Skip to main content

Table 1 Performance metrics of ResoLSTM-Depth model in five-fold cross-validation

From: Deep learning prediction of esophageal squamous cell carcinoma invasion depth from arterial phase enhanced CT images: a binary classification approach

Fold

Accuracy

AUC

Sensitivity

Specificity

F1 score

1

0.882

0.910

0.918

0.845

0.889

2

0.840

0.879

0.891

0.782

0.857

3

0.849

0.892

0.863

0.838

0.830

4

0.866

0.916

0.905

0.821

0.877

5

0.849

0.910

0.844

0.855

0.857

Average

0.857

0.901

0.884

0.828

0.862

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us