Skip to main content

Table 2 The performance of the three models in the trainig set

From: Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Models

Sensitivity (95% CI)

Specificity (95% CI)

Accuracy

AUC (95% CI)

Regularization logistic regression

0.786 (0.691–0.862)

0.708 (0.683–0.733)

0.932

0.788 (0.743–0.833)

Random forest

0.806 (0.714–0.879)

0.601 (0.574–0.628)

0.931

0.744 (0.693–0.795)

Support vector machines

0.612 (0.508–0.709)

0.680 (0.654–0.705)

0.931

0.689 (0.635–0.744)

  1. AUC area under the curve, CI confidence intervals