Table 2 Comparison of the AUCs, accuracies, sensitivities, specificities and BrierScores of the top three individual classifiers in both cross-validation and independent testing.

From: A stacking ensemble machine learning model for predicting postoperative axial pain intensity in patients with degenerative cervical myelopathy

Model

AUC

Accuracy (%)

Sensitivity (%)

Specificity (%)

Brier score

Cross-validation

 EmbeddingLR-RF

0.82

79.59

0.82

0.77

0.18

 EmbeddingRF-MLP

0.83

82.69

0.83

0.83

0.18

 RFE-SVM

0.82

78.42

0.77

0.8

0.18

Independent testing

 EmbeddingLR-RF

0.81

79.97

0.77

0.83

0.18

 EmbeddingRF-MLP

0.81

80.49

0.80

0.81

0.18

 RFE-SVM

0.80

76.10

0.78

0.74

0.19

  1. EmbeddingLR embedding logistic regressor, RF random forest, EmbeddingRF embedding random forest, MLP multilayer perceptron, RFE recursive feature elimination, SVM supported vector machine.
Back to article page