Figure 4. Performance of four different ML-based classifiers.

Performance of various classifiers for distinguishing between DHSs and non-DHSs. A total of 33 classifiers were evaluated using five independent 10-fold cross-validation techniques, and their average performances in terms of MCC, accuracy, sensitivity, and specificity are shown. (A) SVM-based performance, (B) RF-based performance, (C) ET-based performance, and (D) k-NN-based performance. The final selected model for each ML method is shown in red filled circle.