Prediction of hospitalization expenses for ischemic heart disease: machine learning based on SHAP theory_Chinese Journal of Evidence-Based Medicine

Authors：

TU Lang , LI Shulei , FAN Ruoxi , YU Jingxin ,  ZHOU Xiaoyuan

West China School of Public Health and West China Fourth Hospital, Sichuan University, Chengdu 610041, P.R. China;

Corresponding author：

ZHOU Xiaoyuan, Email: zhouxyuan@scu.edu.cn

Keywords：

Ischemic heart disease; Hospitalization expenses; Machine learning; SHAP; Influencing factor

DOI：

10.7507/1672-2531.202503190

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To construct the prediction model of hospitalization expenses for ischemic heart disease, reveal the key factors affecting hospitalization expenses, and analyze the interaction between variables. Methods Patients from Sichuan medical insurance comprehensive service platform from January 2020 to December 2021 were extracted. The training set and test set were divided according to the ratio of 7∶3. Six machine learning models were constructed and trained by ten-fold cross validation, and was explained by SHAP theory. Results XGBoost model had the best performance among these models, with a R² of 0.60, RMSE of 9 969.71 yuan, and MAE of 5 242.90 yuan in the test set. SHAP results showed that the five variables with the greatest impact on hospitalization expenses were surgery, length of stay, hospital grade, disease type and DRG. Hospitalization costs were higher when grade 3 or 4 procedures were performed, the length of stay was prolonged, the hospitalization was in a tertiary hospital, and payments were made for acute myocardial infarction and non-DRG. With the prolongation of hospital stay, the hospitalization expenses increased faster when the patient had grade 4 surgery and was in a tertiary hospital. In addition, DRG payment will reduce the length of hospital stay and the hospitalization expenses of patients with different disease types. Conclusion The interpretable XGBoost model constructed in this study has a good predictive performance for the hospitalization expenses of patients with ischemic heart disease. Combined with SHAP theory, it can effectively identify the key factors affecting the hospitalization expenses and analyze their interactions.

1.	Wang H, Zhang H, Zou Z. Changing profiles of cardiovascular disease and risk factors in China: a secondary analysis for the Global Burden of Disease Study 2019. Chin Med J (Engl), 2023, 136(20): 2431-2441.
2.	Collaborators GBDF. Burden of disease scenarios for 204 countries and territories, 2022-2050: a forecasting analysis for the Global Burden of Disease Study 2021. Lancet, 2024, 403(10440): 2204-2256.
3.	Shi H, Xia Y, Cheng Y, et al. Global burden of ischemic heart disease from 2022 to 2050: projections of incidence, prevalence, deaths, and disability-adjusted life years. Eur Heart J Qual Care Clin Outcomes, 2024, 2024: qcae049.
4.	刘明波, 何新叶, 杨晓红, 等. 《中国心血管健康与疾病报告2023》要点解读. 中国全科医学, 2025, 28(1): 20-38.
5.	毛英, 孙李丽, 陈欣妍, 等. 缺血性心脏病患者医疗经济负担分析. 中国卫生标准管理, 2023, 14(14): 42-46.
6.	周立业, 夏鑫婧, 郭志飞, 等. 山西省运城市某三甲医院冠心病患者住院费用影响因素研究. 医学与社会, 2022, 35(11): 116-122.
7.	余浪, 易东. B-P神经网络模型在缺血性心脏病住院费用影响因素分析中的应用. 中国病案, 2018, 19(3): 78-82.
8.	张晔, 迟卫军, 徐云伟, 等. 基于随机森林的冠心病患者住院费用影响因素的分析. 中国病案, 2019, 20(2): 53-57.
9.	张慧, 贺松, 张硕, 等. 基于GWO-SVR的冠心病住院费用预测. 智能计算机与应用, 2020, 10(11): 42-46.
10.	夏涛, 徐辉煌, 郑建立. 基于机器学习的冠心病住院费用预测研究. 智能计算机与应用, 2019, 9(5): 35-39.
11.	Sulaieva O, Yerokhovych V, Zemskov S, et al. The impact of war on people with type 2 diabetes in Ukraine: a survey study. EClinicalMedicine, 2024, 79: 103008.
12.	王兆华, 刘杰, 王博, 等. 融合机器学习与SHAP值算法的居民需求响应个体异质性因素挖掘与应用研究. 系统工程理论与实践, 2024, 44(7): 2247-2259.
13.	刘忠典, 许琪, 陈伊静, 等. 心血管疾病中高风险人群颈动脉粥样硬化的识别: 基于机器学习的预测模型及验证. 中国全科医学, 2024, 27(30): 3763-3771.
14.	四川省医疗保障局. 关于省本级开展基本医疗保险区域点数法总额预算和按疾病诊断相关分组(DRG)付费工作的实施意见(川医保规〔2021〕11号). 2021.
15.	吴妮, 周晓媛, 王寓凡, 等. DRG付费下四川省心脑血管疾病患者住院费用及天数的影响因素研究. 医学与社会, 2024, 37(10): 77-84.
16.	Guo X, Qin Y, Feng Z, et al. Investigating the anti-inflammatory effects of icariin: a combined met a-analysis and machine learning study. Heliyon, 2024, 10(15): e35307.
17.	Schober P, Boer C, Schwarte LA. Correlation coefficients: appropriate use and interpretation. Anesth Analg, 2018, 126(5): 1763-1768.
18.	郭小川, 冯贞贞, 刘文瑞, 等. 基于Stacking集成算法的中医证候诊断模型建立——以肺癌为例. 中医杂志, 2024, 65(17): 1775-1783.
19.	Speiser JL, Miller ME, Tooze J, et al. A Comparison of random forest variable selection methods for classific ation prediction modeling. Expert Syst Appl, 2019, 134: 93-101.
20.	O'Connell NS, Jaeger BC, Bullock GS, et al. A comparison of random forest variable selection methods for regressio n modeling of continuous outcomes. Brief Bioinform, 2025, 26(2): bbaf096.
21.	刘砾雯, 韩立丰, 张文洁, 等. 基于梯度提升的珠海市结肠癌患者住院费用影响因素研究. 医学与社会, 2025, 38(3): 25-31.
22.	Lundberg SM, Lee SI. A unified approach to interpreting model predictions. 2017.
23.	Fu Q, Wu Y, Zhu M, et al. Identifying cardiovascular disease risk in the U. S. population using e nvironmental volatile organic compounds exposure: a machine learning p redictive model based on the SHAP methodology. Ecotoxicol Environ Saf, 2024, 286: 117210.
24.	姚敏欣. 基于机器学习模型的心血管疾病患者住院费用预测研究. 中国医疗保险, 2024, (6): 105-118.
25.	葛龙, 张南, 王月. DRG支付方式改革对高血压患者住院次均费用的影响研究. 中国医院管理, 2023, 43(12): 25-28.
26.	王文君, 贾晓倩, 周道平, 等. DRG支付改革下某公立医院干预措施及实施效果分析. 中国医院, 2023, 27(2): 69-72.
27.	伏欣, 张华, 谢亚坤, 等. 我国DRG支付方式改革对住院时间及费用影响的meta分析. 医学与社会, 2024, 37(4): 74-80.
28.	王寓凡, 周晓媛, 吴妮, 等. 基于多水平模型的心血管患者高额住院费用影响因素研究. 卫生经济研究, 2025, 42(2): 55-58.
29.	毛英, 孙李丽, 刘芳, 等. 合并多种慢性病的缺血性心脏病患者住院费决策树分析. 中国医院统计, 2023, 30(5): 381-386.

1. Wang H, Zhang H, Zou Z. Changing profiles of cardiovascular disease and risk factors in China: a secondary analysis for the Global Burden of Disease Study 2019. Chin Med J (Engl), 2023, 136(20): 2431-2441.
2. Collaborators GBDF. Burden of disease scenarios for 204 countries and territories, 2022-2050: a forecasting analysis for the Global Burden of Disease Study 2021. Lancet, 2024, 403(10440): 2204-2256.
3. Shi H, Xia Y, Cheng Y, et al. Global burden of ischemic heart disease from 2022 to 2050: projections of incidence, prevalence, deaths, and disability-adjusted life years. Eur Heart J Qual Care Clin Outcomes, 2024, 2024: qcae049.
4. 刘明波, 何新叶, 杨晓红, 等. 《中国心血管健康与疾病报告2023》要点解读. 中国全科医学, 2025, 28(1): 20-38.
5. 毛英, 孙李丽, 陈欣妍, 等. 缺血性心脏病患者医疗经济负担分析. 中国卫生标准管理, 2023, 14(14): 42-46.
6. 周立业, 夏鑫婧, 郭志飞, 等. 山西省运城市某三甲医院冠心病患者住院费用影响因素研究. 医学与社会, 2022, 35(11): 116-122.
7. 余浪, 易东. B-P神经网络模型在缺血性心脏病住院费用影响因素分析中的应用. 中国病案, 2018, 19(3): 78-82.
8. 张晔, 迟卫军, 徐云伟, 等. 基于随机森林的冠心病患者住院费用影响因素的分析. 中国病案, 2019, 20(2): 53-57.
9. 张慧, 贺松, 张硕, 等. 基于GWO-SVR的冠心病住院费用预测. 智能计算机与应用, 2020, 10(11): 42-46.
10. 夏涛, 徐辉煌, 郑建立. 基于机器学习的冠心病住院费用预测研究. 智能计算机与应用, 2019, 9(5): 35-39.
11. Sulaieva O, Yerokhovych V, Zemskov S, et al. The impact of war on people with type 2 diabetes in Ukraine: a survey study. EClinicalMedicine, 2024, 79: 103008.
12. 王兆华, 刘杰, 王博, 等. 融合机器学习与SHAP值算法的居民需求响应个体异质性因素挖掘与应用研究. 系统工程理论与实践, 2024, 44(7): 2247-2259.
13. 刘忠典, 许琪, 陈伊静, 等. 心血管疾病中高风险人群颈动脉粥样硬化的识别: 基于机器学习的预测模型及验证. 中国全科医学, 2024, 27(30): 3763-3771.
14. 四川省医疗保障局. 关于省本级开展基本医疗保险区域点数法总额预算和按疾病诊断相关分组(DRG)付费工作的实施意见(川医保规〔2021〕11号). 2021.
15. 吴妮, 周晓媛, 王寓凡, 等. DRG付费下四川省心脑血管疾病患者住院费用及天数的影响因素研究. 医学与社会, 2024, 37(10): 77-84.
16. Guo X, Qin Y, Feng Z, et al. Investigating the anti-inflammatory effects of icariin: a combined met a-analysis and machine learning study. Heliyon, 2024, 10(15): e35307.
17. Schober P, Boer C, Schwarte LA. Correlation coefficients: appropriate use and interpretation. Anesth Analg, 2018, 126(5): 1763-1768.
18. 郭小川, 冯贞贞, 刘文瑞, 等. 基于Stacking集成算法的中医证候诊断模型建立——以肺癌为例. 中医杂志, 2024, 65(17): 1775-1783.
19. Speiser JL, Miller ME, Tooze J, et al. A Comparison of random forest variable selection methods for classific ation prediction modeling. Expert Syst Appl, 2019, 134: 93-101.
20. O'Connell NS, Jaeger BC, Bullock GS, et al. A comparison of random forest variable selection methods for regressio n modeling of continuous outcomes. Brief Bioinform, 2025, 26(2): bbaf096.
21. 刘砾雯, 韩立丰, 张文洁, 等. 基于梯度提升的珠海市结肠癌患者住院费用影响因素研究. 医学与社会, 2025, 38(3): 25-31.
22. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. 2017.
23. Fu Q, Wu Y, Zhu M, et al. Identifying cardiovascular disease risk in the U. S. population using e nvironmental volatile organic compounds exposure: a machine learning p redictive model based on the SHAP methodology. Ecotoxicol Environ Saf, 2024, 286: 117210.
24. 姚敏欣. 基于机器学习模型的心血管疾病患者住院费用预测研究. 中国医疗保险, 2024, (6): 105-118.
25. 葛龙, 张南, 王月. DRG支付方式改革对高血压患者住院次均费用的影响研究. 中国医院管理, 2023, 43(12): 25-28.
26. 王文君, 贾晓倩, 周道平, 等. DRG支付改革下某公立医院干预措施及实施效果分析. 中国医院, 2023, 27(2): 69-72.
27. 伏欣, 张华, 谢亚坤, 等. 我国DRG支付方式改革对住院时间及费用影响的meta分析. 医学与社会, 2024, 37(4): 74-80.
28. 王寓凡, 周晓媛, 吴妮, 等. 基于多水平模型的心血管患者高额住院费用影响因素研究. 卫生经济研究, 2025, 42(2): 55-58.
29. 毛英, 孙李丽, 刘芳, 等. 合并多种慢性病的缺血性心脏病患者住院费决策树分析. 中国医院统计, 2023, 30(5): 381-386.

Chinese Journal of Evidence-Based Medicine

Latest ArticlesPrediction of hospitalization expenses for ischemic heart disease: machine learning based on SHAP theory

Abstract Full text Figures/Tables Video References Cited by

Format

Content