BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents
This work addresses the barrier of biomechanical analysis for clinicians by making data from accessible motion capture more useful, though it appears incremental as it builds on existing AI and tool integration methods.
The authors tackled the problem of analyzing markerless motion capture data for clinicians without programming expertise by developing BiomechAgent, a code-generating AI agent that uses natural language for tasks like data retrieval, visualization, and clinical reasoning, achieving robust accuracy on data retrieval and visualization tasks.
Markerless motion capture is making quantitative movement analysis increasingly accessible, yet analyzing the resulting data remains a barrier for clinicians without programming expertise. We present BiomechAgent, a code-generating AI agent that enables biomechanical analysis through natural language and allows users to querying databases, generating visualizations, and even interpret data without requiring users to write code. To evaluate BiomechAgent's capabilities, we developed a systematic benchmark spanning data retrieval, visualization, activity classification, temporal segmentation, and clinical reasoning. BiomechAgent achieved robust accuracy on data retrieval and visualization tasks and demonstrated emerging clinical reasoning capabilities. We used our dataset to systematically evaluate several of our design decisions. Biomechanically-informed, domain-specific instructions significantly improved performance over generic prompts, and integrating validated specialized tools for gait event detection substantially boosted accuracy on challenging spatiotemporal analysis where the base agent struggled. We also tested BiomechAgent using a local open-weight model instead of a frontier cloud based LLM and found that perform was substantially diminished in most domains other than database retrieval. In short, BiomechAgent makes the data from accessible motion capture and much more useful and accessible to end users.