A novel semi-automated classifier of hip osteoarthritis on DXA images shows expected relationships with clinical outcomes in UK Biobank

Abstract

Objective Conventional scoring methods for radiographic hip osteoarthritis (rHOA) are subjective and show inconsistent relationships with clinical outcomes. To provide a more objective rHOA scoring method, we aimed to develop a semi-automated classifier based on dual-energy X-ray absorptiometry (DXA) images, and confirm its relationships with clinical outcomes. Methods Hip DXAs in UK Biobank (UKB) were marked up for osteophyte area from which acetabular, superior and inferior femoral head osteophyte grades were derived. Joint space narrowing (JSN) grade was obtained automatically from minimum joint space width (mJSW) measures. Clinical outcomes related to rHOA comprised hip pain, hospital diagnosed OA (HES OA) and total hip replacement (THR). Logistic regression and Cox proportional hazard modelling were used to examine associations between overall rHOA grade (0–4; derived from combining osteophyte and JSN grades), and the clinical outcomes. Results 40 340 individuals were included in the study (mean age 63.7), of whom 81.2% had no evidence of rHOA, while 18.8% had grade ≥1 rHOA. Grade ≥1 osteophytes at each location and JSN were associated with hip pain, HES OA and THR. Associations with all three clinical outcomes increased progressively according to rHOA grade, with grade 4 rHOA and THR showing the strongest association [57.70 (38.08–87.44)]. Conclusions Our novel semi-automated tool provides a useful means for classifying rHOA on hip DXAs, given its strong and progressive relationships with clinical outcomes. These findings suggest DXA scanning can be used to classify rHOA in large DXA-based cohort studies supporting further research, with the future potential for population-based screening.

Machine Learning–Derived Acetabular Dysplasia and Cam Morphology Are Features of Severe Hip Osteoarthritis: Findings From UK Biobank

“…(14) Moreover, we found that rHOA grade ≥1 to 4 is associated with progressively stronger relationships between rHOA and hospital-diagnosed HOA/subsequent THR. (17) This study has several strengths. We investigated relationships of hip shape with different definitions of HOA in a very large study population.…”

“…( 14 ) Moreover, we found that rHOA grade ≥1 to 4 is associated with progressively stronger relationships between rHOA and hospital‐diagnosed HOA/subsequent THR. ( 17 )…”

“…We have since derived four grades of overall rHOA from the sum of osteophyte and mJSW grades (total 12). ( 17 ) In the present study, we used moderate rHOA (grade 2 only) and rHOA grade ≥3, as outcomes.…”

Investigation of the genetic architecture of cam morphology, and its relationship with hip osteoarthritis, using alpha angle as a proxy measure

“…This study included UKB participants with a left hip dual-energy X-ray absorptiometry (DXA) scan (iDXA GE-Lunar, Madison, WI). Outline points were automatically placed around each hip and features of radiographic HOA (rHOA) were measured semi automatically as previously described (15, 17, 18). AA was estimated using the outline points that excluded osteophytes (Figure 1) and a previously published Python code (19, 20).…”

“…Outcome measures of osteoarthritis and observational associations in UK Biobank UKB participants were asked whether they had hip pain for >3months via questionnaire on the same day as their DXA scan. Hospital diagnosed HOA was based on hospital episode statistics (HES) data, termed HES OA, as was total hip replacement (THR) (17). Logistic regression was used to examine associations between AA with clinical outcomes, apart from with THR which was examined using Cox proportional hazard modelling.…”