EEGDecoder-x: an explainable deep learning framework for cross-subject EEG-based detection of Alzheimer's and Creutzfeldt–Jakob disease - Takeaways - MDSpire

EEGDecoder-x: A Transparent Deep Learning Approach for Cross-Subject Detection of Alzheimer's Disease and Creutzfeldt–Jakob Disease Using EEG Data

  • By

  • Muhammad Suffian

  • Nadia Mammone

  • Cosimo Ieracitano

  • Giovanbattista Gaspare Tripodi

  • Angelo Pascarella

  • Edoardo Ferlazzo

  • Francesco Carlo Morabito

  • July 20, 2026

Share

  • 1

    EEGDecoder-x is an interpretable framework for classifying Alzheimer's disease and Creutzfeldt–Jakob disease using EEG data.

  • 2

    The framework includes EEGDecoder-Net, a hybrid attention network, and EEGDecoder-XAI, an explainability module for model insights.

  • 3

    EEGDecoder-x achieved 97.22% classification accuracy using a Leave-One-Subject-Out evaluation on a dataset of 36 subjects.

  • 4

    The approach addresses challenges of EEG artifacts, subject-independent evaluation, and the need for model interpretability.

  • 5

    EEGDecoder-x combines convolutional neural networks with dual attention mechanisms to capture spatio-temporal dependencies in EEG.

Original Source(s)

EEGDecoder-x: an explainable deep learning framework for cross-subject EEG-based detection of Alzheimer's and Creutzfeldt–Jakob disease

  • by Muhammad Suffian, Nadia Mammone, Cosimo Ieracitano, Giovanbattista Gaspare Tripodi, Angelo Pascarella, Edoardo Ferlazzo, Francesco Carlo Morabito

  • July 20, 2026

Related Content

Sedative medications: a potentially modifiable risk factor for improving neurocognitive outcomes after critical illness in infants and children

Associations between arterial oxygenation and oxidative stress markers in serum and bronchoalveolar lavage fluid of patients with severe brain injury

Small extracellular vesicles proteome reveals persistent inflammatory and coagulopathic dysregulation in long-COVID