Skip to main content

Table 2 Performance of the different models on the hold-out test set

From: Radiomics using computed tomography to predict CD73 expression and prognosis of colorectal cancer liver metastases

Model

AUC

Accuracy

Sensitivity

Specificity

F1 score

TabNet

0.79 (95% CI 0.65–0.92)

0.71

0.63

0.79

0.67

XGBoost

0.61 (95% CI 0.45–0.77)

0.60

0.69

0.53

0.61

SVM

0.60 (95% CI 0.44–0.76)

0.49

0.94

0.11

0.63

RF

0.59 (95% CI 0.43–0.75)

0.63

0.75

0.53

0.65

LR

0.51 (95% CI 0.34–0.68)

0.46

0.63

0.32

0.51

  1. AUC area under the curve, TabNet attentive interpretable tabular learning, XGBoost extreme gradient boosting; SVM support vector machine, RF random forest, LR logistic regression
Back to article page

Journal of Translational Medicine

ISSN: 1479-5876

Contact us