Candidate Diagnostic Biomarker Screening

To identify significant prognostic variables, two machine-learning algorithms were used to predict disease status. The least absolute shrinkage and selection operator (LASSO) is a regression analysis algorithm that uses regularization to improve the prediction accuracy. The LASSO regression algorithm was carried out using the “glmnet” package in R to identify the genes significantly associated with the discrimination of AMI and normal samples. Support vector machine (SVM) is a supervised machine-learning technique widely utilized for both classification and regression. To avoid overfitting, an RFE algorithm was employed to select the optimal genes from the meta-data cohort (24). Therefore, to identify the set of genes with the highest discriminative power, support vector machine recursive feature elimination (SVM-RFE) was applied to select the appropriate features. The overlapping genes between the two algorithms were included and the expression levels of candidate genes were further validated in the {"type":"entrez-geo","attrs":{"text":"GSE60993","term_id":"60993"}}GSE60993 dataset.