Table 4 Area under ROC curve for all prediction models.

From: Comparison of machine learning models for the prediction of mortality of patients with unplanned extubation in intensive care units

Model

AUROC

SE

95% CI

ANN

0.846

0.028

0.791–0.902

LR

0.853

0.025

0.804–0.903

RF

0.910

0.022

0.867–0.954

SVM

0.843

0.028

0.787–0.898

  1. AUROC = Area under ROC curve.
  2. SE = Standard Error of area under ROC curve.
  3. CI = Confidence interval.
Back to article page