用多智能体大模型自动分析患者访谈，提升主题分析效率。
Automated Healthcare Thematic Analysis using Multi-Agent Large Language Model: Algorithm Development and Evaluation
- 设计三智能体框架，分工生成摘要、初码和主题。
- 在12份心衰患者访谈中，结果接近资深研究者水平。
- 适合需要快速开展定性研究的医疗团队使用。
理解患者体验对推动以患者为中心的护理至关重要。定性主题分析广泛用于探索这些体验，但过程仍耗时、主观且难以扩展。本研究开发并评估了协作主题识别代理（CoTI），一种多智能体大语言模型框架，旨在通过快速生成支持性摘录、初始编码和主题来辅助人工主题分析。CoTI由三个智能体组成：指导者（Instructor）优化指令提示，主题化者（Thematizer）提取支持性摘录并生成每段访谈的初始编码，代码本生成者（CodebookGenerator）将所有访谈中的相似编码归类形成包含主题的代码本。我们主要使用12份心力衰竭患者访谈对CoTI进行评估，其输出与资深研究人员构建的参考标准对比。为进一步探索人机协作，我们在用户端应用中实施了CoTI。结果显示，CoTI生成的支持性摘录、初始编码和主题比初级研究者、基线自然语言处理模型及其他基础大语言模型更接近资深研究者的成果。在一次探索性的人机协作实验中，初级研究者与CoTI合作带来的收益仅略高于CoTI单独运行，可能是因为初级研究者过度依赖CoTI，限制了独立批判性思维。CoTI能通过快速生成供研究人员审阅的支持性摘录、初始编码和主题，显著提升主题分析效率。这些发现凸显了CoTI在可扩展定性研究中的潜力。
原文摘要 · Abstract (English)
Understanding patients experiences is essential for advancing patient-centered care. Qualitative thematic analysis is widely used to explore these experiences, however, the process remains labor-intensive, subjective, and difficult to scale. This study aimed to develop and evaluate Collaborative Theme Identification Agent (CoTI), a multi-agent large language model framework designed to support manual thematic analysis by rapidly generating supporting excerpts, initial codes, and themes. CoTI consists of three agents: Instructor, Thematizer, and CodebookGenerator. The Instructor refines instruction prompts, the Thematizer extracts supporting excerpts and generates initial codes for each transcript, and the CodebookGenerator groups similar codes across all transcripts into a codebook with themes. We evaluated CoTI primarily using 12 heart failure patient transcripts. CoTI-generated outputs were compared against the reference standard developed by senior investigators. To explore human-AI interaction in thematic analysis, we further implemented CoTI in a user-facing application. CoTI generated supporting excerpts, initial codes, and themes that were more similar to those of senior investigators than did the outputs of junior investigators, baseline natural language processing models, and other basic large language models. In an exploratory human-AI collaboration experiment, we found that the collaboration between CoTI and junior investigators provided only marginal gains compared to CoTI alone. A possible hypothesis was that junior investigators may over-rely on CoTI and limit their independent critical thinking. CoTI can improve the efficiency of thematic analysis by rapidly generating supporting excerpts, initial codes, and themes for human researchers review. These findings highlight CoTI potential as a useful tool for scalable qualitative research.
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。