Construction and evaluation of a prognostic nomogram prediction model for patients with coronary heart disease based on Lp-PLA2，LP( a) ，and clinical risk factors
10.19405/j.cnki.issn1000-1492.2025.09.023
- VernacularTitle:基于脂蛋白相关磷脂酶 A2、脂蛋白( a) 及临床危险因素的冠心病患者预后列线图预测模型的构建及评价
- Author:
Tianqi Wang
1
;
Zeping Hu
1
;
Xuetao Zhu
1
Author Information
1. Dept of Cardiology，The First Affiliated Hospital of Anhui Medical University，Hefei 230022
- Publication Type:Journal Article
- Keywords:
lipoprotein-associated phospholipase A2;
lipoprotein(a);
coronary heart disease;
nomogram;
prognostic prediction model;
risk factor
- From:
Acta Universitatis Medicinalis Anhui
2025;60(9):1735-1745
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To construct and to validate a nomogram prediction model based on Lipoprotein-associated phospholipase A2(Lp-PLA2) and Lipoprotein(a) [LP(a) ]for predicting the risk of major adverse cardiovascular events(MACE) in patients with coronary heart disease(CHD).
Methods:A retrospective analysis was conducted on the clinical data of 442 patients with coronary heart disease(CHD). Among them,411 patients who completed follow-up were randomly divided into a training set(288 cases) and a validation set(123 cases) at a 7 ∶ 3 ratio.Independent risk factors for major adverse cardiovascular events(MACE) in CHD patients were screened through Lasso regression analysis and Cox regression analysis,and a nomogram prediction model was constructed. The predictive performance of the model was evaluated using time-dependent receiver operating characteristic curves(ROC),calibration curves,and decision curve analysis.
Results:Variables were screened through Lasso regression and Cox regression analysis. The final model included nine independent predictors,namely age,smoking history,clinical phenotype of CHD,the number of coronary artery lesions,Gensini score,BNP,Lp-PLA2,LP(a), and the history of statin use. The area under the ROC curve in the training set was 0. 897,0. 885,and 0. 909 at 1,2,and 3 years,respectively; The area under the ROC curve in the validation set was 0. 885,0. 881,and 0. 923 at 1,2,and 3 years,respectively. These results demonstrated that the model had excellent discriminatory power. The calibration curves and decision curves demonstrated that the model had high clinical practicality in predicting the occurrence of MACE in CHD patients.
Conclusion:The nomogram prediction model based on LP-PLA2,LP(a)and other risk factors provides an effective tool for the prognosis assessment of CHD patients,facilitating the early identification of high-risk patients and enabling individualized intervention.
- Full text:2026032815381853717基于脂蛋白相关磷脂酶A2、脂蛋白(a)及临床危险因素的冠心病患者预后列线图预测模型的构建及评价_王天齐.pdf
