Jin Hui, Zhang Ling, Sun Yan, Xu Ya, Luo Man
Mental Health Center, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
Huai'an No. 3 People's Hospital, Huaian Second Clinical College, Xuzhou Medical University, Huai'an, Jiangsu, China.
Front Public Health. 2025 May 21;13:1582779. doi: 10.3389/fpubh.2025.1582779. eCollection 2025.
Environmental exposure to heavy metals, such as arsenic, cadmium, and lead, is a known risk factor for cardiovascular diseases.
We aim to examine the associations between heavy metal exposure and the mortality of patients with cardiovascular diseases.
We analyzed data from the NHANES 2003-2018, including urine and blood metal concentrations from 4,924 participants. Five machine learning models-CoxPHSurvival, FastKernelSurvivalSVM, GradientBoostingSurvival, RandomSurvivalForest, and ExtraSurvivalTrees-were used to predict cardiovascular mortality. Model performance was assessed with the concordance index (C-index), integrated Brier score, time-dependent AUC, and calibration curves. SHAP analysis was conducted using a reduced background dataset created via K-means clustering.
GradientBoostingSurvival (GBS) showed the best performance for hypertension (C-index: 0.780, mean AUC: 0.798). RandomSurvivalForest (RSF) was the top model for coronary heart disease (C-index: 0.592, mean AUC: 0.626) and myocardial infarction (C-index: 0.705, mean AUC: 0.743), while CoxPHSurvival excelled for heart failure (C-index: 0.642, mean AUC: 0.672) and stroke (C-index: 0.658, mean AUC: 0.691). ExtraSurvivalTrees performed best in angina (C-index: 0.652, mean AUC: 0.669). Calibration curves confirmed the models' accuracy. SHAP analysis identified age as the most influential factor, with heavy metals like lead, cadmium, and thallium significantly contributing to risk. A user-friendly web calculator was developed for individualized survival predictions.
Machine learning models, including GradientBoostingSurvival, RandomSurvivalForest, CoxPHSurvival, and ExtraSurvivalTrees, demonstrated strong performance in predicting mortality risk for various cardiovascular diseases. Key metals were identified as significant risk factors in cardiovascular risk assessment.
环境暴露于重金属，如砷、镉和铅，是已知的心血管疾病风险因素。
我们旨在研究重金属暴露与心血管疾病患者死亡率之间的关联。
我们分析了2003 - 2018年美国国家健康与营养检查调查（NHANES）的数据，包括4924名参与者的尿液和血液金属浓度。使用五种机器学习模型——CoxPH生存模型、快速核生存支持向量机（FastKernelSurvivalSVM）、梯度提升生存模型（GradientBoostingSurvival）、随机生存森林（RandomSurvivalForest）和额外生存树（ExtraSurvivalTrees）——来预测心血管死亡率。通过一致性指数（C指数）、综合Brier评分、时间依赖AUC和校准曲线评估模型性能。使用通过K均值聚类创建的简化背景数据集进行SHAP分析。
梯度提升生存模型（GBS）在预测高血压方面表现最佳（C指数：0.780，平均AUC：0.798）。随机生存森林（RSF）是预测冠心病（C指数：0.592，平均AUC：0.626）和心肌梗死（C指数：0.705，平均AUC：0.743）的最佳模型，而CoxPH生存模型在预测心力衰竭（C指数：0.642，平均AUC：0.672）和中风（C指数：0.658，平均AUC：0.691）方面表现出色。额外生存树在预测心绞痛方面表现最佳（C指数：0.652，平均AUC：0.669）。校准曲线证实了模型的准确性。SHAP分析确定年龄是最有影响力的因素，铅、镉和铊等重金属对风险有显著贡献。开发了一个用户友好的网络计算器用于个性化生存预测。
包括梯度提升生存模型、随机生存森林、CoxPH生存模型和额外生存树在内的机器学习模型在预测各种心血管疾病的死亡风险方面表现出强大性能。关键金属被确定为心血管风险评估中的重要风险因素。
