Gait Disorder Assessment Based on a Large-Scale Clinical Trial: WiFi vs. Video vs. Doctor's Visual Inspection

Neurological gait disorders can affect a large population, with devastating consequences on the quality of life. In this paper, we are interested in fundamentally understanding the potential of emerging sensing modalities (e.g., WiFi) for neurological gait disorder assessment. Towards this goal, we conduct a one-year-long clinical trial in collaboration with the Neurology Associates of Santa Barbara, the results of which are detailed in this paper. More specifically, our medical campaign encompasses 114 real subjects and a wide spectrum of disorders (e.g., Parkinson's, Neuropathy, Post Stroke, Dementia, and Arthritis). We then develop the first WiFi-based gait disorder sensing system of its kind, distinguished by its scope of validation with a large and diverse patient cohort. To ensure generalizability, we mainly leverage publicly-accessible online videos of gait disorders for training, and develop a video-to-RF pipeline to convert them to synthetic RF data. We then extensively test the system in a neurology center (i.e., the Neurology Associates of Santa Barbara). In addition, we provide a 1-1 comparison with a vision-based system, by developing a vision-based gait disorder assessment system under the same exact conditions (e.g., same subjects, etc), a comparison crucial for developing smart health systems and the first of its kind to our knowledge. We finally contrast both systems with the accuracy of neurologists when basing evaluation solely on the visual inspection of the gait, by designing a large survey and distributing it to an extensive network of neurologists, thus offering the first such apples-to-apples comparison of these three sensing modalities. Overall, the findings can shape the integration of new sensing modalities into medical practice, and pave the way toward equitable healthcare.