Skip to main content

Table 3 Performance of different prediction models generated by sixfold cross-validation on the training data set

From: Integrative transcriptomic, proteomic, and machine learning approach to identifying feature genes of atrial fibrillation using atrial samples from patients with valvular heart disease

Classifier Precision Recall F-Measure MCC AUC auPRC TP rate FP rate Kappa statistic
NB 0.869 0.869 0.869 0.729 0.925 0.920 0.869 0.143 0.728
SMO 0.863 0.862 0.862 0.715 0.860 0.814 0.862 0.142 0.715
RF 0.768 0.769 0.768 0.518 0.887 0.881 0.769 0.259 0.516
  1. NB Naive Bayes, SMO sequential minimal optimization, RF random forest, MCC Matthews correlation coefficient, AUC area under receiver operating curve, auPRC area under precision recall curve, TP true positive, FP false positive