Table 1 Detailed metrics for lymph node metastasis prediction in early oral tongue cancer.

From: Subnetwork representation learning for discovering network biomarkers in predicting lymph node metastasis in early oral cancer

Measure

Value*

Description

TP

10

# of True positive

TN

19

# of True negative

FP

3

# of False positive

FN

1

# of False negative

Sensitivity

0.9091

\(TPR = \frac{TP}{TP + FN}\)

Specificity

0.8636

\(SPC = \frac{TN}{FP + TN}\)

Precision

0.7692

\(PPV = \frac{TP}{TP + FP}\)

Negative predictive value

0.9500

\(NPV = \frac{TN}{TN + FN}\)

False positive rate

0.1364

\(FPR = \frac{FP}{FP + TN}\)

False discovery rate

0.2308

\(FDR = \frac{FP}{FP + TP}\)

False negative rate

0.0909

\(FNR = \frac{FN}{FN + TP}\)

Accuracy

0.8788

\(ACC = \frac{TP + TN}{P + N}\)

F1 score

0.8333

\(F1 = \frac{2TP}{2TP + FP + FN}\)

  1. * Note that the metrics are not class-balanced.
Back to article page