Quantifying Rodda and Graham Gait Classification from 3D Makerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort

2026-05-11

AI Summary

This study addresses the limitations of traditional three-dimensional instrumented gait analysis—namely its high cost and limited accessibility—and the lack of objective, quantitative standards in clinical observation. To overcome these challenges, we propose the first markerless gait analysis method based on single-view clinical videos, leveraging deep learning to reconstruct 3D joint kinematics and directly predict z-scores for knee and ankle joints as required by the Rodda and Graham classification system. Requiring no specialized equipment, this approach enables scalable gait abnormality screening and longitudinal monitoring. Evaluated on 152 children (1,058 limbs), the model achieved R² = 0.80 (CCC = 0.89) for knee z-scores and R² = 0.57 (CCC = 0.72) for ankle z-scores; it also attained an AUROC of 0.88 for detecting excessive knee flexion and 43% accuracy in the seven-class Rodda–Graham classification.

Abstract

Cerebral Palsy (CP) is a neurological disorder of movement and the most common cause of lifelong physical disability in childhood. Approximately 75% of children with CP are ambulatory, and accurate gait assessment is central to preserving walking function, which deteriorates by mid-adulthood in a quarter to half of adults with CP. The Rodda and Graham classification system quantifies sagittal-plane gait deviations using ankle and knee z-scores derived from 3D Instrumented Gait Analysis (3D-IGA), but 3D-IGA is expensive and limited to specialized centers, while observational assessment shows only moderate inter-rater agreement. We developed a markerless gait analysis pipeline that quantifies Rodda and Graham knee and ankle z-scores directly from single-view clinical gait videos. Across 1,058 bilateral limb samples from 529 trials of 152 children (88 male, 63 female; age 12.1 $\pm$ 4.0 years; 60 distinct primary diagnoses, cerebral palsy the most common at $n=54$), the sagittal-view model achieved $R^2 = 0.80 \pm 0.02$ and CCC $= 0.89 \pm 0.02$ for knee z-scores and $R^2 = 0.57 \pm 0.02$ and CCC $= 0.72 \pm 0.02$ for ankle z-scores against 3D-IGA. Binary screening for excess knee flexion achieves AUROC $= 0.88$, correctly identifying 83% of affected children, and applying Rodda and Graham rules yields $43 \pm 1$% 7-class accuracy with macro-AUROC $= 0.78 \pm 0.01$, ankle prediction error remaining the primary bottleneck. Beyond cross-sectional screening, continuous z-scores support longitudinal trajectory tracking across visits, providing a quantitative substrate for monitoring disease progression and treatment response unavailable from observational scales. These results demonstrate the feasibility of video-based z-score estimation, excess-flexion screening, and longitudinal trajectory tracking as a path toward scalable, objective gait assessment in low-resource clinical settings.

Problem

• gait assessment
• cerebral palsy
• Rodda and Graham classification
• markerless motion capture
• clinical video analysis

Innovation

• markerless gait analysis
• single-view video
• Rodda and Graham classification
• z-score estimation
• longitudinal trajectory tracking