心脑血管病防治2025，Vol.25Issue(9)：20-25,6.DOI:10.3969/j.issn.1009-816x.2025.09.005
基于Lasso-Logistic回归分析构建冠心病经皮冠状动脉介入术后主要不良心血管事件的列线图预测模型
Establishment of a nomogram prediction model for major adverse cardiovascular events after percutaneous coronary intervention in coronary heart disease patients based on Lasso-Logistic regression analysis
摘要
Abstract
Objective To analyze the influencing factors for major adverse cardiovascular events(MACE)within 1 year after percutaneous coronary intervention(PCI)in patients with coronary heart disease(CHD)using Lasso-Logistic regression analysis,and establish a nomogram prediction model based on these influencing factors.Methods A total of 210 CHD patients who underwent PCI at the First Hospital of Qinhuangdao from January 2022 to October 2023 were selected.The occurrence of MACE within 1 year after PCI was recorded,and the patients were categorized into the MACE(52 cases)and non-MACE(158 cases)groups according to whether MACE occurred.Clinical data of both groups were collected and compared.Influencing factors for MACE within 1 year after PCI in CHD patients were analyzed by Lasso-Logistic regression.Subsequently,a nomogram prediction model was constructed using R software based on these factors.The discrimination of the nomogram prediction model was evaluated using receiver operating characteristic(ROC)curve analysis,and its predictive performance was assessed using calibration curves.Results Compared with the non-MACE group,the MACE group had significantly higher values for age,proportion of multivessel disease,hypertension,diabetes,smoking,low-density lipoprotein cholesterol(LDL-C),high-sensitivity C-reactive protein(hs-CRP),procalcitonin(PCT),uric acid(UA),D-dimer(D-D),soluble suppression of tumorigenicity-2(sST2),interleukin-33(IL-33),and lipoprotein-associated phospholipase A2(Lp-PLA2),while estimated glomerular filtration rate(eGFR)was significantly lower(t/χ2=6.519,8.652,5.066,5.145,15.316,7.789,2.310,5.553,8.198,9.905,9.806,9.000,8.192,4.885;all P<0.05).Lasso-Logistic regression analysis revealed age,multivessel disease,smoking,LDL-C,eGFR,UA,D-D,sST2,IL-33,and Lp-PLA2 as influencing factors for MACE in CHD patients within 1 year after PCI(OR=2.450,3.064,2.066,1.355,0.874,1.201,1.295,1.260,1.117,1.119;all P<0.05).A nomogram prediction model was constructed based on the influencing factors of MACE in CHD patients within 1 year after PCI,and the ROC curve of the nomogram prediction model was plotted.The AUC of this prediction model for predicting MACE in CHD patients within 1 year after PCI was 0.915(95%CI=0.866-0.965).Furthermore,the calibration curve indicated good agreement between predicted and observed risks.Conclusion Age,multivessel disease,smoking,LDL-C,eGFR,UA,D-D,sST2,IL-33,and Lp-PLA2 are identified as influencing factors for MACE in CHD patients within 1 year after PCI.The nomogram prediction model based on these factors demonstrates excellent predictive performance.关键词
冠心病/经皮冠状动脉介入/主要不良心血管事件Key words
Coronary heart disease/Percutaneous coronary intervention/Major adverse cardiovascular events引用本文复制引用
孙优,赵云凤,董采杰,蔡丽丽..基于Lasso-Logistic回归分析构建冠心病经皮冠状动脉介入术后主要不良心血管事件的列线图预测模型[J].心脑血管病防治,2025,25(9):20-25,6.基金项目
河北省秦皇岛市科学技术研究与发展计划(202004A028) （202004A028）
