Deep neural networks enable quantitative movement analysis using single-camera videos

TLDR

Neurological and musculoskeletal diseases impair movement, limiting function and social participation, and quantitative motion assessment is essential but currently restricted to expensive, specialist systems. We present a machine‑learning method that predicts clinically relevant motion parameters from a single ordinary video of a patient. The models predict walking speed, cadence, knee flexion angle, and GDI with correlations of r = 0.73–0.83, approaching theoretical limits imposed by natural variability. These results show that commodity cameras can deliver accurate, scalable gait analysis, expanding access in clinics and at home and enabling large‑scale studies of neurological and musculoskeletal disorders.

Abstract

Abstract Many neurological and musculoskeletal diseases impair movement, which limits people’s function and social participation. Quantitative assessment of motion is critical to medical decision-making but is currently possible only with expensive motion capture systems and highly trained personnel. Here, we present a method for predicting clinically relevant motion parameters from an ordinary video of a patient. Our machine learning models predict parameters include walking speed ( r = 0.73), cadence ( r = 0.79), knee flexion angle at maximum extension ( r = 0.83), and Gait Deviation Index (GDI), a comprehensive metric of gait impairment ( r = 0.75). These correlation values approach the theoretical limits for accuracy imposed by natural variability in these metrics within our patient population. Our methods for quantifying gait pathology with commodity cameras increase access to quantitative motion analysis in clinics and at home and enable researchers to conduct large-scale studies of neurological and musculoskeletal disorders.