Table 7. Evaluation of the diagnostic accuracy of the machine learning algorithms using all FrOr parameters in detecting respiratory alterations in patients with sickle cell anemia and normal and abnormal spirometric exams.
| SVML [37, 38] |
ADAB [39] |
1-NN [37, 38, 40] |
RF [39, 40] |
SVMR [40] |
PARZEN [41] |
|
|---|---|---|---|---|---|---|
| Normal exam | ||||||
| AUC | 0.92 | 0.82 | 0.96 | 0.95 | 0.92 | 0.90 |
| Se (%) | 95.2 | 85.7 | 95.2 | 95.2 | 95.2 | 81.0 |
| Sp (%) | 95.7 | 82.6 | 95.7 | 95.7 | 95.7 | 95.7 |
| Abnormal exam | ||||||
| AUC | 0.96 | 0.92 | 0.97 | 0.96 | 0.90 | 0.89 |
| Se (%) | 100.0 | 100.0 | 100.0 | 100.0 | 97.5 | 91.7 |
| Sp (%) | 95.7 | 82.6 | 95.7 | 95.7 | 91.3 | 95.7 |
SVML: Support Vector Machine with Linear Kernel
ADAB: Adaboost with decision tree classifiers
1-NN: K Nearest Neighbor (K = 1)
RF: Random Forests
SVMR: Support Vector Machine with Radial Basis Kernel
PARZEN: Parzen classifier