Skip to main content

Table 3 Classification results for HCC/CHB from Hong Kong dataset using SLR

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

  Training results Test results
Accuracy 0.822 (0.031) 0.694
Sensitivity 0.717 (0.071) 0.500
Specificity 0.931 (0.053) 0.913
AUC 0.724 (0.054) 0.607
  1. Training results: we did cross validation within the Hong Kong dataset using SLR with λ = 0.56. Test results: we applied the model trained in Shanghai dataset using sparse logistic regression and took Hong Kong dataset as the test set
  2. AUC Area under the receiver operating characteristic curve; CHB Chronic hepatitis B; HCC Hepatocellular carcinoma; SLR Sparse logistic regression