InsightFlow: LLM-Driven Synthesis of Patient Narratives for Mental Health into Causal Models
For mental health clinicians, this work addresses the time-consuming and variable process of manual case formulation by automating causal graph generation, though improvements in temporal reasoning and redundancy reduction are needed.
InsightFlow uses LLMs to automatically generate 5P-aligned causal graphs from psychotherapy transcripts, achieving structural similarity comparable to inter-annotator agreement and high semantic alignment with human expert graphs, with moderate clinical utility.
Clinical case formulation organizes patient symptoms and psychosocial factors into causal models, often using the 5P framework. However, constructing such graphs from therapy transcripts is time consuming and varies across clinicians. We present InsightFlow, an LLM based approach that automatically generates 5P aligned causal graphs from patient-therapist dialogues. Using 46 psychotherapy intake transcripts annotated by clinical experts, we evaluate LLM generated graphs against human formulations using structural (NetSimile), semantic (embedding similarity), and expert rated clinical criteria. The generated graphs show structural similarity comparable to inter annotator agreement and high semantic alignment with human graphs. Expert evaluations rate the outputs as moderately complete, consistent, and clinically useful. While LLM graphs tend to form more interconnected structures compared to the chain like patterns of human graphs, overall complexity and content coverage are similar. These results suggest that LLMs can produce clinically meaningful case formulation graphs within the natural variability of expert practice. InsightFlow highlights the potential of automated causal modeling to augment clinical workflows, with future work needed to improve temporal reasoning and reduce redundancy.