Skip to main content

Table 2 Classification results for HCC/CHB using LR, SLR, SVM and SSVM

From: Sparse logistic regression revealed the associations between HBV PreS quasispecies and hepatocellular carcinoma

 

LR

SLR (λ = 0.53)

SVM

SSVM (λ = 0.55)

Test set

Training set

Test set

Test set

Test set

Accuracy

0.688

0.861 (0.032)

0.794

0.777

0.679

Sensitivity

0.718

0.809 (0.051)

0.803

0.775

0.662

Specificity

0.634

0.898 (0.019)

0.780

0.780

0.707

AUC

0.644

0.883 (0.043)

0.795

0.836

0.685

  1. LR: We applied the trained model in training set to the test set (Test set). SLR: We did cross validation within the training set (Training set), and applied the trained model to the test set (Test set). SVM: We applied the trained model in training set to the test set (Test set). SSVM: We did cross validation within the training set, and applied the trained model to the test set (Test set)
  2. AUC Area under the receiver operating characteristic curve; CHB Chronic hepatitis B; HCC Hepatocellular carcinoma; LR Logistic regression; SLR Sparse logistic regression; SVM Support vector machine; SSVM Sparse support vector machine