Skip to main content
. 2025 Sep 1;16:1630863. doi: 10.3389/fimmu.2025.1630863

Table 8.

The performance of the ML models developed using mRMR-selected features on the validation dataset.

Model Sensitivity Specificity Accuracy AUC Kappa MCC

  • DT

  • 55.93

  • 66.67

  • 59.78

  • 0.65

  • 0.21

  • 0.22

  • RF

  • 59.32

  • 69.70

  • 63.04

  • 0.73

  • 0.27

  • 0.28

  • LR

  • 66.10

  • 75.76

  • 69.57

  • 0.72

  • 0.39

  • 0.40

  • XGB

  • 55.93

  • 75.76

  • 63.04

  • 0.71

  • 0.28

  • 0.31

  • KN

  • 57.63

  • 72.73

  • 63.04

  • 0.69

  • 0.27

  • 0.29

  • GNB

  • 79.66

  • 39.39

  • 65.22

  • 0.60

  • 0.20

  • 0.21

  • ET

  • 52.54

  • 72.73

  • 59.78

  • 0.74

  • 0.22

  • 0.24

  • SVC

  • 66.10

  • 69.70

  • 67.39

  • 0.71

  • 0.34

  • 0.34

  • MLP

  • 64.41

  • 66.67

  • 65.22

  • 0.67

  • 0.29

  • 0.30

DT, decision tree; RF, random forest; LR, logistic regression; XGB, extreme gradient boosting; KNN, k-nearest neighbors; GNB, Gaussian Naïve Baise; ET, extra tree; SVC, support vector classifier; MLP, multilayer perceptron; AUC, area under curve; kappa, Cohen’s kappa coefficient; MCC, Mathew’s correlation coefficient.