D-GATNet: Interpretable Temporal Graph Attention Learning for ADHD Identification Using Dynamic Functional Connectivity

2026-03-27

AI Summary

This study addresses the limitations of existing automated ADHD neuroimaging diagnostic methods, which often overlook the time-varying nature of brain networks and lack interpretability. To this end, we propose D-GATNet, a novel framework that constructs dynamic functional connectivity graph sequences using sliding-window Pearson correlations, captures spatial dependencies via graph attention networks, and models temporal dynamics through one-dimensional convolution combined with a temporal attention mechanism. For the first time, our approach integrates multi-level interpretability analysis—encompassing graph attention weights, region-of-interest (ROI) importance scores, and temporal attention patterns. Evaluated on the ADHD-200 Beijing dataset, D-GATNet achieves a balanced accuracy of 85.18% ± 5.64 and an AUC of 0.881, outperforming current state-of-the-art methods while revealing critical functional abnormalities in the cerebellum and the default mode network.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder whose neuroimaging-based diagnosis remains challenging due to complex time-varying disruptions in brain connectivity. Functional MRI (fMRI) provides a powerful non-invasive modality for identifying functional alterations. Existing deep learning (DL) studies employ diverse neuroimaging features; however, static functional connectivity remains widely used, whereas dynamic connectivity modeling is comparatively underexplored. Moreover, many DL models lack interpretability. In this work, we propose D-GATNet, an interpretable temporal graph-based framework for automated ADHD classification using dynamic functional connectivity (dFC). Sliding-window Pearson correlation constructs sequences of functional brain graphs with regions of interest as nodes and connectivity strengths as edges. Spatial dependencies are learned via a multi-layer Graph Attention Network, while temporal dynamics are modeled using 1D convolution followed by temporal attention. Interpretability is achieved through graph attention weights revealing dominant ROI interactions, ROI importance scores identifying influential regions, and temporal attention emphasizing informative connectivity segments. Experiments on the Peking University site of the ADHD-200 dataset using stratified 10-fold cross-validation with a 5-seed ensemble achieved 85.18% +_5.64 balanced accuracy and 0.881 AUC, outperforming state-of-the-art methods. Attention analysis reveals cerebellar and default mode network disruptions, indicating potential neuroimaging biomarkers.

Problem

• ADHD
• dynamic functional connectivity
• interpretable deep learning
• fMRI
• brain graph

Innovation

• Dynamic Functional Connectivity
• Graph Attention Network
• Temporal Attention
• Interpretable Deep Learning
• ADHD Classification