Skip to main content
. 2022 Nov 22;10:1082794. doi: 10.3389/fbioe.2022.1082794

FIGURE 6.

FIGURE 6

ROC curves of SVM methods to classification. (A) ROC curve of training set, the AUC were 0.974 in DM (sensitivity and specificity were 0.84 and {"MCI”: 0.82, “DM”: 0.92, “N": 0.97}), 0.939 in MCI (sensitivity and specificity were 0.85 and {"MCI”: 0.82, “DM”: 0.92, “N": 0.97}), 0.983 in N (sensitivity and specificity were 0.75 and {"MCI”: 0.82, “DM”: 0.92, “N": 0.97}) respectively; (B) ROC curve of validation set, the AUC were 0.846 in DM (sensitivity and specificity were 0.88 and {"MCI”: 0.86, “DM”: 0.76, “N": 0.95}), 0.857 in MCI (sensitivity and specificity were 0.73 and {"MCI”: 0.86, “DM”: 0.76, “N": 0.95}), 0.825 in N (sensitivity and specificity were 0.50 and {"MCI”: 0.86, “DM”: 0.76, “N": 0.95}) respectively.