li X, Miao M, et al. Multi-objective and hierarchical optimization of power collection system for photovoltaic power plants based on the multi-elite co-evolutionary partheno-genetic algorithm[J]. Power System Protection & Control, 2016, 44(12): 29-35.
[20] Yang Y, Dong J, Sun X, et al. A CFCC-LSTM model for sea surface temperature prediction[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 15(2): 1-5.
[21] 陆坚毅,杨超,揭婉晨.考虑绕行特征的电动汽车快速充电站选址问题及自适应遗传算法[J].运筹与管理,2017,26(01):8-17.
[22] Liao G C, Tsao T P. Application of a fuzzy neural network combined with a chaos genetic algorithm and simulated annealing to short-term load forecasting[J]. IEEE Transactions on Evolutionary Computation, 2006, 10(3): 330-340.
[23] Zhao X C. Simulated annealing algorithm with adaptive neighborhood[J]. Applied Soft Computing, 2011, 11(2): 1827-1836.
[24] 张凌波,宰娜,顾幸生.基于改进教学算法优化BP神经网络的催化剂碳含量预测模型[J].控制与决策,2016,31(9):1723-1728.
[25] Mohamed A, Dahl G E, Hinton G. Acoustic modeling using deep belief networks[J]. IEEE Transactions on Audio, Speech and Language Processing, 2012, 20(1): 14-22.

基于LSTM-GA混合模型的患者预约排队策略优化

Optimization of Patient Reservation Queuing Policy Based on LSTM-GA Hybrid Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张帝, 梅子翘, 陈峰, 赵一飞. 汽车滚装码头泊位调度优化模型与算法研究[J]. 运筹与管理, 2022, 31(3): 9-16.
[2]	邰世文, 商剑平, 饶卫振. 煤炭码头船货匹配下泊位动态分配多目标优化模型及算法[J]. 运筹与管理, 2022, 31(1): 14-21.
[3]	范厚明, 徐振林, 李阳, 杨翔. 开放式多中心需求可拆分VRP及混沌遗传模拟退火算法[J]. 运筹与管理, 2022, 31(1): 92-98.
[4]	刘琴, 申海, 黎建强. 基于部件指派的多状态系统可靠度优化研究[J]. 运筹与管理, 2021, 30(9): 25-30.
[5]	郑红星, 段爽, 孙丛. 考虑翻箱的场桥调度和提箱集卡数量的集成优化[J]. 运筹与管理, 2021, 30(9): 48-55.
[6]	闫妍, 张锦, 唐秋宇, 张洪基. 航线联盟下航空货运网络枢纽点选址问题研究[J]. 运筹与管理, 2021, 30(9): 64-72.
[7]	初良勇, 左世萍, 阮志毅. 考虑退货不确定性的多层次多站点逆向物流网络选址优化研究[J]. 运筹与管理, 2021, 30(9): 73-79.
[8]	丁肇炜, 杨建华, 王艾, 王欣. 面向突发事件的安保巡逻选址-路径优化研究[J]. 运筹与管理, 2021, 30(8): 1-6.
[9]	王愚勤, 胡卉, 刘富鑫, 王艳慧, 赵姣, 韩毅. 智能网联下无人车配送路径优化[J]. 运筹与管理, 2021, 30(8): 52-58.
[10]	刘畅, 姚建明. 高铁场景下的无人零售终端补货供应链调度优化研究[J]. 运筹与管理, 2021, 30(7): 9-15.
[11]	李建斌, 梅启煌, 张蕊, 戴宾. 运单体积不确定对货运共享平台定价决策的影响研究[J]. 运筹与管理, 2021, 30(4): 69-75.
[12]	周丽, 杨江龙. 基于遗传算法的多通道密集式移动货架订单拣选研究[J]. 运筹与管理, 2021, 30(2): 84-90.
[13]	刘国山, 王敏, 张转霞. 基于时间窗延迟的资源约束项目调度双层优化研究[J]. 运筹与管理, 2021, 30(12): 6-12.
[14]	吕海利, 孙佳祺, 吴姝. 考虑机器能耗的绿色作业车间调度问题[J]. 运筹与管理, 2021, 30(12): 220-225.
[15]	徐小峰, 孙玉萍, 林姿汝. 缺货情形下轴辐式库存的纵横向协作调拨[J]. 运筹与管理, 2021, 30(10): 113-119.