Scholarlink

Brain dysfunction significantly impacts daily activities, as seen in Alzheimer's disease (AD). Despite advancements in research, the lack of reliable diagnostic tools continues to pose challenges for the early detection and classification of this condition. This paper focuses on utilizing machine learning techniques for the preliminary screening and characterization of Alzheimer’s disease. In this article, a methodology has been proposed using PCA and a Random Forest Classifier for AD detection. For reducing dimensions on MRI images PCA is applied, keeping 95% of the data variance in the end. Next the model is trained using “Random Forest Classifier” to classify AD stages using key features. By providing efficient processing and better classification of imbalanced datasets, the proposed approach is suitable for early-stage AD detection.

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

Identification Techniques of the Initial Phase of Alzheimer’s Disease Built on Machine Learning Methods

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mainak Chatterjee,
  • Sagarika Chowdhury,
  • Arunava Banerjee,
  • Sachin Sen,
  • Manik Khan

摘要

Brain dysfunction significantly impacts daily activities, as seen in Alzheimer's disease (AD). Despite advancements in research, the lack of reliable diagnostic tools continues to pose challenges for the early detection and classification of this condition. This paper focuses on utilizing machine learning techniques for the preliminary screening and characterization of Alzheimer’s disease. In this article, a methodology has been proposed using PCA and a Random Forest Classifier for AD detection. For reducing dimensions on MRI images PCA is applied, keeping 95% of the data variance in the end. Next the model is trained using “Random Forest Classifier” to classify AD stages using key features. By providing efficient processing and better classification of imbalanced datasets, the proposed approach is suitable for early-stage AD detection.