Table 5 Performance comparison of machine learning models for classification.
Network Architecture | Accuracy | Sensitivity | Specificity | Precision | F1-Score | MCC | AUC |
|---|---|---|---|---|---|---|---|
DT | 83.9 | 82.5 | 85.1 | 82.3 | 82.8 | 0.65 | 0.83 |
KNN | 84.5 | 83.3 | 85.9 | 83.1 | 83.6 | 0.66 | 0.84 |
RF | 85.8 | 84.6 | 86.8 | 84.5 | 84.8 | 0.68 | 0.85 |
SVM | 87.5 | 86.5 | 88.4 | 86.4 | 86.8 | 0.71 | 0.87 |
XGboost | 89.6 | 88.9 | 90.3 | 88.7 | 89.0 | 0.73 | 0.89 |
CNN | 91.2 | 91.0 | 91.4 | 90.8 | 91.1 | 0.75 | 0.91 |
DNN | 92.1 | 91.9 | 92.3 | 91.6 | 91.8 | 0.76 | 0.92 |
RNN | 92.7 | 92.4 | 93.0 | 92.2 | 92.4 | 0.78 | 0.93 |
Hybridnet | 93.8 | 93.6 | 94.1 | 93.4 | 93.5 | 0.80 | 0.94 |
DeepFusionNet | 94.2 | 92.5 | 96.1 | 93.8 | 95.0 | 0.846 | 0.96 |
