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

Table 3 Impact effect of the variable synergies in PVBSP forecasting

PVBSP forecasting	Variable 1	Variable 2
Highest impact	Age	BMI, GNL3, MCF2L, FTO
Moderate impact	Age	mtDNA haplogroup, GDF5, SUPT3H, TGFA, TP63
	BMI	TP63, SUPT3H
	GDF5	MCF2L
Lowest impact	TGFA	mtDNA haplogroup, cluster, FTO, GNL3, SUPT3H, MCF2L
	SUPT3H	mtDNA haplogroup, cluster, FTO, GNL3
	GNL3	mtDNA haplogroup, cluster, FTO
	FTO	mtDNA haplogroup, cluster
	Cluster	mtDNA haplogroup

Variable 1 indicates a fixed variable, and variable 2 is a flexible variable that could have an impact along with variable 1
PVBSP Probability values of being structural progressors

ISSN: 1741-7015