Opportunities and challenges of supervised machine learning for the classification of motor evoked potentials according to muscles

Table 2 Test performance scores

Bold: best performance for each paradigm. Accuracy (Acc) reflects the percentage of correctly assigned labels. ROC AUC is the area under the curve plotting the true positive against the false positive rate. A high ROC AUC means that the model is good at distinguishing between the positive and negative classes. The F-score (F1), macro weighted in case of multiclass classification, is the harmonic average of precision (also known as positive predictive value) and recall (also known as sensitivity). A good F1 can only be achieved if both precision and recall are high

ISSN: 1472-6947