Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 27, 2026Scientific ReportsOpen Access

Adaptive neighborhood aggregation graph neural network for early diagnosis of Alzheimer’s disease

View Full Paper
Ask AI
Bookmark
Share

Authors

JSJinhua ShengHZHaowen ZhongQZQiao Zhang

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved early diagnosis of Alzheimer's disease using a novel graph neural network model, suggesting significant clinical implications.

Key Points

  • This research aims to develop a new model for the early diagnosis of Alzheimer's disease by addressing challenges related to subtle brain alterations.
  • Implemented Adaptive Neighborhood Aggregation Graph Neural Network (ANA-GNN) for multimodal AD classification.
  • Incorporated an adaptive neighborhood aggregation module for disease-specific task modeling.
  • Evaluated on a cohort of 707 subjects from the ADNI dataset.
  • ANA-GNN achieved an overall accuracy of 85.23% in early AD diagnosis.
  • The model achieved an F1-score of 85.44%, exceeding state-of-the-art baselines.
  • High-importance regions identified included the hippocampus, amygdala, and posterior cingulate cortex, aligning with known biomarkers.

Cite This Study

Sheng et al. (2026) studied this question.

synapsesocial.com/papers/69eefcaefede9185760d3951https://doi.org/10.1038/s41598-026-50351-2
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Graph neural networks in Alzheimer's disease diagnosis: a review of unimodal and multimodal advances2025
  2. 2Comorbidity-based framework for Alzheimer’sdisease classification using graph neural networks2024 · 1 citations
  3. 3Adaptive Spectral Graph Attention Filtering Network for Alzheimer's Disease Classification Using Multimodal Data2026
  4. 4Advancing Alzheimer's Disease Detection Harnessing Graph Convolutional Networks For Enhanced Early Identification2024 · 2 citations
  5. 5Multiomics-based graph convolutional neural network for Alzheimer’s disease diagnosis and MCI progression prediction2025