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

Abstract

The contribution of shape changes to hip osteoarthritis (HOA) remains unclear, as is the extent to which these vary according to HOA severity. In the present study, we used statistical shape modeling (SSM) to evaluate relationships between hip shape and HOA of different severities using UK Biobank DXA images. We performed a cross-sectional study in individuals with left hip dual-energy X-ray absorptiometry (DXA) scans. Statistical shape modeling (SSM) was used to quantify hip shape. Radiographic HOA (rHOA) was classified using osteophyte size and number and joint space narrowing. HOA outcomes ranged in severity from moderate (grade 2) to severe (grade ≥3) rHOA, hospital-diagnosed HOA, and subsequent total hip replacement (THR). Confounder-adjusted logistic regression between the top 10 hip shape modes (HSMs) and OA outcomes was performed. Further models adjusted for alpha angle (AA) and lateral center-edge angle (LCEA), reflecting acetabular dysplasia and cam morphology, respectively. Composite HSM figures were produced combining HSMs associated with separate OA outcomes. A total of 40,311 individuals were included (mean 63.7 years, 47.8% male), of whom 5.7% had grade 2 rHOA, 1.7% grade ≥3 rHOA, 1.3% hospital-diagnosed HOA, and 0.6% underwent THR. Composite HSM figures for grade 2 rHOA revealed femoral neck widening, increased acetabular coverage, and enlarged lesser and greater trochanters. In contrast, grade ≥3 rHOA, hospital-diagnosed HOA, and THR were suggestive of cam morphology and reduced acetabular coverage. Associations between HSMs depicting cam morphology and reduced acetabular coverage and more severe HOA were attenuated by AA and LCEA adjustment, respectively. Relationships between hip shape and HOA differed according to severity. Notably, cam morphology and acetabular dysplasia were features of severe HOA, but unrelated to moderate disease, suggesting possible prognostic utility.

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

“…Modelling changes are recognised by Croft grading in late-stage HOA (11), however we are not aware of any previous reports describing cam morphology as a specific feature of HOA. That said, in the same set of DXA images, we have recently found that hip shape changes suggestive of cam morphology are associated with more severe forms of HOA (50).…”

Deep learning based phenotyping of medical images improves power for gene discovery of complex disease

“…While computer vision approaches to extract and analyze DXA scan derived phenotypes are not themselves novel 16,17,29,30 , this work is amongst the first to use this approach on a disease for which diagnosis is primarily radiographic, to demonstrate that having a quantitative endophenotype that captures additional information about variation in disease severity improves power for genomic and epidemiological analysis. Although not based on the imaging data, two novel phenotyping methods leveraging deep learning to impute missing data in the UKB and to generate disease liability scores from binary case-control data in the EHR have shown significant boosts in statistical power for genomic studies 31,32 .…”

“…Taking advantage of these developments in computer vision, recent genetic studies have successfully applied these methods to generate image derived phenotypes (IDPs) of distribution of body fat, heart structure, liver fat percentage, and brain morphology, and have linked these novel traits with genome-wide significant loci [10][11][12][13][14] . While some recent studies on musculoskeletal disease employ these novel phenotyping approaches [15][16][17] , neither these nor the studies on other traits have specifically investigated how generating quantitative IDPs that underlie binary disease status could be used to improve power for gene discovery at biobank scale.…”

Hip geometric parameters are associated with radiographic and clinical hip osteoarthritis: findings from a cross-sectional study in UK Biobank

“…An alternative explanation is that the femoral neck is widened as part of, or in parallel to the onset of HOA rather than the widened femoral neck causing HOA. Recent evidence from studies using SSM suggests a wider femoral neck is associated with more severe HOA and separately a genetic study suggested that a genetic predisposition to HOA led to cam-like changes at the femoral head (11,26,27). Both these Hip geometry and its associations with hip osteoarthritis studies suggest that hip shape is associated with but might not be a cause of HOA which has treatment implications.…”

“…; https://doi.org/10.1101/2023.03. 28.23287740 doi: medRxiv preprint Hip geometry and its associations with hip osteoarthritis suitable for ascertaining both hip shape and radiographic HOA (rHOA) measures (10,11). In addition, DXA scans involve lower doses of radiation than traditional radiographs, offering the potential for use in screening.…”