Scholarlink

Alzheimer’s Disease (AD) is a neurodegenerative condition primarily affecting individuals aged 65 and above, resulting in progressive cognitive decline. Accurate and fair early detection of AD progression from Mild Cognitive Impairment (MCI) is vital for timely intervention and healthcare equality. Cerebrospinal Fluid (CSF) biomarkers, Apolipoprotein E4 (APOE4) genetic data, and Mini-Mental State Examination (MMSE) scores are key diagnostic tools commonly used to assess MCI to AD progression. This paper proposes CMAAD-Net (CSF, MMSE score, and APOE4 for AD detection network) by employing an ensemble learning technique. CMAAD-Net achieves a highly predictive accuracy of 0.9321 while keeping all fairness metrics within acceptable thresholds, outperforming other methods. Moreover, variations in biomarker patterns between MCI and AD individuals differ across genders and age groups, highlighting the importance of considering these demographics when detecting progression from MCI to AD.

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

Predicting Progression from Mild Cognitive Impairment to Alzheimer’s Using an AI-Based Multimodal Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Quoc-Toan Nguyen,
  • Nghia Duong-Trung

摘要

Alzheimer’s Disease (AD) is a neurodegenerative condition primarily affecting individuals aged 65 and above, resulting in progressive cognitive decline. Accurate and fair early detection of AD progression from Mild Cognitive Impairment (MCI) is vital for timely intervention and healthcare equality. Cerebrospinal Fluid (CSF) biomarkers, Apolipoprotein E4 (APOE4) genetic data, and Mini-Mental State Examination (MMSE) scores are key diagnostic tools commonly used to assess MCI to AD progression. This paper proposes CMAAD-Net (CSF, MMSE score, and APOE4 for AD detection network) by employing an ensemble learning technique. CMAAD-Net achieves a highly predictive accuracy of 0.9321 while keeping all fairness metrics within acceptable thresholds, outperforming other methods. Moreover, variations in biomarker patterns between MCI and AD individuals differ across genders and age groups, highlighting the importance of considering these demographics when detecting progression from MCI to AD.