Fig. 4

ROC curve of seven machine learning models using top 10 features on validation data: The model built using XGB classifier (represented by pink solid line) shows the best AUC followed by RF classifier. The X-axis represents the false positive rate i.e. 1-Specificity while Y-axis represents the true positive rate i.e. Sensitivity. Abbreviations: ROC, Receiver Operating Characteristics; DT, Decision Tree; RF, Random Forest; SVM, Support Vector Machine; LR, Logistic Regression; GNB, Gaussian Naïve Bayes; KNN, k-Nearest Neighbour; XGB, eXtreme Gradient Boosting