Graph Attention Network-Based Detection of Autism Spectrum Disorder

Abigail Kelly; Ramchandra Rimal; Arpan Sainju

stat.APMar 27, 2026

Graph Attention Network-Based Detection of Autism Spectrum Disorder

Authors: Abigail Kelly, Ramchandra Rimal, Arpan Sainju

Organizations: Computational and Data Science, Middle Tennessee State University, 1301 E. Main St., Murfreesboro, 37132, TN, USA. · Department of Mathematical Sciences, Middle Tennessee State University, 1301 E. Main St., Murfreesboro, 37132, TN, USA.

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by atypical brain connectivity. One of the crucial steps in addressing ASD is its early detection. This study introduces a novel computational framework that employs an Attention-Based Graph Convolutional Network, referred to as the GATGraphClassifier, for detecting ASD. We utilize Functional Magnetic Resonance Imaging (fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE) repository to construct functional connectivity matrices using Pearson correlation, which captures interactions between various brain regions. These matrices are then transformed into graph representations, where the nodes and edges represent the brain regions and functional connections, respectively. The GATGraphClassifier employs attention mechanisms to identify critical connectivity patterns, thereby enhancing the model's interpretability and diagnostic accuracy. Our proposed framework demonstrates superior performance across all standard classification metrics compared to existing state-of-the-art methods. Notably, we achieved an average accuracy of 88.79% on the test data over 30 independent runs, surpassing the benchmark model's performance by 12.27%. In addition, we identified the crucial brain regions associated with ASD, consistent with the previous studies, and a few novel regions. This study not only contributes to the advancement of ASD detection but also shows the potential for broader adaptability of GATGraphClassifier in analyzing complex relational data in various fields, where understanding intricate connectivity and interaction patterns is essential.

Figures & tables

Layer(s)	Details	Output Shape	Activation
Input	-	(N, 316)	-
GAT Block (1)	GATConv (8 heads), BatchNorm, Dropout (p=0.1)	(N, 2048)	ELU
GAT Blocks (2–7)	GATConv (8 heads), BatchNorm, Dropout (p=0.2)	(N, 2048)	ELU
Pooling	Global Mean Pool	(N, 2048)	-
FC1	Linear (2048 → 1024), Dropout (p=0.2)	(N, 1024)	ReLU
FC2	Linear (1024 → 2)	(N, 2)	LogSoftmax

Table 1: GAT-Based Model Architecture

Metric	Average	Minimum	Maximum	Standard Deviation
Accuracy	88.79	79.55	96.59	3.72
Precision	86.50	75.00	95.24	4.34
Recall	90.16	75.61	97.56	5.02
AUC	0.96	0.90	0.99	0.02
F1 Score	0.88	0.78	0.96	0.04

Table 2: Performance Metrics of our Model

Method	Accuracy	Precision	Recall	AUC
ASD-DiagNet ( Eslami et al., 2019 )	69.07	65.25	69.58	0.71
ASD-SWNet ( Zhang et al., 2024 )	76.52	76.15	80.65	0.81
Hi-GCN ( Jiang et al., 2020 )	72.63	65.16	70.54	0.79
GCN ( Parisot et al., 2018 )	70.58	68.32	74.29	0.72
Our Approach	88.79	86.50	90.16	0.96

Table 3: Performance of our Model vs. Existing Models (from ( Zhang et al., 2024 ) )

Shapley (with Score)	Attention (with Score)
Vermis 8 ( $3.294\times 10^{-4}$ )	Vermis 6 (3.706)
Cingulum Ant R ( $3.292\times 10^{-4}$ )	Vermis 8 (3.658)
Temporal Inf L ( $2.004\times 10^{-4}$ )	Vermis 9 (3.625)
SupraMarginal R ( $1.947\times 10^{-4}$ )	Temporal Inf R (3.558)
Supp Motor Area L ( $1.800\times 10^{-4}$ )	Cerebelum 4 5 R (3.444)

Table 4: Top 5 Most Important Brain Regions based on Shapley Score and Attention Mechanism Score

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Metric	Average	Minimum	Maximum	Standard Deviation
Accuracy	46.45	42.05	51.17	2.40
Precision	46.27	43.90	48.78	1.30
Recall	94.23	87.80	100.00	2.92
AUC	0.46	0.29	0.62	0.07
F1 Score	0.62	0.59	0.96	0.02

Appendix

Table 5: Performance metrics of GCN model

Explore similar work

Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning
Mar 16, 2026Ansar Rahman, Hassan Shojaee-Mend, Sepideh HatamikiaMultimodal Graph Learning Multimodal Fusion
Department of Medicine, Danube Private University (DPU), Krems, Austria · Department of Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria · Department of Medical Informatics, Faculty of Medicine, Gonabad University of Medical Sciences, Gonabad, Iran +1
Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks
Mar 3, 2026Syeda Hareem Madani, Noureen Bibi, Adam Rafiq Jeraj +3Autism Spectrum Disorder Neuroimaging
Salim Habib University · VentureDive · National University of Computer and Emerging Sciences
D-GATNet: Interpretable Temporal Graph Attention Learning for ADHD Identification Using Dynamic Functional Connectivity
Mar 27, 2026Qurat Ul Ain, Alptekin Temizel, Soyiba JawedClassification Neuroimaging
Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan · Graduate School of Informatics, Middle East Technical University, 06800, Ankara, Turkey

Mar 16, 2026J/K move · Enter open · S save

Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning

Ansar Rahman, Hassan Shojaee-Mend, Sepideh Hatamikia

Department of Medicine, Danube Private University (DPU), Krems, Austria · Department of Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria · Department of Medical Informatics, Faculty of Medicine, Gonabad University of Medical Sciences, Gonabad, Iran+1

Multimodal Graph Learning Multimodal Fusion Autism Spectrum Disorder Cross-Modal Attention

Open paper AskPDF arXiv

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition characterized by atypical functional brain connectivity and subtle structural alterations. rs-fMRI has been widely used to identify disruptions in large-scale brain networks, while structural MRI provides complementary information about morphological organization. Despite their complementary nature, effectively integrating these heterogeneous imaging modalities within a unified framework remains challenging. This study proposes a multimodal graph learning framework that preserves the dominant role of functional connectivity while integrating structural imaging and phenotypic information for ASD classification. The proposed framework is evaluated on ABIDE-I dataset. Each subject is represented as a node within a population graph. Functional and structural features are extracted as modality-specific node attributes, while inter-subject relationships are modeled using a pairwise association encoder (PAE) based on phenotypic information. Two Edge Variational GCNs are trained to learn subject-level embeddings. To enable effective multimodal integration, we introduce a novel asymmetric transformer-based cross-attention mechanism that allows functional embeddings to selectively incorporate complementary structural information while preserving functional dominance. The fused embeddings are then passed to a MLP for ASD classification. Using stratified 10-fold cross-validation, the framework achieved an AUC of 87.3% and an accuracy of 84.4%. Under leave-one-site-out cross-validation (LOSO-CV), the model achieved an average cross-site accuracy of 82.0%, outperforming existing methods by approximately 3% under 10-fold cross-validation and 7% under LOSO-CV. The proposed framework effectively integrates heterogeneous multimodal data from the multi-site ABIDE-I dataset, improving automated ASD classification across imaging sites.

Abstract

Explore similar work

Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning

Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks

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