Validation of Automated Mobility Assessment Using a Single 3D Sensor

Jiun-Yu Kao, Minh Nguyen, Luciano Nocera, Cyrus Shahabi, Antonio Ortega, Carolee J. Winstein, Ibrahim Sorkhoh, Yu-Chen Chung, Yi-An Chen, Helen Bacon

Abstract: Reliable mobility assessment is essential to diagnose or optimize treatment in persons affected by mobility disorders, e.g., for musculo-skeletal disorders. In this work, we present a system that is able to automatically assess mobility using a single 3D sensor. We validate the system ability to assess mobility and predict the medication state of Parkinson’s disease patients while using a relatively small number of motion tasks. One key component of our system is a graph-based feature extraction technique that can capture the dynamic coordination between parts of the body while providing results that are easier to interpret than those obtained with other data-driven approaches. We further discuss the system and the study design, highlighting aspects that provide insights for developing mobility assessment applications in other contexts.