Skip to main content
Fig. 4 | BMC Medical Informatics and Decision Making

Fig. 4

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

Fig. 4

Performances of the classification methods. Depicted are accuracy (bars) and ROC AUC (dots) values for the color-coded algorithms for all three paradigms. The scores are the result of evaluating the methods on the single test dataset (MEP data of 8 patients). The RF classifier performed best overall and on the raw data in particular. The kNN classifier performed second best overall. Note that the LogReg performed poorly on raw and PCA data, but well on feature extracted data (in all paradigms)

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us