Research Article
Usage of Probabilistic and General Regression Neural Network for Early Detection and Prevention of Oral Cancer
Table 1
Performance of PNN/GRNN model for classification of malignant and benign case for oral cancer.
| | Performance estimation parameter | Performance |
| | Positive/negative ratio | 3.0837 | | Accuracy | 99.02% | | True positive (TP) | 75.02% | | True negative (TN) | 24.00% | | False positive (FP) | 0.49% | | False negative (FN) | 0.49% | | Sensitivity | 99.35% | | Specificity | 98.01% | | Geometric mean of sensitivity-specificity | 98.68% | | Positive predictive value (PPV) | 99.35% | | Negative predictive value (NPV) | 98.01% | | Geometric mean of PPV and NPV | 98.68% | | Precision | 99.35% | | Recall | 99.35% | | -measure | 0.9935 | | Area under ROC curve | 0.9974 |
|
|
