Scholarlink

<p>The early detection of dementia is a major challenge because prodromal cognitive decline is subtle and variable among individuals. The majority of currently available approaches are based on cross-sectional population cut-offs, expensive neuroimaging studies or cumbersome multimodal deep learning pipelines, limiting the interpretability and external validity for pragmatic deployment in clinical practice. To alleviate these deficiencies, we develop a new AID onset detection which is referred to as AIDCMEDD-PBSD that stands for Artificial Intelligence-Driven Cognitive Monitoring based on Personalized Baseline Shift Detection (PBSD) to identify early D stage. In contrast to traditional classifiers, the presented approach estimates an individual’s cognitive and behavioral baseline, and subsequently identifies prolonged deviations over time thereby facilitating fine-grained longitudinal surveillance. AIDECAMEDD-PBSD consists of a set of low-cost multimodal signals such as short speech elicitation tasks, cognitive microtests, and passive smartphone behavioral markers. Resilient statistical feature normalization with median and MAD is paired with cumulative sum-based shift detection to uncover sustained cognitive differences. The feature-level alerts are then merged through a simple and interpretable logistic regression model, yielding a clinical actionable dementia risk score as well as individual explanations of the features. Experimental results on benchmark speech datasets and longitudinal cognitive assessment data show that the proposed model achieves 94.6% detection accuracy, 92.8% sensitivity, 93.9% specificity which outperforms the traditional cross-sectional machine learning models by a margin of 8–12% in early detection of AD. Significantly, the AIDCMEDD-PBSD detects cognitive decline about 9.4 months before traditional screening cut-offs. The findings support the effectiveness of individualized longitudinal shift modeling as a pragmatic, interpretable and scalable approach for monitoring early dementia in real-world conditions.</p>

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

AIDCMEDD-PBSD: A Personalized Baseline Shift Detection Framework for Continuous Early Dementia Monitoring Using Multimodal Cognitive Signals

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月1日

查看全文
  • S. Maheswari,
  • E. K. Jayachandran,
  • Lekhsha P.,
  • Harshavardhini P. M.

摘要

The early detection of dementia is a major challenge because prodromal cognitive decline is subtle and variable among individuals. The majority of currently available approaches are based on cross-sectional population cut-offs, expensive neuroimaging studies or cumbersome multimodal deep learning pipelines, limiting the interpretability and external validity for pragmatic deployment in clinical practice. To alleviate these deficiencies, we develop a new AID onset detection which is referred to as AIDCMEDD-PBSD that stands for Artificial Intelligence-Driven Cognitive Monitoring based on Personalized Baseline Shift Detection (PBSD) to identify early D stage. In contrast to traditional classifiers, the presented approach estimates an individual’s cognitive and behavioral baseline, and subsequently identifies prolonged deviations over time thereby facilitating fine-grained longitudinal surveillance. AIDECAMEDD-PBSD consists of a set of low-cost multimodal signals such as short speech elicitation tasks, cognitive microtests, and passive smartphone behavioral markers. Resilient statistical feature normalization with median and MAD is paired with cumulative sum-based shift detection to uncover sustained cognitive differences. The feature-level alerts are then merged through a simple and interpretable logistic regression model, yielding a clinical actionable dementia risk score as well as individual explanations of the features. Experimental results on benchmark speech datasets and longitudinal cognitive assessment data show that the proposed model achieves 94.6% detection accuracy, 92.8% sensitivity, 93.9% specificity which outperforms the traditional cross-sectional machine learning models by a margin of 8–12% in early detection of AD. Significantly, the AIDCMEDD-PBSD detects cognitive decline about 9.4 months before traditional screening cut-offs. The findings support the effectiveness of individualized longitudinal shift modeling as a pragmatic, interpretable and scalable approach for monitoring early dementia in real-world conditions.