Table 3. Predictive performance of radiomic modelsa.
AUC (95% CI) | High sensitivity model | High specificity model | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
Sensitivity | Specificity | NPV | PPV | Sensitivity | Specificity | NPV | PPV | |||
SVM | 0.93 (0.924–0.953) | 0.89 | 0.80 | 0.89 | 0.80 | 0.78 | 0.90 | 0.82 | 0.88 | |
LR | 0.93 (0.921–0.953) | 0.89 | 0.85 | 0.90 | 0.84 | 0.78 | 1.0 | 0.83 | 1.0 |
aTotal lesions: 38 (positive: 18/negative: 20). PPV, positive predictive value; NPV, negative predictive value; AUC, areas under the ROC curves; ROC, receiver operating characteristic; LR, logistic regression; SVM, support vector machine.