Scott D. Uhlrich

Deep learning models detect neuromuscular disease and quantify functional impairment from video-derived biomechanics data

This paper develops deep learning models to detect neuromuscular diseases and quantify movement impairment using video-derived biomechanics data from smartphone recordings.

Running with an exotendon reduces compressive knee contact force

This study finds that using an exotendon reduces peak knee compressive contact force during running without affecting shear forces or other joints.

Integrating Machine Learning with Musculoskeletal Simulation Improves OpenCap Video-Based Dynamics Estimation

This paper develops a hybrid machine learning and musculoskeletal simulation framework to improve dynamics estimation from smartphone video during walking, achieving lower error rates than simulation-only or ML-only approaches.

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

Smartphone-video biomechanics (OpenCap) reproduced four timed function tests (r > 0.98) and separated facioscapulohumeral from myotonic dystrophy better than test times (balanced accuracy 82% vs 50%; 129 participants).

Marker Data Enhancement For Markerless Motion Capture

This paper improves motion capture accuracy by enhancing sparse keypoints with a more generalizable marker enhancer trained on a larger dataset.