Table 2. Summary of results.

Shown are leave-one-out cross-validation accuracy, sensitivity, and specificity based on the testing dataset for the three feature-based machine learning classifiers. No feature selection was conducted and WM voxels of the entire brain were used for classification. For RF, the 95% confidence intervals (CI) were also reported based on the 100 random trials.

	Deep learning	SVM	RF
Accuracy	0.845	0.724	0.810 (0.759–0.862)
Sensitivity	0.760	0.640	0.800 (0.699–0.880)
Specificity	0.909	0.788	0.818 (0.772–0.879)