Skip to main content
. Author manuscript; available in PMC: 2018 Sep 1.
Published in final edited form as: Hum Mutat. 2017 Jun 28;38(9):1225–1234. doi: 10.1002/humu.23256

Figure 3.

Figure 3

AUC performance of machine learning methods with three Crohn’s association sets (90 loci, 138 loci and 473 SNPs set). 95% confidence intervals of AUCs for each method are shown as error bars in the plot. The methods are conditional probability based Naïve Bayes (NBCP), odds ratio based Naïve Bayes (NBOR), Weka based Naïve Bayes (NBW), Logistic Regression (LR), Neural Net (NN), Random Forest (RF), and consensus machine learning method among NBOR, LR and RF (CONML). The difference in performance between the individual methods is small.