Research Article
Radial Basis Function Artificial Neural Network for the Investigation of Thyroid Cytological Lesions
Table 5
Performance indices for the RBF ANN for the training and test sets and for both sets combined.
| ā | Training set | Test set | Both sets |
| Sensitivity (%) | 82.51 | 81.37 | 81.94 | Specificity (%) | 94.59 | 90.01 | 92.29 | PPV (%) | 89.48 | 81.74 | 85.47 | NPV (%) | 90.65 | 89.78 | 90.22 | FPR (%) | 5.41 | 9.99 | 7.71 | FNR (%) | 17.49 | 18.63 | 18.06 | OA (%) | 90.26 | 86.94 | 88.60 | PLR | 15.25 | 8.14 | 10.63 | NLR | 0.18 | 0.21 | 0.20 | Odds ratio | 82.47 | 39.34 | 54.29 |
|
|