Scholarlink

<p>Chronic digestive system diseases (CDSD) are common in older adults, and depressive symptoms are associated with poorer prognosis and quality of life. We developed a machine-learning screening model to identify prevalent depressive symptoms in individuals with CDSD using data from the China Health and Retirement Longitudinal Study (CHARLS). This study included 3762 participants with CDSD from the 2011 survey and examined 45 behavioral, health, psychological, and sociodemographic variables. Feature selection was performed using logistic regression and LASSO regression, and seven modeling approaches were compared. Temporal validation was conducted in participants who newly reported physician-diagnosed CDSD in the 2015 CHARLS wave, with model inputs and depressive symptoms measured in the same wave. Among 3762 participants, 1900 had depressive symptoms. Thirteen variables were retained, including education, residence, life assessment, health assessment, fall history, disability, kidney disease, arthritis, heart disease, eyesight, instrumental activities of daily living, sleep duration, and grip strength. XGBoost was selected as the final model, achieving an area under the curve of 0.793 and an F1-score of 0.724 in the testing set, with acceptable calibration. These findings suggest that machine-learning approaches may support preliminary screening of existing depressive symptoms in people with CDSD.</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 machine-learning-derived online screening tool for depressive symptoms in chronic digestive system diseases patients: a cross-sectional study with temporal validation from CHARLS

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月14日

查看全文
  • Zixun Huang,
  • Liangze Ma,
  • Xin Wang,
  • Mingheng Liu,
  • Shaopeng Zheng,
  • Shugeng Lin,
  • Yukun Ma,
  • Qiangzhou Xu,
  • Limin Ma,
  • Shaobin Chen

摘要

Chronic digestive system diseases (CDSD) are common in older adults, and depressive symptoms are associated with poorer prognosis and quality of life. We developed a machine-learning screening model to identify prevalent depressive symptoms in individuals with CDSD using data from the China Health and Retirement Longitudinal Study (CHARLS). This study included 3762 participants with CDSD from the 2011 survey and examined 45 behavioral, health, psychological, and sociodemographic variables. Feature selection was performed using logistic regression and LASSO regression, and seven modeling approaches were compared. Temporal validation was conducted in participants who newly reported physician-diagnosed CDSD in the 2015 CHARLS wave, with model inputs and depressive symptoms measured in the same wave. Among 3762 participants, 1900 had depressive symptoms. Thirteen variables were retained, including education, residence, life assessment, health assessment, fall history, disability, kidney disease, arthritis, heart disease, eyesight, instrumental activities of daily living, sleep duration, and grip strength. XGBoost was selected as the final model, achieving an area under the curve of 0.793 and an F1-score of 0.724 in the testing set, with acceptable calibration. These findings suggest that machine-learning approaches may support preliminary screening of existing depressive symptoms in people with CDSD.