Skip to main content

Table 1 Best performance for each classifier and number of features used to yield the same result. SVM = Support Vector Machine; MLP = Multilayer Perceptron; Instance-Based Algorithm (IBA) derived from k-nearest neighbors (IBk) (k = 1, k = 3, k = 5); AUC = Area under the ROC curve

From: Machine learning techniques for computer-aided classification of active inflammatory sacroiliitis in magnetic resonance imaging

ClassifierMetric nameMetric valueNumber of features
SVMAUC0.8672
Sensitivity0.8502
Specificity0.9601
IBk with k = 1AUC0.9006
Sensitivity0.8506
Specificity0.9236
IBk with k = 3AUC0.9325
Sensitivity0.8503
Specificity1.00024
IBk with k = 5AUC0.9152
Sensitivity0.8005
Specificity1.00017
MLPAUC0.926158
Sensitivity0.85150
Specificity0.92316