Identification of Gait Abnormalities in Patients with Hip Osteoarthritis Using a Monocular Vision 3D Motion Capture System

This study aimed to compare the accuracy of video-based kinematic measurements using artificial intelligence (AI) between patients with hip osteoarthritis (OA) and healthy participants, and to compare the gait abnormality estimated from video data with that calculated using optical three-dimensional motion capture (MOCAP) data. This study used open-access datasets of MOCAP and video data including 20 patients with hip OA and 20 healthy participants. Video data were processed using the MYoACT application to extract marker data. The mean absolute error (MAE) of joint angles between MOCAP and MYoACT data was calculated. In patients with hip OA, the modified Gait Abnormality Score (mGAS) for each joint angle was calculated by averaging the absolute differences between each patient’s value and the mean value of healthy participants, divided by the standard deviation of healthy participants, across the entire gait cycle. No significant difference in the MAE was observed between groups. In patients with hip OA, the mGAS showed no significant difference between MYoACT and MOCAP data. These findings suggest that AI-driven video-based kinematic measurements show no clear difference in the accuracy between patients with hip OA and healthy participants, and demonstrate the potential to identify gait abnormalities.