DW-DGAT: Dynamically Weighted Dual Graph Attention Network for Neurodegenerative Disease Diagnosis

2026-01-15

AI Summary

This work proposes a dynamic weighted dual-graph attention network to address key challenges in the early diagnosis of Parkinson’s disease and Alzheimer’s disease, including heterogeneity in multimodal data, inconsistency between neuroimaging and phenotypic information, and class imbalance. The method integrates three types of structured multimodal biomarkers and constructs a micro–macro dual-graph attention architecture operating at both the brain-region and subject levels. A dynamic class-weighting mechanism is introduced to adaptively mitigate the impact of imbalanced class distributions. Leveraging a generalizable multimodal fusion strategy and a stable loss function, the proposed approach achieves state-of-the-art performance on the PPMI and ADNI datasets, significantly improving early diagnostic accuracy.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Parkinson's disease (PD) and Alzheimer's disease (AD) are the two most prevalent and incurable neurodegenerative diseases (NDs) worldwide, for which early diagnosis is critical to delay their progression. However, the high dimensionality of multi-metric data with diverse structural forms, the heterogeneity of neuroimaging and phenotypic data, and class imbalance collectively pose significant challenges to early ND diagnosis. To address these challenges, we propose a dynamically weighted dual graph attention network (DW-DGAT) that integrates: (1) a general-purpose data fusion strategy to merge three structural forms of multi-metric data; (2) a dual graph attention architecture based on brain regions and inter-sample relationships to extract both micro- and macro-level features; and (3) a class weight generation mechanism combined with two stable and effective loss functions to mitigate class imbalance. Rigorous experiments, based on the Parkinson Progression Marker Initiative (PPMI) and Alzhermer's Disease Neuroimaging Initiative (ADNI) studies, demonstrate the state-of-the-art performance of our approach.

Problem

• neurodegenerative disease
• early diagnosis
• multi-metric data
• data heterogeneity
• class imbalance

Innovation

• dual graph attention network
• dynamic weighting
• multi-metric data fusion
• class imbalance mitigation
• neurodegenerative disease diagnosis