Admission Control of Multi-Level Emergency Patients with Time-Varying Demands

doi:10.16183/j.cnki.jsjtu.2021.122

Abstract

Abstract:

The Markov decision process (MDP) model is developed for the patient admission control problem and is extended based on the uniformization method to realize a real-time period-by-period decision process. The classical MDP iterative method is extended, and the two-way iteration algorithm and the two-way threshold iteration algorithm are proposed to solve the new model. Numerical experiments are conducted based on the data from the resuscitation room of a large hospital in Shanghai. The results show that the proposed method can improve the admission rate of critical patients and enhance the medical service level of the hospital compared with the existing decision method.

Key words: patient admission control, Markov decision process(MDP), uniformization method, time-varying demands

CLC Number:

TP13
R197.32

XU Jie, WANG Zixiang, LIU Yuxin, LIU Ran, YANG Zhitao. Admission Control of Multi-Level Emergency Patients with Time-Varying Demands[J]. Journal of Shanghai Jiao Tong University, 2022, 56(8): 1067-1077.

Figures/Tables 10

Fig.1

Fig.2

Tab.1

Tab.2

Tab.3

Tab.4

Tab.5

Fig.3

Tab.6

Fig.4

References 18

[1]	LEE H R, LEE T. Markov decision process model for patient admission decision at an emergency department under a surge demand[J]. Flexible Services and Manufacturing Journal, 2018, 30(1/2): 98-122. doi: 10.1007/s10696-017-9276-8 URL
[2]	万志远, 刘勤明, 叶春明, 等. 突发事件下的医院应急资源动态分配模型研究[J]. 计算机应用研究, 2020, 37(2): 456-459.
	WAN Zhiyuan, LIU Qinming, YE Chunming, et al. Research on hospital emergency resource dynamic allocation model under emergencies[J]. Application Research of Computers, 2020, 37(2): 456-459.
[3]	GEDIK R, ZHANG S F, RAINWATER C. Strategic level proton therapy patient admission planning: A Markov decision process modeling approach[J]. Health Care Management Science, 2017, 20(2): 286-302. doi: 10.1007/s10729-016-9354-6 URL
[4]	DAI J J, GENG N, XIE X L. Dynamic admission quota control with controllable and uncontrollable demands and random service time[J]. IEEE Transactions on Automatic Control, 2021, 66(6): 2925-2932. doi: 10.1109/TAC.2020.3014117 URL
[5]	BATISTA A, VERA J, POZO D. Multi-objective admission planning problem: A two-stage stochastic approach[J]. Health Care Management Science, 2020, 23(1): 51-65. doi: 10.1007/s10729-018-9464-4 URL
[6]	HULSHOF P J H, MES M R K, BOUCHERIE R J, et al. Patient admission planning using approximate dynamic programming[J]. Flexible Services and Manufacturing Journal, 2016, 28(1/2): 30-61. doi: 10.1007/s10696-015-9219-1 URL
[7]	DIAMANT A, MILNER J, QUERESHY F. Dynamic patient scheduling for multi-appointment health care programs[J]. Production and Operations Management, 2018, 27(1): 58-79. doi: 10.1111/poms.12783 URL
[8]	AYVAZ N, HUH W T. Allocation of hospital capacity to multiple types of patients[J]. Journal of Revenue and Pricing Management, 2010, 9(5): 386-398. doi: 10.1057/rpm.2010.30 URL
[9]	LI X J, LIU D C, GENG N, et al. Optimal ICU admission control with premature discharge[J]. IEEE Transactions on Automation Science and Engineering, 2019, 16(1): 148-164. doi: 10.1109/TASE.2018.2827664 URL
[10]	KIM S H, CHAN C W, OLIVARES M, et al. ICU admission control: An empirical study of capacity allocation and its implication for patient outcomes[J]. Management Science, 2015, 61(1): 19-38. doi: 10.1287/mnsc.2014.2057 URL
[11]	CHAN C W, FARIAS V F, BAMBOS N, et al. Optimizing intensive care unit discharge decisions with patient readmissions[J]. Operations Research, 2012, 60(6): 1323-1341. doi: 10.1287/opre.1120.1105 URL
[12]	AKHAVIZADEGAN F, ANSARIFAR J, JOLAI F. A novel approach to determine a tactical and operational decision for dynamic appointment scheduling at nuclear medical center[J]. Computers & Operations Research, 2017, 78: 267-277. doi: 10.1016/j.cor.2016.09.015 URL
[13]	HULSHOF P J H, BOUCHERIE R J, HANS E W, et al. Tactical resource allocation and elective patient admission planning in care processes[J]. Health Care Management Science, 2013, 16(2): 152-166. doi: 10.1007/s10729-012-9219-6 URL
[14]	梁峰, 徐苹. 基于MDP和动态规划的医疗检查预约调度优化方法研究[J]. 运筹与管理, 2020, 29(5): 17-25.
	LIANG Feng, XU Ping. Appointment scheduling of medical examination based on MDP and dynamic programming[J]. Operations Research and Management Science, 2020, 29(5): 17-25.
[15]	中华人民共和国卫生部. 急诊病人病情分级指导原则(征求意见稿)[J]. 中华危重症医学杂志(电子版), 2011, 4(4): 241-243.
	Ministry of Health of the People's Republic of China. Guidelines for grading the condition of emergency patients (draft for comments)[J]. Chinese Journal of Critical Care Medicine (Electronic Edition), 2011, 4(4): 241-243.
[16]	LIU R, XIE X L. Physician staffing for emergency departments with time-varying demand[J]. INFORMS Journal on Computing, 2018, 30(3): 588-607. doi: 10.1287/ijoc.2017.0799 URL
[17]	文静, 耿娜, Xiaolan Xie, 等. 基于仿真的急诊室动态调度研究[J]. 工业工程与管理, 2021, 26(3): 160-167.
	WEN Jing, GENG Na, XIAOLAN Xie, et al. Simulation study of dynamic scheduling for emergency department[J]. Industrial Engineering and Management, 2021, 26(3): 160-167.
[18]	PLATZMAN L K. Introduction to probability models[J]. Journal of Quality Technology, 1982, 14(4): 228-229.

参数	取值
N	3
T	6
Δ	1
μ⁰, μ¹	0.4, 0.63

算例	双向迭代算法总收益	枚举总收益
1	58.565	58.565
2	30.453	30.453
3	134.397	134.397
4	106.729	106.729
5	64.915	64.915
6	35.923	35.923
7	143.311	143.311
8	114.536	114.536

参数	取值
N	30
T	24
Δ	1
μ⁰, μ¹	0.1, 0.333
r⁰, r¹	20, 3
p⁰, p¹	-30,-1

策略	均匀化评估总收益	仿真评估总收益	收益提升/%	算法运行时间/s
K0	1023.18	1023.38	-	-
K1	1094.26	1094.58	6.96	15481
K2	1093.97	1094.14	6.91	706
K3	1057.48	1057.16	3.30	691

K0				K1				K2				K3
Y	Y₀	Y₁		Y	Y₀	Y₁		Y	Y₀	Y₁		Y	Y₀	Y₁
0.956	0.956	0.956		0.912	0.991	0.842		0.913	0.991	0.845		0.886	0.981	0.798