Cognitive Decline Detection from EEG using Optimized Machine Learning

  • Unique Paper ID: 183259
  • Volume: 12
  • Issue: 3
  • PageNo: 601-606
  • Abstract:
  • Alzheimer’s Disease (AD), a leading cause of cognitive decline among the elderly, necessitates timely diagnosis for effective management and treatment. This study presents a novel non-invasive multimodal deep learning framework that integrates electroencephalography (EEG) signals, cognitive test scores, and magnetic resonance imaging (MRI) features to enhance the early prediction and progression analysis of AD. EEG signals are preprocessed using bandpass filtering and Principal Component Analysis (PCA) for dimensionality reduction, while key features are extracted using Hilbert Transform. These features are then classified using various machine learning algorithms including Linear Discriminant Analysis (LDA), Support Vector Machines (SVM), Artificial Neural Networks (ANN), and others. Among all, LDA combined with PCA achieved the highest classification accuracy of 96.6%. The experimental results highlight the efficacy of EEG-based multimodal analysis in distinguishing between Alzheimer’s, Mild Cognitive Impairment (MCI), and healthy controls. This research underscores the potential of multimodal deep learning systems in advancing early-stage AD diagnostics and provides insights for future clinical deployment.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 12
  • Issue: 3
  • PageNo: 601-606

Cognitive Decline Detection from EEG using Optimized Machine Learning

Related Articles