Exploring Large Language Models for Automated Gait Analysis

Exploring Large Language Models for Automated Gait Analysis
Rebecca Keilhauer, Michael Lorenz, Carlo Dindorf, Stefan Ernst, Chen-Yu Wang, Paul Messer, Didier Stricker
In: Proceedings of 2nd International Conference of AIxHMC 2025. International Conference on Artificial Intelligence for Medicine, Health, and Care (AIxMHC-2025), October 13-15, Taichung, Taiwan, Province of China, IEEE Xplore, 2025.

Abstract:

Biomechanical gait analysis is a critical tool in orthopedic diagnosis and rehabilitation, particularly for patients undergoing total knee arthroplasty. Traditional assessments, however, are time-intensive, subjective, and reliant on expert interpretation. In this study, we investigate the use of large language models (LLMs), specifically ChatGPT-4o, to generate clinically relevant gait assessments based on spatiotemporal mo- tion data. We collected gait recordings from 11 preoperative knee arthroplasty patients and obtained expert annotations from phys- iotherapists. Using a structured prompt engineering approach, we enabled ChatGPT-4o to produce full-body gait descriptions, which were then evaluated in a blinded study by physiotherapy students and experts teaching gait analysis. Our results show that ChatGPT-4o achieves comparable levels of correctness and clarity to human-generated assessment. Nonetheless, limitations such as the absence of pathological context, and evaluator variability highlight the need for further refinement. This work presents a proof of concept for integrating generative AI into clinical gait analysis and underscores its potential as an assistive tool in physiotherapy and orthopedic diagnostics. Additionally we make the data publicly available.