Skip to main content
Fig. 3 | BMC Medicine

Fig. 3

From: Single nucleotide polymorphism genes and mitochondrial DNA haplogroups as biomarkers for early prediction of knee osteoarthritis structural progressors: use of supervised machine learning classifiers

Fig. 3

Sensitivity analysis using the support vector machine. a Representation of the different input combinations. Model number (No.) 1 includes all 12 variables, and one variable is removed in each of the others. A black rectangle indicates the used variable, while the white cells the non-used variable. In b and c, accuracy data in the training (train) and testing (test) stages of the developed support vector machine (SVM) with the different variable combinations using the whole (all) population (n = 901) is shown. The ovals in b and c indicate the models having a lower accuracy when the given variable is removed. BMI, body mass index

Back to article page