Table 5 Accuracy of cervical cancer according to different machine learning algorithms
Model | Tool | AUC | CA | F1 | Precision | Recall | Specificity | Support |
|---|---|---|---|---|---|---|---|---|
SVM | Orange | 0.883 | 0.742 | 0.704 | 0.741 | 0.742 | 0.8 | – |
Sklearn | 0.861 | – | 0.85 | 0.87 | 0.85 | – | 72 | |
Random forest | Orange | 0.868 | 0.755 | 0.745 | 0.744 | 0.755 | 0.841 | – |
Sklearn | 0.972 | – | 0.97 | 0.97 | 0.98 | – | 72 | |
Logistic regression | Orange | 0.863 | 0.735 | 0.721 | 0.72 | 0.735 | 0.828 | – |
Sklearn | 1 | – | 1 | 1 | 1 | – | 72 | |
AdaBoost | Orange | 0.86 | 0.742 | 0.737 | 0.737 | 0.742 | 0.828 | – |
Sklearn | 1 | – | 1 | 1 | 1 | – | 72 | |
Naïve Bayes | Orange | 0.851 | 0.621 | 0.627 | 0.642 | 0.621 | 0.836 | – |
Sklearn | 0.958 | – | 0.96 | 0.96 | 0.96 | – | 72 | |
Neural network | Orange | 0.847 | 0.718 | 0.719 | 0.721 | 0.718 | 0.838 | – |
Sklearn | 0.986 | – | 0.99 | 0.99 | 0.98 | – | 72 | |
kNN | Orange | 0.845 | 0.735 | 0.725 | 0.723 | 0.735 | 0.833 | – |
Sklearn | 0.861 | – | 0.85 | 0.87 | 0.85 | – | 72 | |
CN2 rule inducer | Orange | 0.821 | 0.674 | 0.675 | 0.676 | 0.674 | 0.815 | – |
Sklearn | – | – | – | – | – | – | 72 | |
Decision tree | Orange | – | – | – | – | – | – | – |
Sklearn | 0.986 | – | 0.99 | 0.98 | 0.99 | – | 72 | |
Quadratic classifier | Orange | – | – | – | – | – | – | – |
Sklearn | 0.431 | – | 0.3 | 0.22 | 0.5 | – | 72 |