Video-Based Biomechanical Analysis Captures Disease-Specific Movement Signatures of Different Neuromuscular Diseases

Area of Science:

• Biomedical Engineering
• Movement Science
• Digital Health

Background:

• Assessing human movement is crucial for diagnosing and monitoring neuromuscular disorders.
• Timed function tests (TFTs) are fast but lack disease-specific movement pattern capture.
• Smartphone video-based biomechanical analysis offers potential for sensitive, clinical-setting movement quantification.

Purpose of the Study:

• To compare the sensitivity and disease-specific capabilities of video-based biomechanical analysis against traditional TFTs.
• To evaluate the potential of smartphone video analysis for diagnosing and monitoring movement-related conditions.

Main Methods:

• Collected observational data from 129 individuals (28 facioscapulohumeral muscular dystrophy, 58 myotonic dystrophy, 43 controls).
• Utilized OpenCap software for smartphone video-based biomechanics capture of nine movements (median 16 minutes/participant).
• Extracted 34 movement features to reproduce four TFTs and identify disease-specific signatures.

Main Results:

• Video-based biomechanics accurately reproduced all four TFTs (r>0.98) with comparable reliability.
• Video metrics demonstrated superior performance in disease classification compared to TFTs (P=0.021).
• Identified disease-specific movement signatures, like gait kinematics, not detectable by TFTs.

Conclusions:

• Smartphone video-based biomechanical analysis provides more sensitive, disease-specific outcomes than current functional movement assessments.
• This technology supports digital health solutions for motor function assessment and monitoring.
• It complements traditional measures, improving care, management, and clinical trial design for movement disorders.