MHINDR - a DSM5 based mental health diagnosis and recommendation framework using LLM

2025-09-30

AI Summary

This study addresses the challenges of dynamic symptom tracking and low diagnostic interpretability in mental health assessment by proposing the first LLM-driven framework that integrates DSM-5 diagnostic criteria with explicit temporal modeling. Methodologically, it combines named entity recognition, fine-grained temporal information extraction, psychometric feature quantification, and rule-guided reasoning to automatically construct individualized symptom evolution trajectories from mental health forum texts, generating structured diagnostic summaries and evidence-based intervention recommendations. Key contributions include: (1) the first incorporation of DSM-5 criteria and temporal logic into the LLM’s reasoning pipeline, enabling interpretable and verifiable symptom progression inference; and (2) robust support for multi-disorder identification and longitudinal tracking, achieving significantly higher accuracy than baseline models. The framework has been empirically validated in real-world clinical and corporate employee well-being settings, demonstrating high scalability and deployment feasibility.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Mental health forums offer valuable insights into psychological issues, stressors, and potential solutions. We propose MHINDR, a large language model (LLM) based framework integrated with DSM-5 criteria to analyze user-generated text, dignose mental health conditions, and generate personalized interventions and insights for mental health practitioners. Our approach emphasizes on the extraction of temporal information for accurate diagnosis and symptom progression tracking, together with psychological features to create comprehensive mental health summaries of users. The framework delivers scalable, customizable, and data-driven therapeutic recommendations, adaptable to diverse clinical contexts, patient needs, and workplace well-being programs.

Problem

• Automating mental health diagnosis using LLM and DSM-5 criteria
• Tracking symptom progression through temporal information extraction
• Generating personalized therapeutic recommendations for clinical contexts

Innovation

• LLM framework integrates DSM-5 for mental health diagnosis
• Extracts temporal data for symptom progression tracking
• Generates scalable personalized therapeutic recommendations