5-year all-cause mortality survival analysis and interpretable study in patients with coronary artery disease combined with chronic heart failure

ZHANG Weichang; TIAN Jing; YANG Hong; HAN Qinghua; ZHANG Yanbo

doi:10.16462/j.cnki.zhjbkz.2023.04.001

Volume 27 Issue 4

Apr. 2023

Turn off MathJax

Article Contents

Abstract

References

Article Navigation > CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION > 2023 > 27(4): 373-378

ZHANG Weichang, TIAN Jing, YANG Hong, HAN Qinghua, ZHANG Yanbo. 5-year all-cause mortality survival analysis and interpretable study in patients with coronary artery disease combined with chronic heart failure[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2023, 27(4): 373-378. doi: 10.16462/j.cnki.zhjbkz.2023.04.001

Citation:

ZHANG Weichang, TIAN Jing, YANG Hong, HAN Qinghua, ZHANG Yanbo. 5-year all-cause mortality survival analysis and interpretable study in patients with coronary artery disease combined with chronic heart failure[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2023, 27(4): 373-378. doi: 10.16462/j.cnki.zhjbkz.2023.04.001

Citation:

ZHANG Weichang, TIAN Jing, YANG Hong, HAN Qinghua, ZHANG Yanbo. 5-year all-cause mortality survival analysis and interpretable study in patients with coronary artery disease combined with chronic heart failure[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2023, 27(4): 373-378. doi: 10.16462/j.cnki.zhjbkz.2023.04.001

PDF( 2758 KB)

5-year all-cause mortality survival analysis and interpretable study in patients with coronary artery disease combined with chronic heart failure

doi: 10.16462/j.cnki.zhjbkz.2023.04.001

ZHANG Weichang¹,
TIAN Jing²,
YANG Hong¹,
HAN Qinghua^{2
,
,},
ZHANG Yanbo^{1, 2
,
,}

1.
Department of Biostatistics, School of Public Health, Shanxi Medical University, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan 030000, China
2.
Department of Cardiology, First Hospital of Shanxi Medical University, Taiyuan 030000, China
3.
School of Health Services and Management, Shanxi University of Chinese Medicine, Jinzhong 030619, China

Funds:

National Natural Science Foundation of China 81872714

National Natural Science Foundation of China 82173631

Shanxi Provincial Key Laboratory 201805D111006

More Information

Corresponding author: HAN Qinghua, E-mail: syhqh@sohu.com; ZHANG Yanbo, E-mail: sxmuzyb@126.com
Received Date: 2022-05-06
Rev Recd Date: 2023-01-09

Available Online: 2023-04-28

Publish Date: 2023-04-10

Abstract

Abstract

Objective To investigate the risk factors for all-cause mortality in patients with coronary heart disease combined with chronic heart failure by using machine learning algorithms and shapley additive explanations (SHAP). Methods A total of 2 648 patients diagnosed with coronary heart disease combined with chronic heart failure in two tertiary hospitals in Shanxi Province were selected for the study. The Cox, random survival forests (RSF), and XGBoost models were constructed using the variables screened by XGBoost; SHAP was applied to analyze the model interpretability. Results The prediction model created using XGBoost had the highest predictive performance with a concordance index (C-index) of 0.902 (0.900-0.915). The model showed that higher age, NTproBNP, systolic blood pressure, and creatinine were associated with a higher risk of death. Diabetes, central nervous system disorders, and statins significantly influenced patient prognosis. Conclusions The survival analysis prediction model constructed by XGBoost can more accurately assess the poor prognosis of patients and, in combination with SHAP, can provide a clear interpretation of individualized risk prediction for patients. It is helpful to assist doctors in personalizing clinical treatment for patients.
- XGBoost,
- Coronary heart disease,
- Chronic heart failure,
- Survival analysis,
- Interpretable

FullText(HTML)

References(21)

References

[1]	北京高血压防治协会, 北京糖尿病防治协会, 北京慢性病防治与健康教育研究会, 等. 基层心血管病综合管理实践指南2020[J]. 中国医学前沿杂志(电子版), 2020, (8): 1-73. DOI: 10.12037/YXQY.2020.08-01. Beijing Hypertension Association, Beijing Diabetes Prevention and Treatment Association, Beijing Research for Chronic Diseases Control and Health Education, et al. Practice Guide for comprehensive management of cardiovascular diseases at the grassroots level 2020[J]. Chinese Journal of the Frontiers of Medical Science(Electronic Version), 2020, (8): 1-73. DOI: 10.12037/YXQY.2020.08-01.
[2]	Savarese G, Lund LH. Global public health burden of heart failure[J]. Card Fail Rev, 2017, 3(1): 7-11. DOI: 10.15420/cfr.2016:25:2.
[3]	Van HL, Carson JAS, Appel LJ, et al. Recommended dietary pattern to achieve adherence to the American heart association/american college of cardiology (AHA/ACC) guidelines: a scientific statement from the American heart association[J]. Circulation, 2016, 134(22): e505-e529. DOI: 10.1161/CIR.0000000000000462.
[4]	王增武, 胡盛寿. 《中国心血管健康与疾病报告2020》要点解读[J]. 中国心血管杂志, 2021, 26(3): 209-218. DOI: 10.3969/j.issn.1007-5410.2021.03.001. Wang ZW, Hu ST. Interpretation of report on cardiovascular health and diseases in China 2020[J]. Chin J Cardiovasc Medicine, 2021, 26(3): 209-218. DOI: 10.3969/j.issn.1007-5410.2021.03.001.
[5]	王增武, 马志毅, 薛素芳, 等. 基层冠心病与缺血性脑卒中共患管理专家共识2022[J]. 中国心血管病研究, 2022, 20(9): 772-793. DOI: 10.3969/j.issn.1672-5301.2022.09.002. Wang ZW, Ma ZY, Xue SF, et al. 2022 expert consensus on the management of coronary heart disease with ischemic stroke in community[J]. Chin J Cardiovasc Res, 2022, 20(9): 772-793. DOI: 10.3969/j.issn.1672-5301.2022.09.002.
[6]	杨弘, 田晶, 孟冰霞, 等. 加权随机森林和代价敏感支持向量机与心衰患者死亡风险评估[J]. 中国卫生统计, 2022, 39(3): 381-384, 388. DOI: 10.3969/j.issn.1002-3674.2022.03.012. Yang H, Tian J, Meng BX, et al. Weighted random forests and cost-sensitive support vector machines and the assessment of mortality risk in patients with heart failure[J]. Chin J Health Stat, 2022, 39(3): 381-384, 388. DOI: 10.3969/j.issn.1002-3674.2022.03.012.
[7]	杨弘, 田晶, 王可, 等. 混合型缺失数据填补方法比较与应用[J]. 中国卫生统计, 2020, 37(3): 395-399. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGWT202003016.htm Yang H, Tian J, Wang K, et al. Comparison and application of hybrid missing data filling methods[J]. Chin J Health Stat, 2020, 37(3): 395-399. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGWT202003016.htm
[8]	Ishwaran H, Kogalur UB, Blackstone EH, et al. Random survival forests[J]. Ann Appl Stat, 2008, 2(3): 841-860. DOI: 10.1214/08-AOAS169.
[9]	陈哲, 许恒敏, 李哲轩, 等. 随机生存森林: 基于机器学习算法的生存分析模型[J]. 中华预防医学杂志, 2021, 55(1): 104-109. DOI: 10.3760/cma.j.cn112150-20200911-01197. Chen Z, Xu HM, Li ZX, et al. Random survival forest: applying machine learning algorithm in survival analysis of biomedical data[J]. Chin J Prevent Med, 2021, 55(1): 104-109. DOI: 10.3760/cma.j.cn112150-20200911-01197.
[10]	Chen TQ, Carlos G. XGBoost: a scalable tree boosting system[J]. ACM, 2016, 785-794.
[11]	潘进, 丁强, 江爱朋, 等. 基于XGBoost的冷水机组不平衡数据故障诊断[J]. 机械强度, 2021, 43(1): 27-33. DOI: 10.16579/j.issn.1001.9669.2021.01.004. Pan J, Ding Q, Jiang AP, et al. Fault diagnosis of unbalanced data of chillers based on XGBoost[J]. J Mechanical Strength, 2021, 43(1): 27-33. DOI: 10.16579/j.issn.1001.9669.2021.01.004.
[12]	Lundberg S, Lee S I. A unified approach to interpreting model predictions[C]// Conference and Workshop on Neural Information Processing Systems. California: NIPS Press, 2017: 4765-4774.
[13]	Agus Salim, E ST, Vincent YT, et al. C-reactive protein and serum creatinine, but not haemoglobin A1c, are independent predictors of coronary heart disease risk in non-diabetic Chinese[J]. Eur J Prev Cardiol, 2016, 23(12): 1339-1349. DOI: 10.1177/2047487315626547.
[14]	Chami J, Fleming S, Taylor C, et al. Point-of-care NT-proBNP monitoring for heart failure: observational feasibility study in primary care[J]. BJGP open, 2022, 6(3): BJGPO. 2022.0005. DOI: 10.3399/BJGPO.2022.0005.
[15]	Dunlay SM, Givertz MM, Aguilar D, et al. Type 2 diabetes mellitus and heart failure: a scientific statement from the American heart association and the heart failure society of America: this statement does not represent an update of the 2017 ACC/AHA/HFSA heart failure guideline update[J]. Circulation, 2019, 140(7): e294-e324. DOI: 10.1161/CIR.0000000000000691.
[16]	Wang J, Wu XF, Li YR, et al. Serum bilirubin concentrations and incident coronary heart disease risk among patients with type 2 diabetes: the Dongfeng-Tongji cohort[J]. Acta Diabetol, 2017, 54(3): 257-264. DOI: 10.1007/s00592-016-0946-x.
[17]	Arnold Suzanne V, Bhatt Deepak L, Barsness Gregory W, et al. Clinical management of stable coronary artery disease in patients with Type 2 diabetes mellitus: A scientific statement from the American heart association[J]. Circulation, 2020, 141(19). DOI: 10.1161/CIR.0000000000000766.
[18]	Zhang JJ, Guo Q, Peng LY, et al. The association of neck circumference with incident congestive heart failure and coronary heart disease mortality in a community-basedpopulation with or without sleep-disordered breathing[J]. BMC Cardiovasc Disord, 2018, 18(1): 108. DOI: 10.1186/s12872-018-0846-9.
[19]	Yoshihisa A, Sato T, Kajimoto K, et al. Heterogeneous impact of body mass index on in-hospital mortality in acute heart failure syndromes: an analysis from the ATTEND registry[J]. Eur Heart J Acute Cardiovasc Care, 2019, 8(7): 589-598. DOI: 10.1177/2048872617703061.
[20]	韩嫱, 田晶, 闫晶晶, 等. 冠心病合并心力衰竭患者再住院影响因素的多水平模型[J]. 中华疾病控制杂志, 2019, 23(8): 961-965. DOI: 10.16462/j.cnki.zhjbkz.2019.08.015. Han Q, Tian J, Yan JJ, et al. Multilevel model analysis for influencing factors of readmission in coronary heart disease patients with heart failure[J]. Chin J Dis Control Prev, 2019, 23(8): 961-965. DOI: 10.16462/j.cnki.zhjbkz.2019.08.015.
[21]	李靓, 田晶, 闫晶晶, 等. 冠心病合并慢性心力衰竭患者不同结局的零膨胀联合脆弱模型[J]. 中华疾病控制杂志, 2021, 25(8): 962-967. DOI: 10.16462/j.cnki.zhjbkz.2021.08.016. Li J, Tian J, Yan JJ, et al. Joint frailty models for zero-inflated analysis of different outcomes in patients with coronary heart disease complicated with chronic heart failure[J]. Chin J Dis Control Prev, 2021, 25(8): 962-967. DOI: 10.16462/j.cnki.zhjbkz.2021.08.016.

Relative Articles

Relative Articles

Supplements(0)

Cited By

Cited by

Periodical cited type(14)

1.	周足妹，蒋启荣，徐杨. 尿酸水平对冠心病慢性心力衰竭后并发症的影响分析. 基层医学论坛. 2025(02): 28-31 .
2.	汤莉莹，王晶，白玉芝，李培，赵霞，田甜. 冠心病合并射血分数保留型心力衰竭患者不良预后的影响因素. 中国医师杂志. 2024(02): 281-284 .
3.	张红梅，张宁，孙玉娇，张洲. 基于机器学习和logistic回归分析模型分析2型糖尿病轻度认知功能障碍的影响因素. 中华疾病控制杂志. 2024(03): 269-276 . 本站查看
4.	李芳，王倩，李悦，李峥. 专病一体化护理联合协同护理模式对老年慢性心力衰竭患者的影响. 齐鲁护理杂志. 2024(06): 9-12 .
5.	江洋，刘泽岩，叶丽，汪栋林，程景林，万俊. 血清LncRNA FAF、ITIH4在慢性心力衰竭患者中的表达意义及对预后的预测价值. 疑难病杂志. 2024(04): 418-422+428 .
6.	张韵聆，付吉芬，纵艺璇，艾敏，邢星，孙迎莉. 基于CiteSpace探讨近5年慢性心力衰竭护理研究热点. 全科护理. 2024(11): 2002-2006 .
7.	邓颖，柴琪，杨正婷，卢文婷，罗艺婷，蔡云石. 基于灰色-马尔科夫模型预测四川省脑血管疾病死亡率趋势研究. 检验医学与临床. 2024(12): 1769-1774 .
8.	胡佳曼，池嘉宁，吴宁霞，蔡华，赖莹莹，林彩龙，林仲秋，黄建玉，黎蔚华，李敏，苏澎，程文姚，徐琳. 老年男性冠心病合并慢性心力衰竭患者的远期预后研究. 中华老年医学杂志. 2024(04): 422-428 .
9.	于倩，安跃振，张雷，王佳旺，李建伟，宋苗苗. 参麦注射液治疗冠心病慢性心力衰竭. 长春中医药大学学报. 2024(10): 1147-1150 .
10.	蒋睿，贾诗宇，徐琳，吴建，王赛怡. 基于机器学习和logistic回归分析探究老年人死亡的影响因素. 河南医学研究. 2024(24): 4442-4447 .
11.	李世阁，张晓丹，叶章正. 沙库巴曲缬沙坦联合芪苈强心胶囊治疗冠心病心力衰竭的临床疗效. 深圳中西医结合杂志. 2024(20): 33-36 .
12.	史蓓蓓，王妍，崔晓婷. ACR、Cys C、ApoA1水平与慢性心力衰竭患者病情严重程度及预后的相关性分析. 分子诊断与治疗杂志. 2023(12): 2224-2228 .
13.	黄进发，黄诗聪. 沙库巴曲缬沙坦结合琥珀酸美托洛尔对冠心病伴慢性心力衰竭患者心功能、血清生化指标的影响. 中外医疗. 2023(35): 69-72 .
14.	孙悦，陈广新，于淼，郭金兴. 基于可解释性机器学习的新冠肺炎疾病风险预测研究. 新一代信息技术. 2023(12): 40-44 .