BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents

TL;DR

BiomechAgent is an AI tool that simplifies biomechanical data analysis by enabling clinicians to query, visualize, and interpret motion capture data using natural language, reducing the need for programming expertise.

Contribution

We introduce BiomechAgent, a novel AI agent that performs biomechanical analysis through natural language, integrating domain-specific tools and benchmarks for clinical and research applications.

Findings

High accuracy in data retrieval and visualization tasks

Emerging capabilities in clinical reasoning

Enhanced performance with biomechanically-informed prompts

Abstract

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.