Skip to main content

Table 3 Performance (five-fold cross validation) of the predictive models for each serotype when using PCC for feature selection. SVM: Support Vector Machine; Sn: Sensitivity; Sp: Specificity; Acc: Accuracy; MCC: Matthews Correlation Coefficient

From: Rapid classification of group B Streptococcus serotypes based on matrix-assisted laser desorption ionization-time of flight mass spectrometry and machine learning techniques

SerotypeFeature selectionClassifiersBin sizeNumber of featuresSnSpAccMCC
I aPCCRandom Forest935100.0%96.1%97.3%0.939
SVM928100.0%99.6%99.8%0.994
I bRandom Forest338100.0%93.3%95.3%0.899
SVM330100.0%99.3%99.5%0.988
IIIRandom Forest6791.0%90.2%90.5%0.795
SVM6791.0%89.7%90.2%0.789
VRandom Forest946100.0%92.3%94.6%0.885
SVM943100.0%99.6%99.8%0.994
VIRandom Forest63197.3%91.6%93.7%0.872
SVM71894.6%93.2%93.7%0.868