Skip to main content
. 2023 May 24;14:1151728. doi: 10.3389/fimmu.2023.1151728

Table 2.

Performance metrics for five models in the validation dataset.

Model AUC (SD) Accuracy (SD) Sensitivity (SD) Specificity (SD) PPV (SD) NPV (SD) F1 score (SD) Kappa (SD)
XGBoost 0.956 (0.089) 0.887 (0.157) 0.933 (0.133) 1.000 (0.000) 1.000 (0.000) 0.850 (0.200) 0.960 (0.080) 0.790 (0.283)
RandomForest 0.922 (0.097) 0.887 (0.157) 0.867 (0.163) 1.000 (0.000) 1.000 (0.000) 0.850 (0.200) 0.920 (0.098) 0.790 (0.283)
GNB:Gaussian Naive Bayes; 0.889 (0.141) 0.860 (0.196) 0.867 (0.163) 1.000 (0.000) 0.900 (0.200) 0.833 (0.211) 0.874 (0.170) 0.723 (0.391)
logistic 0.889 (0.141) 0.893 (0.137) 0.933 (0.133) 0.933 (0.133) 0.933 (0.133) 0.867 (0.163) 0.920 (0.098) 0.790 (0.273)
SVM 0.889 (0.141) 0.893 (0.137) 0.933 (0.133) 0.933 (0.133) 0.933 (0.133) 0.867 (0.163) 0.920 (0.098) 0.790 (0.273)

PPV, Positive Predictive Value; NPV, Negative predictive value; XGBoost, eXtreme Gradient Boosting; SVM, support vector machines; SD, Standard Deviation.