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 2 TASOAC participant baseline characteristics

	Total (n = 229)	Progressors^a (n = 71)	No-progressors^a (n = 158)	p-value
Age, years	62 ± 7	63 ± 7	61 ± 7	0.155
Gender, man, % (n)	48 (109)	37 (26)	53 (83)	0.032^b
BMI, kg/m²	27.5 ± 4.5	28.3 ± 5.0	27.0 ± 4.1	0.127
WOMAC
Pain (0–20)	1.3 ± 2.5	1.7 ± 2.8	1.2 ± 2.4	0.045
Function (0–68)	4.4 ± 9.0	5.6 ± 10.4	3.8 ± 8.3	*0.055*
Stiffness (0–8)	0.7 ± 1.3	1.0 ± 1.5	0.5 ± 1.2	0.002
Total (0–96)	6.4 ± 12.4	8.3 ± 14.0	5.5 ± 11.6	0.027
Joint space width, mm	4.7 ± 1.0	3.8 ± 0.8	5.1 ± 0.8	< 0.0001
Joint space narrowing, score^c	0.5 ± 0.5	1.0 ± 0.2	0.3 ± 0.5	< 0.0001

BMI Body mass index, WOMAC Western Ontario and McMaster Universities Osteoarthritis Index, mm Medial minimum, n Number of participants
^aStructural progressors and non-progressors were as defined in the “Methods” section
Kellgren-Lawrence was unavailable for the Tasmanian Older Adult Cohort Study (TASOAC) cohort. Continuous variables were compared using the Student’s t-test/Mann–Whitney test; ^bproportions were compared using the chi-squared test/Fisher’s exact test; p-values compared progressors from the no-progressors, and a p ≤ 0.050 (in bold) were considered statistically different. The p-value in italic indicates that it did not quite reach the statistical significance
^cThe joint space narrowing (JSN) scoring was 0–2, as described [37]

ISSN: 1741-7015