Search papers, labs, and topics across Lattice.
InsightFlow uses LLMs to automatically generate causal graphs of patient symptoms and psychosocial factors from psychotherapy transcripts, aligned with the 5P framework. The generated graphs achieve structural similarity comparable to inter-annotator agreement and high semantic alignment with human-generated graphs, as validated against 46 expert-annotated transcripts. Expert evaluations indicate moderate completeness, consistency, and clinical utility, suggesting LLMs can assist in clinical case formulation.
LLMs can now generate clinically meaningful causal models of patient narratives with comparable quality to human experts, potentially automating a time-consuming clinical task.
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.
