Figure 6.

Mean receiver operating characteristic (ROC) curves from the classification models of nvfPPA, lvPPA, and svPPA. We run three separate supervised one-against-all classification models using rain forests (RFs), support vector machines (SVMs), and decision trees (DTs). Shown in the figure is the ROC with the mean area under the curve (AUC) for the DT, SVM, RF models and the corresponding SD. The best classification is the one whose ROC approaches the right upper corner of the plot and that has the highest AUC; here, the best mean AUC resulted from RFs for nfvPPA, RFs for lvPPA, and SVM models for svPPA. PPA = primary progressive aphasia; nfvPPA = nonfluent PPA variant; lvPPA = logopenic PPA variant; svPPA = semantic PPA variant.