用大规模健康数据和机器学习，找出心理社会因素与慢性肾病的关联。
Population Health-Based Machine Learning Reveals Associations Between Psychosocial Factors and Chronic Kidney Disease
- 融合多源健康调查数据，用集成模型预测肾病风险
- 模型准确率超72%，识别出血压、心理健康等关键因素
- 结果可解释，适合临床风险筛查与政策制定
慢性肾病进展隐匿，严重损害生活质量，早期检测对改善患者预后至关重要。本研究分两部分，结合大规模远程医疗数据与先进机器学习技术，实现自我报告肾病状态的分类，并识别疾病的关键驱动因素。基于行为风险因素监测系统（BRFSS 2021：438,693样本；BRFSS 2019：418,268样本）和国家健康访谈调查（NHIS 2021：29,482样本；NHIS 2020：31,568样本）的选定特征，采用九种前沿插补方法处理缺失数据，通过采样策略缓解类别不平衡问题。定制化的堆叠集成模型在平衡准确率上达到72.56%-76.12%，对应AUROC为79.59%-82.29%。结合SHapley Additive exPlanations（SHAP）分析与临床评审，识别出定期体检、年龄、血压及心理健康压力指标为关键预测因子。研究构建了稳健且可解释的肾病风险分层框架，为疾病相关因素提供了可操作的洞察。
原文摘要 · Abstract (English)
Chronic kidney disease (CKD) progresses silently and severely undermines quality of life, making early detection critical for improving patient outcomes. We present a two-part study that combines large-scale telehealth data with advanced machine learning to both classify self-reported CKD status and identify key drivers of disease. Using selected features from the Behavioral Risk Factor Surveillance System (BRFSS 2021: 438,693 samples; BRFSS 2019: 418,268 samples) and the National Health Interview Survey (NHIS 2021: 29,482 samples; NHIS 2020: 31,568 samples), we addressed missing data with nine state-of-the-art imputation methods and mitigated class imbalance via sampling strategies. Our customized stacked ensemble model achieved balanced accuracy of 72.56-76.12%, with corresponding AUROC scores of 79.59-82.29%. SHapley Additive exPlanations (SHAP) analysis, followed by clinical review, highlighted critical predictors, including regular medical check-ups, age, blood pressure, and indicators of mental health stress. These findings deliver a robust and interpretable framework for CKD risk stratification and provide actionable insights into its associated factors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。