TAMA: A Human-AI Collaborative Thematic Analysis Framework Using Multi-Agent LLMs for Clinical Interviews
This addresses the need for efficient thematic analysis in healthcare settings, particularly for rare diseases like AAOCA, by reducing manual workload while enhancing quality, though it is incremental as it builds on existing LLM-assisted methods.
The paper tackled the problem of automating thematic analysis for clinical interviews, which is resource-intensive, by proposing TAMA, a human-AI collaborative framework using multi-agent LLMs, and demonstrated that it outperforms existing LLM-assisted approaches with higher thematic hit rate, coverage, and distinctiveness.
Thematic analysis (TA) is a widely used qualitative approach for uncovering latent meanings in unstructured text data. TA provides valuable insights in healthcare but is resource-intensive. Large Language Models (LLMs) have been introduced to perform TA, yet their applications in healthcare remain unexplored. Here, we propose TAMA: A Human-AI Collaborative Thematic Analysis framework using Multi-Agent LLMs for clinical interviews. We leverage the scalability and coherence of multi-agent systems through structured conversations between agents and coordinate the expertise of cardiac experts in TA. Using interview transcripts from parents of children with Anomalous Aortic Origin of a Coronary Artery (AAOCA), a rare congenital heart disease, we demonstrate that TAMA outperforms existing LLM-assisted TA approaches, achieving higher thematic hit rate, coverage, and distinctiveness. TAMA demonstrates strong potential for automated TA in clinical settings by leveraging multi-agent LLM systems with human-in-the-loop integration by enhancing quality while significantly reducing manual workload.