Scholarlink

This study aims to develop an AI model that diagnoses Alzheimer’s disease using EEG signals. Alzheimer’s is a progressive neurodegenerative disease characterized by memory loss and cognitive dysfunction, and early diagnosis is critical to slowing the progression of the disease. EEG signals provide essential information in detecting neurological disorders by measuring brain activity non-invasively. This study used correlation matrices obtained from EEG data to distinguish healthy individuals from Alzheimer’s patients. EEG data were processed, a bandpass filter was applied, and average correlation matrices were calculated. The model development process used machine learning algorithms such as SVM, Random Forest, KNN. Multilayer Perceptron (MLP), and Deep Neural Networks. The SVM model obtained the best performance with 94.87% accuracy and 95% F1 score. The results reveal that correlation matrices obtained from EEG signals effectively diagnose Alzheimer’s. These findings significantly contribute to developing EEG-based diagnostic systems and their use in clinical applications.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development of Machine Learning Models for EEG-Based Alzheimer’s Diagnosis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Eren Eroğul,
  • Adem Tekerek

摘要

This study aims to develop an AI model that diagnoses Alzheimer’s disease using EEG signals. Alzheimer’s is a progressive neurodegenerative disease characterized by memory loss and cognitive dysfunction, and early diagnosis is critical to slowing the progression of the disease. EEG signals provide essential information in detecting neurological disorders by measuring brain activity non-invasively. This study used correlation matrices obtained from EEG data to distinguish healthy individuals from Alzheimer’s patients. EEG data were processed, a bandpass filter was applied, and average correlation matrices were calculated. The model development process used machine learning algorithms such as SVM, Random Forest, KNN. Multilayer Perceptron (MLP), and Deep Neural Networks. The SVM model obtained the best performance with 94.87% accuracy and 95% F1 score. The results reveal that correlation matrices obtained from EEG signals effectively diagnose Alzheimer’s. These findings significantly contribute to developing EEG-based diagnostic systems and their use in clinical applications.