Associations of pro-protein convertase subtilisin-like kexin type 9, soluble low-density lipoprotein receptor and coronary artery disease: A case-control study

Construction and Validation of a Predictive Model for Coronary Artery Disease Using Extreme Gradient Boosting

Purpose

Early recognition of coronary artery disease (CAD) could delay its progress and significantly reduce mortality. Sensitive, specific, cost-efficient and non-invasive indicators for assessing individual CAD risk in community population screening are urgently needed.

Patients and Methods

3112 patients with CAD and 3182 controls were recruited from three clinical centers in China, and differences in baseline and clinical characteristics were compared. For the discovery cohort, the least absolute shrinkage and selection operator (LASSO) regression was used to identify significant features and four machine learning algorithms (logistic regression, support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost)) were applied to construct models for CAD risk assessment, the receiver operating characteristics (ROC) curve and precision-recall (PR) curve were conducted to evaluate their predictive accuracy. The optimal model was interpreted by Shapley additive explanations (SHAP) analysis and assessed by the ROC curve, calibration curve, and decision curve analysis (DCA) and validated by two external cohorts.

Results

Using LASSO filtration, all included variables were considered to be statistically significant. Four machine learning models were constructed based on these features and the results of ROC and PR curve implied that the XGBoost model exhibited the highest predictive performance, which yielded a high area of ROC curve (AUC) of 0.988 (95% CI: 0.986-0.991) to distinguish CAD patients from controls with a sensitivity of 94.6% and a specificity of 94.6%. The calibration curve showed that the predicted results were in good agreement with actual observations, and DCA exhibited a better net benefit across a wide range of threshold probabilities. External validation of the model also exhibited favorable discriminatory performance, with an AUC, sensitivity, and specificity of 0.953 (95% CI: 0.945-0.960), 89.9%, and 87.1% in the validation cohort, and 0.935 (95% CI: 0.915-0.955), 82.0%, and 90.3% in the replication cohort.

Conclusion

Our model is highly informative for clinical practice and will be conducive to primary prevention and tailoring the precise management for CAD patients.

Tissue and Serum Biomarkers in Degenerative Aortic Stenosis-Insights into Pathogenesis, Prevention and Therapy

Background and Aim. Degenerative Aortic Stenosis (DAS) is a common disease that causes substantial morbidity and mortality worldwide, especially in the older population. Our aim was to further investigate novel serum and tissue biomarkers to elucidate biological processes involved in this entity. Material and Methods. We evaluated the expression of six biomarkers significantly involved in cardiovascular pathology, i.e., irisin, periostin, osteoglycin, interleukin 18, high mobility group box 1 and proprotein convertase subtilisin/kexin type 9 in the serum at the protein level, and in the tissue at both the protein and mRNA levels of patients with AS (N = 60). Five normal valves obtained after transplantation from hearts of patients with idiopathic dilated cardiomyopathy were also studied. Serum measurements were also performed in 22 individuals without valvular disease who served as controls (C). Results. Higher levels of all factors were found in DAS patients’ serum than in normal C. IHC and PCR mRNA tissue analysis showed the presence of all biomarkers in the aortic valve cusps with DAS, but no trace of PCR mRNA was found in the five transplantation valves. Moreover, periostin serum levels correlated significantly with IHC and mRNA tissue levels in AS patients. Conclusion. We showed that six widely prevalent biomarkers affecting the atherosclerotic process were also involved in DAS, suggesting a strong osteogenic and pro-inflammatory profile, indicating that aortic valve calcification is a multifactorial biological process.