[1]张越,王子翔,周博,等.基于机器学习的线上线下联合服务模式下医生排班算法[J].智能系统学报,2025,20(4):800-812.[doi:10.11992/tis.202404032]
ZHANG Yue,WANG Zixiang,ZHOU Bo,et al.Algorithms for physician scheduling under the online and offline combined service mode based on machine learning[J].CAAI Transactions on Intelligent Systems,2025,20(4):800-812.[doi:10.11992/tis.202404032]
点击复制
ZHANG Yue,WANG Zixiang,ZHOU Bo,et al.Algorithms for physician scheduling under the online and offline combined service mode based on machine learning[J].CAAI Transactions on Intelligent Systems,2025,20(4):800-812.[doi:10.11992/tis.202404032]
基于机器学习的线上线下联合服务模式下医生排班算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第4期
页码:
800-812
栏目:
学术论文—机器学习
出版日期:
2025-08-05
- Title:
- Algorithms for physician scheduling under the online and offline combined service mode based on machine learning
- Keywords:
- telemedicine; physician scheduling; time-varying queueing system; data-driven; deep learning; Markov decision process; approximate dynamic programming; heuristic
- 分类号:
- TP18
- 文献标志码:
- 2025-2-21
- 摘要:
- 线上线下联合的医疗服务模式已经成为我国大型医院普遍采用的新型医疗服务模式，为了优化大型医院在此类模式下的医生资源配置，本文研究考虑切换成本的医生排班问题。针对此问题，建立考虑服务水平限制的医生排班马尔可夫决策过程模型，并设计近似动态规划算法对马尔可夫决策过程高效求解。进一步，考虑患者高度时变到达以及医疗服务时长等多维不确定性，基于合作医院的实际数据，构建数据驱动的循环神经网络模型，提出基于数据驱动的线上线下患者排队系统的性能评估方法。数值实验显示，所提出的方法能够降低医生总工作时长，并有效控制患者等待时间，保证系统的高效运行。本文研究结果可为大型医院合理配置线上线下医疗资源提供理论依据和决策支持。
- Abstract:
- The online and offline combined medical service mode has become a new medical service mode generally adopted by large hospitals in China. Under this mode, large hospitals need to allocate physicians to online and offline services, and arrange online and offline scheduling plans for physicians while considering the switching of physicians between the two services. To address this problem, a Markov decision process model for physician scheduling with service level constraints was developed and an approximate dynamic programming algorithm was designed to solve the Markov decision process with high efficiency. Furthermore, considering multi-dimensional uncertainties such as highly time-varying patient arrival and service hours, a data-driven recurrent neural network was constructed based on the real-life data of the cooperative hospital as a performance evaluation method for the online and offline queueing systems. Numerical experiments show that the proposed methods can reduce the total working hours of physicians, effectively control the waiting time of patients, and ensure the high-efficiency operation of the system.
- 参考文献/References:
-
[1] 于保荣, 杨瑾, 宫习飞, 等. 中国互联网医疗的发展历程、商业模式及宏观影响因素[J]. 山东大学学报(医学版), 2019, 57(8): 39-52.
YU Baorong, YANG Jin, GONG Xifei, et al. Development process, business modes and macrocally influencing factors for Internet-based health service in China[J]. Journal of Shandong University (Health Sciences), 2019, 57(8): 39-52.
[2] 初佃辉, 吴军, 刘志中, 等. 智能化医养融合服务平台关键技术及应用研究[J]. 智能系统学报, 2021, 16(5): 972-988.
CHU Dianhui, WU Jun, LIU Zhizhong, et al. Research on key technologies and applications of intelligent medical and care integration service platform[J]. CAAI transactions on intelligent systems, 2021, 16(5): 972-988.
[3] LUO Jun, ZHANG Jiheng. Staffing and control of instant messaging contact centers[J]. Operations research, 2013, 61(2): 328-343.
[4] RAJAN B, TEZCAN T, SEIDMANN A. Service systems with heterogeneous customers: investigating the effect of telemedicine on chronic care[J]. Management science, 2019, 65(3): 1236-1267.
[5] 国家互联网信息办公室. 数字中国发展报告(2022年)[EB/OL]. (2023-05-23)[2024-04-02]. https://www.cac.gov.cn/2023-05/22/c_1686402318492248.htm.
Cyberspace Administration of China.Digital China development report(2022)[EB/OL]. (2023-05-23)[2024-04-02]. https://www.cac.gov.cn/2023-05/22/c_1686402318492248.htm.
[6] ZHOU Cuihua, HAO Yifei, LAN Yanfei, et al. To introduce or not? strategic analysis of hospital operations with telemedicine[J]. European journal of operational research, 2023, 304(1): 292-307.
[7] 罗利, 付颖, 徐雪茹, 等. 多方参与的互联网医院运营管理研究综述[J]. 工业工程与管理, 2024, 29(4): 205-222.
LUO Li, FU Ying, XU Xueru, et al. The operation management of multi-participant internet hospital: a framework and review[J]. Industrial engineering and management, 2024, 29(4): 205-222.
[8] ERHARD M, SCHOENFELDER J, FüGENER A, et al. State of the art in physician scheduling[J]. European journal of operational research, 2018, 265(1): 1-18.
[9] YOUN S, GEISMAR H N, PINEDO M. Planning and scheduling in healthcare for better care coordination: current understanding, trending topics, and future opportunities[J]. Production and operations management, 2022, 31(12): 4407-4423.
[10] BRUNNER J O, BARD J F, KOLISCH R. Midterm scheduling of physicians with flexible shifts using branch and price[J]. IIE transactions, 2010, 43(2): 84-109.
[11] STOLLETZ R, BRUNNER J O. Fair optimization of fortnightly physician schedules with flexible shifts[J]. European journal of operational research, 2012, 219(3): 622-629.
[12] WANG Zixiang, LIU Ran, SUN Zhankun. Physician scheduling for emergency departments under time-varying demand and patient return[J]. IEEE transactions on automation science and engineering, 2023, 20(1): 553-570.
[13] SINREICH D, JABALI O, DELLAERT N P. Reducing emergency department waiting times by adjusting work shifts considering patient visits to multiple care providers[J]. IIE transactions, 2012, 44(3): 163-180.
[14] LIU Ran, XIE Xiaolan. Physician staffing for emergency departments with time-varying demand[J]. INFORMS journal on computing, 2018, 30(3): 588-607.
[15] ZAERPOUR F, BIJVANK M, OUYANG Huiyin, et al. Scheduling of physicians with time-varying productivity levels in emergency departments[J]. Production and operations management, 2022, 31(2): 645-667.
[16] 祖漫漫. 门诊医生排班问题研究[D]. 大连: 大连理工大学, 2019.
ZU Manman. Study on outpatient doctors’ scheduling problem[D]. Dalian: Dalian University of Technology, 2019.
[17] 王铖恺, 范晓宇, 徐捷, 等. 结合Benders分解和列生成的发热门诊排班数学建模和优化算法[J]. 系统管理学报, 2023, 32(3): 476-487.
WANG Chengkai, FAN Xiaoyu, XU Jie, et al. Mathematical modeling and optimization algorithm for fever clinics scheduling combining benders decomposition and column generation[J]. Journal of systems & management, 2023, 32(3): 476-487.
[18] 兰绍雯. 门诊医生资源协同优化问题研究[D]. 合肥: 合肥工业大学, 2022.
LAN Shaowen. Research on collaborative optimization of outpatient doctor resources[D]. Hefei: Hefei University of Technology, 2022.
[19] PRAKASH A M, ZHONG Xiang. Queueing information management of primary care delivery with E-visits[J]. IEEE transactions on automation science and engineering, 2022, 19(2): 632-645.
[20] ?AK?C? ? E, MILLS A F. On the role of teletriage in healthcare demand management[J]. Manufacturing & service operations management, 2021, 23(6): 1483-1504.
[21] 姜劲, 白闪闪, 王云婷, 等. 线上和线下医疗服务质量对患者线下就医决策的影响[J]. 管理科学, 2020, 33(1): 46-53.
JIANG Jin, BAI Shanshan, WANG Yunting, et al. Influence of online and offline medical service quality on patients’ offline medical decision-making[J]. Journal of management science, 2020, 33(1): 46-53.
[22] HOSSAIN I S, AKHAND M A H, SHUVO M I R, et al. Optimization of university course scheduling problem using particle swarm optimization with selective search[J]. Expert systems with applications, 2019, 127: 9-24.
[23] 宋婷, 陈矛, 吴超, 等. 基于多类迭代局部搜索的自动化排课算法[J]. 计算机应用, 2019, 39(6): 1760-1765.
SONG Ting, CHEN Mao, WU Chao, et al. Automated course arrangement algorithm based on multi-class iterated local search[J]. Journal of computer applications, 2019, 39(6): 1760-1765.
[24] GUPTA V, ZHANG Jiheng. Approximations and optimal control for state-dependent limited processor sharing queues[J]. Stochastic systems, 2022, 12(2): 205-225.
[25] CUI L, TEZCAN T. Approximations for chat service systems using many-server diffusion limits[J]. Mathematics of operations research, 2016, 41(3): 775-807.
[26] POWELL W B. Approximate dynamic programming: Solving the curses of dimensionality[M]. New York: John Wiley & Sons, 2007.
[27] POWELL W B. Perspectives of approximate dynamic programming[J]. Annals of operations research, 2016, 241(1): 319-356.
[28] LIU Derong, XUE Shan, ZHAO Bo, et al. Adaptive dynamic programming for control: a survey and recent advances[J]. IEEE transactions on systems, man, and cybernetics: systems, 2021, 51(1): 142-160.
[29] BURKE E K, BYKOV Y. The late acceptance hill-climbing heuristic[J]. European journal of operational research, 2017, 258(1): 70-78.
[30] YU Yong, SI Xiaosheng, HU Changhua, et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural computation, 2019, 31(7): 1235-1270.
[31] 张驰, 郭媛, 黎明. 人工神经网络模型发展及应用综述[J]. 计算机工程与应用, 2021, 57(11): 57-69.
ZHANG Chi, GUO Yuan, LI Ming. Review of development and application of artificial neural network models[J]. Computer engineering and applications, 2021, 57(11): 57-69.
[32] 李倩玉, 王蓓, 金晶, 等. 基于双向LSTM卷积网络与注意力机制的自动睡眠分期模型[J]. 智能系统学报, 2022, 17(3): 523-530.
LI Qianyu, WANG Bei, JIN Jing, et al. Automatic sleep staging model based on the bi-directional LSTM convolutional network and attention mechanism[J]. CAAI transactions on intelligent systems, 2022, 17(3): 523-530.
[33] 常明煜, 田乐, 郭茂祖. 基于HHT-LSTM的冬奥会临时设施运行趋势预测方法研究[J]. 智能系统学报, 2024, 19(1): 228-237.
CHANG Mingyu, TIAN Le, GUO Maozu. Research on the HHT-LSTM-based operation trend prediction method of temporary facilities for the Winter Olympic Games[J]. CAAI transactions on intelligent systems, 2024, 19(1): 228-237.
[34] XAVIER á S, QIU Feng, AHMED S. Learning to solve large-scale security-constrained unit commitment problems[J]. INFORMS journal on computing, 2021, 33(2): 739-756.
[35] WANG Zixiang, LIU Ran. Managing appointments of outpatients considering the presence of emergency patients: the combination of the analytical and data-driven approach[J]. International journal of production research, 2022, 60(13): 4214-4228.
备注/Memo
收稿日期:2024-4-24。
基金项目:国家自然科学基金项目（72371161）；上海申康医院发展中心管理研究项目（2024SKMR-19）；上海交通大学中国医院发展研究院研究项目（CHDI-2024-A-04）.
作者简介:张越，硕士研究生，主要研究方向为基于机器学习与人工智能的服务系统优化。E-mail：caesar8310@sjtu.edu.cn。;王子翔，讲师，博士，主要研究方向为服务系统建模优化和基于数据驱动的医疗系统运作管理。E-mail：zixiang_wang@hznu.edu.cn。;刘冉，副教授，博士生导师，主要研究方向为生产与服务系统运作管理，发表学术论文60余篇。E-mail：liuran2009@sjtu.edu.cn。
通讯作者:刘冉. E-mail：liuran2009@sjtu.edu.cn
更新日期/Last Update:
1900-01-01