Skip to main content

Table 3 Performance of diagnostic support models constructed using combinations of candidate biomarkers with various classifiers

From: Gene expression profiling identifies candidate biomarkers for active and latent tuberculosis

Features Classifier Accuracy Sensitivity Precision AUC
PTPRC+ASUN Decision tree 91.49 % 91.5 % 97.7 % 0.943
PTPRC+ASUN+DHX29 Random Forest 93.62 % 93.6 % 93.6 % 0.982
PTPRC+ASUN+DHX29 SVM 95.74 % 95.7 % 96.2 % 0.969
PTPRC+ASUN+DHX29 Naïve Bayes 97.87 % 97.9 % 98 % 0.979
  1. Sensitivity: TP/(TP+FN); Precision: TP/(TP+FP); performance was evaluated by 5-fold cross-validation