Table 5.

Mean classification results of each measure of the data from each modality.

Classifier	Extreme learning machine								SVM-L	SVM-RBF	LDA	RF
Feature type	Train Acc	Test Acc	p-value	Sn	Sp	F1-Score	PPV	NPV	Test Acc	Test Acc	Test Acc	Test Acc
Thickness	0.9908	0.9114	0.0001	0.9339	0.8929	0.9120	0.9403	0.9024	0.5630	0.598	0.5900	0.6250
Thickness STD	1.000	0.9048	0.0001	0.9000	0.9089	0.8993	0.9175	0.9099	0.6040	0.614	0.5900	0.5070
Surface Area	0.9900	0.8813	0.0001	0.8339	0.9304	0.8736	0.8575	0.9339	0.5420	0.500	0.4720	0.5690
Volume	0.9930	0.9063	0.0001	0.8786	0.9321	0.9010	0.8975	0.9375	0.4580	0.576	0.5140	0.4240
Curvature	0.9961	0.9238	0.0001	0.9339	0.9143	0.9259	0.9403	0.9300	0.5830	0.601	0.5830	0.5560
WM Volume	0.9954	0.8956	0.0001	0.8643	0.9286	0.8916	0.8820	0.9367	0.4720	0.542	0.5070	0.4930
Cortical GCOR	0.9891	0.9057	0.0001	0.9304	0.8839	0.9051	0.9385	0.8913	0.5490	0.591	0.5970	0.6250
SC Volume	0.9745	0.8989	0.0001	0.9018	0.8946	0.8958	0.9157	0.9014	0.7010	0.597	0.6180	0.6250
SC Intensity	0.9930	0.8990	0.0001	0.8589	0.9339	0.8906	0.8864	0.9389	0.6740	0.625	0.6180	0.6320
SC GCOR	0.9884	0.9124	0.0001	0.8750	0.9482	0.9048	0.9008	0.9528	0.5280	0.583	0.5970	0.5760
Overall Volume	0.9861	0.9105	0.0001	0.9161	0.9036	0.9100	0.9228	0.9103	0.6320	0.631	0.5490	0.5630
Group ICA	0.9915	0.9295	0.0001	0.9000	0.9571	0.9269	0.9139	0.9639	0.7150	0.743	0.6940	0.6390

Sn, Sensitivity; Sp, Specificity; SVM-L, linear support vector machine; SVM-RBF, support vector machine with radial basis function kernel, LDA, linear discriminant analysis; WC, Weighted Concatenation; Acc, Accuracy; PPV, positive predictive value; NPV, Negative predictive value; GCOR, global average functional connectivity; ICA, independent component analysis; WM, white matter; STD, standard deviation; SC, subcortical; RF, random forest.