Methods | AUC | Sensitivity (%) | Specificity (%) | NPV (%) | PPV (%) | PA (%) |
---|
LR | 0.872 | 79.6 | 79.6 | 89.1 | 65.0 | 79.6 |
BP-C1 | 0.873 | 80.5 | 80.5 | 89.7 | 66.2 | 80.5 |
BP-C2 | 0.873 | 80.0 | 80.4 | 89.4 | 65.6 | 80.3 |
BP-C3 | 0.875 | 80.9 | 80.9 | 89.9 | 66.8 | 80.9 |
SVM-C1 | N/A | N/A | 67.8 | 100.0 | 0.0 | 67.8 |
SVM-C2 | N/A | N/A | 67.8 | 100.0 | 0.0 | 67.8 |
SVM-C3 | N/A | 71.3 | 80.1 | 89.9 | 53.0 | 78.0 |
MS | 0.876 | 78.0 | 82.9 | 88.8 | 68.4 | 81.3 |
AMSA | 0.876 | 79.6 | 81.4 | 89.3 | 67.0 | 80.8 |
MdS | 0.872 | 79.8 | 80.9 | 89.4 | 66.5 | 80.5 |
- C1, C2 and C3 represented combination of all features, combination of features with a high predictive power (AUC > 0.8) and combination of complementary features (MS and SFM) using BP neural network, respectively
-
AUC area under receiver operating characteristic curve, NPV negative predictive value, PPV positive predictive value, PA prediction accuracy, LR logistic regression method, BP back propagation neural network method, SVM support vector machine method, MS mean slope, AMSA amplitude spectral area, Mds median slope, N/A not existing