Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks

2025-10-02

AI Summary

Existing graph neural network (GNN)-based models for psychiatric diagnosis exhibit poor interpretability and low clinical credibility. Method: This paper proposes CONCEPTNEURO—a novel framework that constructs functional brain connectomes from resting-state fMRI data and, for the first time, integrates large language models with domain-specific neuroscience knowledge to automatically extract clinically meaningful functional subgraph concepts. It employs concept encoding, knowledge-guided filtering, and an interpretable classifier to achieve end-to-end prediction with intrinsic explanation. Contribution/Results: Evaluated on multiple adolescent psychiatric datasets, CONCEPTNEURO significantly outperforms conventional GNNs in diagnostic accuracy. Crucially, it generates neurobiologically plausible, disorder-specific interpretations of brain connectivity patterns—aligned with established clinical knowledge—thereby facilitating hypothesis generation and supporting downstream clinical validation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Nearly one in five adolescents currently live with a diagnosed mental or behavioral health condition, such as anxiety, depression, or conduct disorder, underscoring the urgency of developing accurate and interpretable diagnostic tools. Resting-state functional magnetic resonance imaging (rs-fMRI) provides a powerful lens into large-scale functional connectivity, where brain regions are modeled as nodes and inter-regional synchrony as edges, offering clinically relevant biomarkers for psychiatric disorders. While prior works use graph neural network (GNN) approaches for disorder prediction, they remain complex black-boxes, limiting their reliability and clinical translation. In this work, we propose CONCEPTNEURO, a concept-based diagnosis framework that leverages large language models (LLMs) and neurobiological domain knowledge to automatically generate, filter, and encode interpretable functional connectivity concepts. Each concept is represented as a structured subgraph linking specific brain regions, which are then passed through a concept classifier. Our design ensures predictions through clinically meaningful connectivity patterns, enabling both interpretability and strong predictive performance. Extensive experiments across multiple psychiatric disorder datasets demonstrate that CONCEPTNEURO-augmented GNNs consistently outperform their vanilla counterparts, improving accuracy while providing transparent, clinically aligned explanations. Furthermore, concept analyses highlight disorder-specific connectivity patterns that align with expert knowledge and suggest new hypotheses for future investigation, establishing CONCEPTNEURO as an interpretable, domain-informed framework for psychiatric disorder diagnosis.

Problem

• Developing interpretable neuropsychiatric diagnostic tools using brain connectivity
• Enhancing graph neural networks with clinically meaningful connectivity concepts
• Providing transparent disorder-specific explanations for psychiatric diagnosis

Innovation

• LLM-generated functional connectivity concepts
• Concept classifier using structured brain subgraphs
• Interpretable GNN framework with clinical alignment