Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection

<table>Receiver operating characteristic curves of 4 classifiers on 2 cases. Receiver operating characteristic curve and area under curve (AUC) of PLS (blue), LDA (brown), SVM (green), and RF (Purple) on (a) Normal versus CRC and (b) pre versus post.</table>

Evidence-Based Complementary and Alternative Medicine

fig4

Figure 4

Figure 4: Random Forest in Clinical Metabolomics for Phenotypic Discrimination and Biomarker Selection 