Skip to main content
Figure 3 | Journal of Clinical Bioinformatics

Figure 3

From: Metabolomics and partial least square discriminant analysis to predict history of myocardial infarction of self-claimed healthy subjects: validity and feasibility for clinical practice

Figure 3

Quantitative evaluation of the diagnostic performance for putative biomarkers. Receiver operating characteristic (ROC) curve analysis was performed to quantify the diagnostic performance of the nineteen candidate metabolites using PLSDA (A), Support Vector Machine (SVM) (B) and Random Forest (RF) (C). The biomarkers were capable of discriminating the MI from HT with area under curve (AUC) of 0.998, 0.998 and 0.991, with average accuracy of 0.947, 0.961 and 0.963, respectively.

Back to article page

Journal of Clinical Bioinformatics

ISSN: 2043-9113