Scholarlink

<p>Under the “Internet Plus” model, this study aims to develop a proof‑of‑concept intelligent decision‑support system for elderly disease risk assessment, with a specific focus on Alzheimer’s Disease (AD). The primary objective is to evaluate whether blood‑based transcriptomic biomarkers can be translated into an interpretable and scalable risk stratification framework suitable for home‑care and community health settings. Whole‑blood transcriptomic and associated clinical data were obtained from a publicly available microarray dataset comprising 329 individuals (144 AD, 104 MCI, and 81 cognitively normal controls). Transcriptomic features were used exclusively for model training, while clinical variables—including cognitive scores, frailty index, depression scores, and medication adherence—were used post hoc for risk annotation and alert simulation. Rigorous preprocessing and quality control were applied, followed by differential gene expression analysis using the limma framework and biologically informed biomarker selection. A Random Forest classifier trained on selected transcriptomic biomarkers achieved an accuracy of 91.2%, with sensitivity of 88.5% and specificity of 93.6% under stratified five‑fold cross‑validation. Model interpretability was supported through permutation‑based feature importance and SHAP analysis, enabling identification of key genes contributing to risk prediction. Based on probabilistic outputs, subjects were categorized into simplified alert states such as “Alzheimer’s Risk Flagged” and “Monitoring Recommended.” Although real‑time home monitoring data were not collected, the proposed system simulates how omics‑driven risk scores could be integrated into EMR‑compatible and IoT‑enabled care platforms. This study demonstrates a scalable and interpretable computational framework that bridges transcriptomic research and practical decision support, highlighting the potential of non‑invasive, individualized, and deployable risk assessment tools for elderly care, particularly in resource‑limited or home‑based environments.</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

Development and application of an intelligent management and home care system for geriatric diseases under the ‘Internet Plus’ model: big data-based risk prediction and personalized intervention

  • 期刊论文

  • 发表日期：

    2026年5月5日

查看全文
  • Yan Zhu,
  • Yuejia Ru,
  • Juan Xie,
  • Tian Zuo,
  • Xinjie Hong,
  • Dongmei Wang

摘要

Under the “Internet Plus” model, this study aims to develop a proof‑of‑concept intelligent decision‑support system for elderly disease risk assessment, with a specific focus on Alzheimer’s Disease (AD). The primary objective is to evaluate whether blood‑based transcriptomic biomarkers can be translated into an interpretable and scalable risk stratification framework suitable for home‑care and community health settings. Whole‑blood transcriptomic and associated clinical data were obtained from a publicly available microarray dataset comprising 329 individuals (144 AD, 104 MCI, and 81 cognitively normal controls). Transcriptomic features were used exclusively for model training, while clinical variables—including cognitive scores, frailty index, depression scores, and medication adherence—were used post hoc for risk annotation and alert simulation. Rigorous preprocessing and quality control were applied, followed by differential gene expression analysis using the limma framework and biologically informed biomarker selection. A Random Forest classifier trained on selected transcriptomic biomarkers achieved an accuracy of 91.2%, with sensitivity of 88.5% and specificity of 93.6% under stratified five‑fold cross‑validation. Model interpretability was supported through permutation‑based feature importance and SHAP analysis, enabling identification of key genes contributing to risk prediction. Based on probabilistic outputs, subjects were categorized into simplified alert states such as “Alzheimer’s Risk Flagged” and “Monitoring Recommended.” Although real‑time home monitoring data were not collected, the proposed system simulates how omics‑driven risk scores could be integrated into EMR‑compatible and IoT‑enabled care platforms. This study demonstrates a scalable and interpretable computational framework that bridges transcriptomic research and practical decision support, highlighting the potential of non‑invasive, individualized, and deployable risk assessment tools for elderly care, particularly in resource‑limited or home‑based environments.