Identification of Microbial and Proteomic Biomarkers in Early Childhood Caries
Table 2
Performance statistics of three classification models tested on the MS proteomics data. The models were optimized for the average misclassification error (zero-one loss). Four different MS datasets generated for combinations of two affinity chips (CM-10 and Q-10) and two intensity instrument settings (high and low) were analyzed. The statistics include averages and standard deviations of test errors, sensitivities, and specificities of respective classifiers. The averages and standard deviations were calculated across 40 different train/test obtained through the random subsampling approach.
“caries cm 10 high”
Test error
Sensitivity
Specificity
SVM
SVM 100 WLCX
Rnd Forest
“caries cm10 low”
Test error
Sensitivity
Specificity
SVM
SVM 100 WLCX
Rnd Forest
“caries q10 high”
Test error
Sensitivity
Specificity
SVM
SVM 100 WLCX
Rnd Forest
“caries q10 low”
Test error
Sensitivity
Specificity
SVM
SVM 100 WLCX
Rnd Forest
SVM: linear support vector machine. SVM on the top 100 Wilcoxon peaks. Random forest.