Keywords
Multi-objective programming
Clinical pathway
DIP payment
Stroke
Submitted : 2025-04-07
Accepted : 2025-04-22
Published : 2025-05-07
Abstract
Objective: Aiming at the problems of clinical pathway optimization and medical cost control for stroke patients, this study proposes a clinical pathway discrimination model based on the XGBoost integrated learning algorithm. Combined with the multi-objective programming (MOP) method, this study explores its application value under the Diagnosis-Intervention Packet (DIP) payment model. Methods: The data of stroke patients (ICD codes I60–I63) from 2018 to 2022 were obtained through the medical record statistical management system of medical institutions in Guangdong Province. Efficiency indicators (average length of hospital stay), health economics indicators (total cost), effectiveness indicators (mortality rate), and specific indicators (NIHSS score) were extracted. The XGBoost algorithm was used to construct the clinical pathway discrimination model, and the hyperparameters were optimized through grid search. Based on the DIP payment rules, the prediction results of the model were used as inputs to establish a dynamic programming model, aiming to minimize costs and maximize curative effects to obtain the optimal clinical pathway plan. Results: The goodness-of-fit (R 2) of the XGBoost model on the test set reached 0.768, which was significantly better than that of the random forest (0.691) and the BP neural network (0.343). The total cost of the clinical pathway optimized by the dynamic programming model decreased by 12.7% (95% CI: 10.2–15.1%), the average length of hospital stay was shortened by 1.8 days, and the NIHSS improvement rate increased by 8.3%. Conclusion: The integrated model proposed in this study has high accuracy and robustness in clinical pathway discrimination. Combined with the MOP method, it can provide a scientific basis for the optimization of medical resources under the DIP model, helping medical institutions achieve the dual goals of precise cost control and curative effect improvement.
References
Chinese Multidisciplinary Expert Consensus on Stroke Condition Monitoring. National Medical Journal of China, 2021, 101(5): 317–326.
Tang D, Ding J, Chen Y, et al., 2021, Research on the Co-promotion Mechanism of Medical Insurance Payment Standards and DRG/DIP Payments. China Health Insurance, 2021(3): 38–42.
Li L, 2014, Research on the Hospitalization Costs of Stroke Patients in Tertiary Medical Institutions in Tianjin, thesis, Tianjin Medical University.
Wang J, 2017, Research on the Disease Economic Burden and Influencing Factors of Stroke Patients in Henan Province, thesis, Zhengzhou University.
Zhou H, 2016, Study on Influencing Factors and Prediction of Hospitalisation Costs for Insured Stroke Patients in Tianjin Municipality, thesis, Tianjin Medical University.
Guang X, 2019, BP Neural Network-based Study of Hospitalisation Costs for Chronically Ill Patients, thesis, Dalian Medical University.
Hajek P, Abedin MZ, Sivarajah U, 2022, Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework. Information Systems Frontiers: A Journal of Research and Innovation, 2019: 1–19. https://doi.org/10.1007/s10796-022-10346-6
Deng Y, Jiao Y, Zhao X, 2013, Current Situation and Effect Evaluation of the Stroke Clinical Pathway Pilot Project. China Modern Medicine, 20(33): 14–16, 19.
Wu Z, Lin X, Zhu D, 2023, Application Effect and Cost-Effectiveness Analysis of the Clinical Pathway for Stroke Rehabilitation. Guangxi Medical Journal, 45(10): 1256–1258.
Chen Y, Feng T, Chang R, et al., 2024, Analysis of the Influencing Factors of the Hospitalization Costs of Ischemic Stroke Patients under the Background of DRGs Payment. Chinese Medical Record, 25(6): 57–61.
Gao Y, Zhang X, 2023, Analysis of the Influencing Factors of the Hospitalization Costs of Stroke Patients in a Class-A Tertiary Hospital in Shanxi Province. Chinese Medical Record, 24(5): 69–72.
He C, Pan X, Liu Y, et al., 2023, Analysis of the Influencing Factors of the Hospitalization Costs of Stroke Patients in Sichuan Province. Modern Preventive Medicine, 2023(8): 1441–1445.
Chen Y, Chang R, Wang P, et al., 2023, Analysis of the Grouping Effect and Hospitalization Costs of Ischemic Stroke Patients Based on DRG. Chinese Journal of Hospital Statistics, 30(6): 457–460.
Li Y, Mao F, Xu H, et al., 2023, Research on the Current Situation and Demand of the Allocation of Medical Resources for Stroke Treatment in Shandong Province. China Medical Equipment, 20(3): 146–151.
Shi L, Qian C, Guo F, 2022, Real-time Driving Risk Assessment Using Deep Learning with XGBoost. Accident Analysis and Prevention, (2022): 106836.
Lan X, Wei R, Cai H, et al., 2019, Application of Machine Learning Algorithms in the Medical Field. Chinese Medical Equipment Journal, 40(3): 5.
Cai Y, Xiao J, He Y, et al., 2022, A Bi-level Multi-objective Programming Model for Water Resources Management under Compound Uncertainties in Dongjiang River Basin, Greater Bay Area of China. Journal of Contaminant Hydrology, (2022): 104020.