BiomechAgent: 通过代码生成代理实现AI辅助的生物力学分析
BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents
AI总结：
BiomechAgent通过自然语言和代码生成技术，使无标记运动捕捉数据的生物力学分析更易被非编程用户使用，提升临床应用的效率和准确性。
摘要：
无标记运动捕捉技术正在使定量运动分析变得越来越普及，但分析由此产生的数据仍然是没有编程经验的临床医生的障碍。我们提出了BiomechAgent，这是一种能够通过自然语言进行生物力学分析的代码生成AI代理，使用户能够查询数据库、生成可视化内容，甚至解释数据，而无需编写代码。为了评估BiomechAgent的能力，我们开发了一个系统性的基准测试，涵盖数据检索、可视化、活动分类、时间分割和临床推理。BiomechAgent在数据检索和可视化任务上实现了稳健的准确性，并在临床推理方面展示了新兴的能力。我们使用我们的数据集系统地评估了几个设计决策。具有生物力学知识的领域特定指令显著提高了性能，而整合经过验证的专用工具进行步态事件检测在具有挑战性的时空分析中显著提高了准确性，尤其是在基础代理挣扎的领域。我们还测试了BiomechAgent使用本地开源模型而不是前沿云基于LLM的情况，发现除了数据库检索外，在大多数其他领域表现明显下降。简而言之，BiomechAgent使运动捕捉的数据变得更容易获取，并且对终端用户更加有用和可访问。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
