Scholarlink

Alzheimer’s disease (AD) is a prevalent brain illness that is frequently connected with maturing and is related with cognitive decline and mental debilitation. The review’s fundamental goal is to utilize AI methods to use mental testing for early ID of Alzheimer’s disease. A CNN and CNN + LSTM are two models that are constructed and evaluated utilizing a dataset. To improve grouping execution, a stacking classifier that joins random forest and Multilayer Perceptron is utilized. The results exhibit how much our outfit approach works on the accuracy of early Alzheimer’s disease diagnosis. Assessment boundaries incorporate 99.5% accuracy, 98.7% precision, 99.1% recall, and 99.2% F1-score to refine current methodologies and accomplish a significant forward leap in early Alzheimer’s diagnosis.

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

Alzheimer’s Disease Identification at Early Stage Using Machine Learning-Based Cognitive Features and Feature Extraction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jyothi Gattoji,
  • L. Arokia Jesu Prabhu,
  • Vijender Solanki

摘要

Alzheimer’s disease (AD) is a prevalent brain illness that is frequently connected with maturing and is related with cognitive decline and mental debilitation. The review’s fundamental goal is to utilize AI methods to use mental testing for early ID of Alzheimer’s disease. A CNN and CNN + LSTM are two models that are constructed and evaluated utilizing a dataset. To improve grouping execution, a stacking classifier that joins random forest and Multilayer Perceptron is utilized. The results exhibit how much our outfit approach works on the accuracy of early Alzheimer’s disease diagnosis. Assessment boundaries incorporate 99.5% accuracy, 98.7% precision, 99.1% recall, and 99.2% F1-score to refine current methodologies and accomplish a significant forward leap in early Alzheimer’s diagnosis.