中国合理用药探索2025，Vol.22Issue(12)：31-38,8.DOI:10.3969/j.issn.2096-3327.2025.12.004
基于LASSO回归的冠心病患者依洛尤单抗疗效预测模型构建分析
Construction and Analysis of a LASSO Regression-Based Predictive Model for the Efficacy of Evolocumab in Patients with Coronary Heart Disease
GUO Guo-xun 1ZHANG Zheng 1ZHANG Zhao 1WEI Xiao-yun 1HENG Zi-wei 1MIAO Dan-dan1
作者信息
- 1. Department of Cardiology,The Fifth Clinical Medical College,Henan University of Chinese Medicine(People's Hospital of Zhengzhou),Zhengzhou 450000,China
- 折叠
摘要
Abstract
Objective:To construct a LASSO regression-based predictive model for the efficacy of evolocumab in patients with coronary heart disease(CHD).Methods:A total of 190 CHD patients treated at a hospital from January 2021 to January 2025 were retrospectively collected and assigned to the training set(n=133)and the validation set(n=57)in a 7:3 ratio.The training set was used for model construction,while the validation set was used for independent verification of the model's generalizability.A univariate analysis was first performed on the clinical data collected from the patients.Subsequently,potential predictors related to the therapeutic effect were screened using LASSO regression analysis.A multivariate Logistic regression analysis was used for further screening to construct a nomogram model.The concordance index(C-index)and calibration curve were used to evaluate model discrimination and calibration,respectively,while clinical decision curve analysis assessed clinical applicability.Additionally,a receiver operating characteristic(ROC)curve was plotted to calculate the area under the curve(AUC)and evaluate the predictive performance of the model.Results:LASSO-Logistic regression analysis revealed that age,number of coronary artery lesions,alanine aminotransferase(ALT),total cholesterol(TC)and low-density lipoprotein cholesterol(LDL-C)were independent influencing factors for the efficacy of evolocumab in patients with CHD.The C-index was 0.858 in the training set and 0.800 in the validation set.The calibration curves demonstrated good agreement between predicted probabilities and observed probabilities,indicating good model discrimination and calibration.ROC curve analysis revealed that the AUC for the predictive model was 0.858(95%CI 0.776～0.941)in the training set and 0.800(95%CI 0.679～0.922)in the validation set,indicating a high predictive ability.Clinical decision curve analysis demonstrated that the clinical utility of this model.Conclusion:Age,number of coronary artery lesions,ALT,TC and LDL-C were identified as predictive factors influencing the efficacy of evolocumab in patients with CHD.The constructed predictive model demonstrates good predictive performance upon validation,which may assist clinicians in optimizing clinical decision-making and thereby improving patient outcomes.关键词
LASSO回归/冠心病/依洛尤单抗/疗效/预测模型Key words
LASSO regression/coronary heart disease/evolocumab/efficacy/predictive model分类
医药卫生引用本文复制引用
GUO Guo-xun,ZHANG Zheng,ZHANG Zhao,WEI Xiao-yun,HENG Zi-wei,MIAO Dan-dan..基于LASSO回归的冠心病患者依洛尤单抗疗效预测模型构建分析[J].中国合理用药探索,2025,22(12):31-38,8.
