Scholarlink

Background <p>Sarcopenia significantly increases the risk of cognitive impairments in older adults. Early detection of mild cognitive impairment (MCI) in individuals with sarcopenia is essential for timely intervention.</p> Aims <p>To develop an accurate prediction model for screening MCI in individuals with sarcopenia.</p> Methods <p>We employed machine learning and deep learning techniques to analyze data from 570 patients with sarcopenia from the China Health and Retirement Longitudinal Study (CHARLS). Our model forecasts MCI incidence over the next four years, categorizing patients into low and high-risk groups based on their risk levels.</p> Results <p>The model was constructed using CHARLS data from 2011 to 2015, incorporating eight validated variables. It outperformed logistic regression, achieving an Area Under the Curve (AUC) of 0.708 (95% CI: 0.544–0.844) for the test set and accurately classifying patients’ risk in the training set. The deep learning model demonstrated a low false-positive rate of 10.23% for MCI in higher-risk groups. Independent validation using 2015–2018 CHARLS data confirmed the model’s efficacy, with an AUC of 0.711 (0.95 CI, 0.588–0.823). An online tool to implement the model is available at <a href="http://47.115.214.16:8000/">http://47.115.214.16:8000/</a>.</p> Conclusions <p>This deep learning model effectively predicts MCI risk in individuals with sarcopenia, facilitating early interventions. Its accuracy aids in identifying high-risk individuals, potentially enhancing patient care.</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

A prediction model for the risk of developing mild cognitive impairment in older adults with sarcopenia: evidence from the CHARLS

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月8日

查看全文
  • Xinyue Liu,
  • Jingyi Ni,
  • Baicheng Wang,
  • Rui Yin,
  • Jinlin Tang,
  • Qi Chu,
  • Lianghui You,
  • Zhenggang Wu,
  • Yan Cao,
  • Chenbo Ji

摘要

Background

Sarcopenia significantly increases the risk of cognitive impairments in older adults. Early detection of mild cognitive impairment (MCI) in individuals with sarcopenia is essential for timely intervention.

Aims

To develop an accurate prediction model for screening MCI in individuals with sarcopenia.

Methods

We employed machine learning and deep learning techniques to analyze data from 570 patients with sarcopenia from the China Health and Retirement Longitudinal Study (CHARLS). Our model forecasts MCI incidence over the next four years, categorizing patients into low and high-risk groups based on their risk levels.

Results

The model was constructed using CHARLS data from 2011 to 2015, incorporating eight validated variables. It outperformed logistic regression, achieving an Area Under the Curve (AUC) of 0.708 (95% CI: 0.544–0.844) for the test set and accurately classifying patients’ risk in the training set. The deep learning model demonstrated a low false-positive rate of 10.23% for MCI in higher-risk groups. Independent validation using 2015–2018 CHARLS data confirmed the model’s efficacy, with an AUC of 0.711 (0.95 CI, 0.588–0.823). An online tool to implement the model is available at http://47.115.214.16:8000/.

Conclusions

This deep learning model effectively predicts MCI risk in individuals with sarcopenia, facilitating early interventions. Its accuracy aids in identifying high-risk individuals, potentially enhancing patient care.