Video-based biomechanical analysis captures disease-specific movement signatures of different neuromuscular diseases

Abstract

Assessing human movement is essential for diagnosing and monitoring movement-related conditions. Timed function tests (TFTs) are among the most widespread assessments due to their speed and simplicity. However, TFTs cannot capture disease-specific movement patterns. Recent advances in smartphone video-based biomechanical analysis allow detailed movement quantification with the ease and speed required for clinical settings. To compare video-based analysis against TFTs, we collected data from 129 individuals: 28 with facioscapulohumeral muscular dystrophy, 58 with myotonic dystrophy, and 43 with typical movement. Video-based movement recordings took a median time of 16 minutes per participant. In addition to reproducing TFTs (r > 0.98), video metrics can outperform TFTs at disease classification (p < 0.001). Video-based analysis also identifies differences in gait kinematics and arm range of motion not evident in TFTs. We conclude that video-based biomechanical analysis can complement existing functional movement assessments and capture more sensitive, disease-specific outcomes from human movement.