用多智能体LLM自动分析临床叙事，提升主题质量与可扩展性
Auto-TA: Towards Scalable Automated Thematic Analysis (TA) via Multi-Agent Large Language Models with Reinforcement Learning
- 构建多智能体框架，分工协作提升主题提取质量
- 结合人类反馈强化学习，使主题更贴近真实临床需求
- 适合需要大规模患者叙事分析的医疗研究团队
先天性心脏病（CHD）带来长期复杂挑战，常被传统临床指标忽视。非结构化叙事蕴含丰富的患者与照护者体验信息，但人工主题分析（TA）耗时且难以扩展。我们提出一种全自动化大语言模型（LLM）流水线，实现临床叙事的端到端主题分析，无需人工编码或全文审阅。系统采用新型多智能体架构，由专用LLM智能体承担不同角色，提升主题质量与人类分析的一致性。通过可选的基于人类反馈的强化学习（RLHF），进一步优化主题相关性。该方法支持大规模定性数据的可扩展、以患者为中心分析，并可针对特定临床场景微调LLM。
原文摘要 · Abstract (English)
Congenital heart disease (CHD) presents complex, lifelong challenges often underrepresented in traditional clinical metrics. While unstructured narratives offer rich insights into patient and caregiver experiences, manual thematic analysis (TA) remains labor-intensive and unscalable. We propose a fully automated large language model (LLM) pipeline that performs end-to-end TA on clinical narratives, which eliminates the need for manual coding or full transcript review. Our system employs a novel multi-agent framework, where specialized LLM agents assume roles to enhance theme quality and alignment with human analysis. To further improve thematic relevance, we optionally integrate reinforcement learning from human feedback (RLHF). This supports scalable, patient-centered analysis of large qualitative datasets and allows LLMs to be fine-tuned for specific clinical contexts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。