Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification

2025-11-18

AI Summary

Existing depression diagnosis models predominantly rely on data-driven graph neural networks, lacking neurobiological interpretability. To address this, we propose NH-GCAT—a novel framework that, for the first time, integrates neuroscience-informed priors into deep learning. It models dynamic, depression-related causal interactions across multi-scale brain organization (regions, circuits, and whole-brain networks) via residual gated fusion, hierarchical circuit encoding, and variational latent causal attention. By jointly leveraging fMRI time-series signals and functional connectivity, NH-GCAT unifies graph neural networks, latent variable modeling, and causal inference to enable interpretable depression identification. Evaluated on the REST-meta-MDD dataset, it achieves 73.3% weighted accuracy and 76.4% AUROC—outperforming state-of-the-art methods—and generates mechanistically grounded, neurobiologically meaningful explanations.

Technology Category

• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Reasoning under Uncertainty: Causality

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Major Depressive Disorder (MDD), affecting millions worldwide, exhibits complex pathophysiology manifested through disrupted brain network dynamics. Although graph neural networks that leverage neuroimaging data have shown promise in depression diagnosis, existing approaches are predominantly data-driven and operate largely as black-box models, lacking neurobiological interpretability. Here, we present NH-GCAT (Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks), a novel framework that bridges neuroscience domain knowledge with deep learning by explicitly and hierarchically modeling depression-specific mechanisms at different spatial scales. Our approach introduces three key technical contributions: (1) at the local brain regional level, we design a residual gated fusion module that integrates temporal blood oxygenation level dependent (BOLD) dynamics with functional connectivity patterns, specifically engineered to capture local depression-relevant low-frequency neural oscillations; (2) at the multi-regional circuit level, we propose a hierarchical circuit encoding scheme that aggregates regional node representations following established depression neurocircuitry organization, and (3) at the multi-circuit network level, we develop a variational latent causal attention mechanism that leverages a continuous probabilistic latent space to infer directed information flow among critical circuits, characterizing disease-altered whole-brain inter-circuit interactions. Rigorous leave-one-site-out cross-validation on the REST-meta-MDD dataset demonstrates NH-GCAT's state-of-the-art performance in depression classification, achieving a sample-size weighted-average accuracy of 73.3% and an AUROC of 76.4%, while simultaneously providing neurobiologically meaningful explanations.

Problem

• Identifying depression from brain networks with neurobiological interpretability
• Modeling depression mechanisms across hierarchical brain spatial scales
• Characterizing disease-altered inter-circuit interactions in whole-brain dynamics

Innovation

• Hierarchical modeling of depression mechanisms at spatial scales
• Residual gated fusion module for local neural oscillations
• Variational latent causal attention for inter-circuit interactions