Scholarlink

The objective of this study was to develop a prediction model to identify individuals at risk. Three predictive models, including logistic regression (LR), random forest (RF), and XGBoost (XGB), were developed using machine learning models. Discriminative performance of the developed models was evaluated using the area under the curve (AUC) analysis, and the whole dataset was divided into training and test sets in a 7:3 ratio. Binary LR analysis revealed that five risk factors, namely stage, age, fear of infection, family relationship, and perceived health, but not including isolation measures, were significantly associated with severe depression and severe anxiety. In the Delong test analysis, XGB exhibited the highest accuracy in predicting severe depression (AUC = 0.914, 95% confidence interval [CI] = 0.909–0.917) and severe anxiety (AUC = 0.863, 95% CI = 0.858-0.869). The XGB model, which utilized machine learning algorithms, can accurately and effectively identify individuals at risk of developing severe mental disorders of cancer patients during the pandemic.

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

Prediction Models for Severe Depression and Anxiety Risk Among Cancer Patients During the COVID-19 Pandemic: A Nationwide Repeated Cross-Sectional Study

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rujun Zheng,
  • Yuhong Zhou,
  • Sicheng Xu,
  • Xiaoyuan Mei,
  • Fang Cheng,
  • Dongmei Li,
  • Chunhua Woo,
  • Xiaoling Wu,
  • Yan Jiang,
  • Junying Li

摘要

The objective of this study was to develop a prediction model to identify individuals at risk. Three predictive models, including logistic regression (LR), random forest (RF), and XGBoost (XGB), were developed using machine learning models. Discriminative performance of the developed models was evaluated using the area under the curve (AUC) analysis, and the whole dataset was divided into training and test sets in a 7:3 ratio. Binary LR analysis revealed that five risk factors, namely stage, age, fear of infection, family relationship, and perceived health, but not including isolation measures, were significantly associated with severe depression and severe anxiety. In the Delong test analysis, XGB exhibited the highest accuracy in predicting severe depression (AUC = 0.914, 95% confidence interval [CI] = 0.909–0.917) and severe anxiety (AUC = 0.863, 95% CI = 0.858-0.869). The XGB model, which utilized machine learning algorithms, can accurately and effectively identify individuals at risk of developing severe mental disorders of cancer patients during the pandemic.