Skip to main content

Table 1 Results of each algorithm model after LASSO dimensionality reduction

From: Radiomics models for diagnosing microvascular invasion in hepatocellular carcinoma: which model is the best model?

  TP FN FP TN Accuracy Sensitivity Specificity
LASSO+DT 20 6 8 24 75.86% 76.92% 75.00%
LASSO+Bayes 13 10 8 27 68.97% 56.52% 77.14%
LASSO+BPnet 17 9 4 28 77.59% 65.38% 87.50%
LASSO+K-NN 23 7 4 24 81.03% 76.67% 85.71%
LASSO+SVM 23 2 11 22 77.59% 92.00% 66.67%
LASSO+RF 25 2 9 22 81.03% 92.59% 70.97%
LASSO+GBDT 19 4 5 30 84.48% 82.61% 85.71%
  1. *FN False Negative, FP False Positive, TN True Negative, TP True Positive