Using Large Language Models to Create Personalized Networks From Therapy Sessions

2025-12-05

AI Summary

This study addresses the limitation in psychotherapy case conceptualization—its heavy reliance on extensive longitudinal data—by proposing a few-shot, personalized therapeutic network generation method leveraging large language models (LLMs). Methodologically, it introduces a multi-step generative framework: (1) psychological process identification and dimensional annotation via in-context learning; (2) bottom-up thematic extraction and relational modeling through two-stage clustering; and (3) generation of clinically interpretable “explanation-augmented” networks. Evaluated on only 77 therapy dialogues, expert assessments indicate high clinical relevance, novelty, and utility (72–75% agreement), with 90% of clinicians preferring the generated networks. The core contribution lies in overcoming the data dependency bottleneck: this is the first approach to automate the construction of highly interpretable and clinically acceptable personalized therapeutic networks from minimal data, enabling scalable, evidence-informed case conceptualization in resource-constrained settings.

Technology Category

• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent advances in psychotherapy have focused on treatment personalization, such as by selecting treatment modules based on personalized networks. However, estimating personalized networks typically requires intensive longitudinal data, which is not always feasible. A solution to facilitate scalability of network-driven treatment personalization is leveraging LLMs. In this study, we present an end-to-end pipeline for automatically generating client networks from 77 therapy transcripts to support case conceptualization and treatment planning. We annotated 3364 psychological processes and their corresponding dimensions in therapy transcripts. Using these data, we applied in-context learning to jointly identify psychological processes and their dimensions. The method achieved high performance even with a few training examples. To organize the processes into networks, we introduced a two-step method that grouped them into clinically meaningful clusters. We then generated explanation-augmented relationships between clusters. Experts found that networks produced by our multi-step approach outperformed those built with direct prompting for clinical utility and interpretability, with up to 90% preferring our approach. In addition, the networks were rated favorably by experts, with scores for clinical relevance, novelty, and usefulness ranging from 72-75%. Our findings provide a proof of concept for using LLMs to create clinically relevant networks from therapy transcripts. Advantages of our approach include bottom-up case conceptualization from client utterances in therapy sessions and identification of latent themes. Networks generated from our pipeline may be used in clinical settings and supervision and training. Future research should examine whether these networks improve treatment outcomes relative to other methods of treatment personalization, including statistically estimated networks.

Problem

• Automates personalized network creation from therapy transcripts
• Reduces need for intensive longitudinal data collection
• Enhances clinical utility and interpretability of treatment planning

Innovation

• LLMs generate personalized networks from therapy transcripts
• Two-step clustering organizes processes into clinically meaningful networks
• In-context learning identifies psychological processes with minimal training data