Table 3 Accuracies, sensitivities, specificities, and area under the curve (AUC) values of prediction models in a leave-one-out cross-validation (LOOCV) of the primary dataset.

From: Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis

Machine learning algorithm

Accuracy

Sensitivity

Specificity

AUC

LR

0.834

0.833

0.836

0.915

SVM

0.866

0.902

0.800

0.932

SNN

0.796

0.833

0.727

0.896

RF

0.815

0.892

0.673

0.902

NB

0.809

0.853

0.727

0.867

Mean ± SD

0.824 ± 0.027

0.863 ± 0.033

0.753 ± 0.065

0.902 ± 0.024

95% CI

0.790–0.858

0.822–0.903

0.672–0.833

0.873–0.932

  1. LR: logistic regression, SVM: support vector machine, SNN: standard neural network, RF: random forest, NB: naïve Bayes.
Back to article page