Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Journal of Computational Methods in Sciences and Engineering

Multiomics-based graph convolutional neural network for Alzheimer’s disease diagnosis and MCI progression prediction

View Full Paper
Ask AI
Bookmark
Share

Authors

TZT. Zhang

Discussion

Loading...

Member takes

Overview

This analysis demonstrates improved accuracy in Alzheimer's diagnosis and MCI progression prediction using a graph convolutional neural network.

Key Points

  • The CA-GCN model achieved high diagnostic accuracy with an AUC of 0.97, improving Alzheimer's diagnosis.
  • Experimental results showed the model also predicted MCI progression accurately, with an AUC of 0.88.
  • This study utilized a novel adjacency matrix and Chebyshev convolution in the model's construction for better performance.
  • The findings suggest adopting this model could assist in timely treatment decisions, reducing burdens on families.

Cite This Study

T. Zhang (2025) studied this question.

synapsesocial.com/papers/68c1a8fe54b1d3bfb60e1bbehttps://doi.org/10.1177/14727978251364448
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. 1Comorbidity-based framework for Alzheimer’sdisease classification using graph neural networks2024 · 1 citations
  2. 2Advancing Alzheimer's Disease Detection Harnessing Graph Convolutional Networks For Enhanced Early Identification2024 · 2 citations
  3. 3MLC-GCN: Multi-Level Connectomes Based GCN for AD Detection2025
  4. 4Deep Convolutional Curvelet Transform- Based MRI Approach for Early Detection of ALZHEIMER' S Disease2024
  5. 5Graph neural networks in Alzheimer's disease diagnosis: a review of unimodal and multimodal advances2025