Download Full Text (1.0 MB)



Gait training in physical therapy is a common standard of practice for new lower limb prosthetic users. Progress is typically assessed through functional outcome measures such as the 10-meter or 6-minute walk tests1. While these tests measure walking speed and endurance, they fall short of capturing gait quality or quantifying gait parameters which literature shows to be of therapeutic value 2,3. Routine access to quantitative gait assessment could provide clinicians with benchmarks to optimize treatment interventions. Traditional gait analysis systems require specialized equipment making them very resource-intensive and inconvenient to operate. Using human pose estimation techniques, we have developed and trained a custom gait analysis system that allows us to measure spatiotemporal gait parameters from video4,5. Lower limb prosthetic users were recorded while ambulating during routine physical therapy appointments. Manual annotation of these videos was used to categorize system performance. The goal of the study was to demonstrate if longitudinal tracking of various gait parameters such as cadence and velocity across numerous subjects showed improvements that reflected coinciding functional outcome measures.

Publication Date



gait training, gait analysis, physical therapy, artificial intelligence


Medicine and Health Sciences | Physical Therapy | Rehabilitation and Therapy


Presented at the 2024 AOA Research Symposium.

Longitudinal Monitoring of Gait Parameters for Lower Limb Prosthetic Users with Physical Therapy Using Video-Based Gait Analysis