Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels

BackgroundEnvironmental exposure to heavy metals, such as arsenic, cadmium, and lead, is a known risk factor for cardiovascular diseases.ObjectiveWe aim to examine the associations between heavy metal exposure and the mortality of patients with cardiovascular diseases.MethodsWe analyzed data from th...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Jin, Ling Zhang, Yan Sun, Ya Xu, Man Luo
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1582779/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261524791164928
author Hui Jin
Ling Zhang
Yan Sun
Ya Xu
Man Luo
author_facet Hui Jin
Ling Zhang
Yan Sun
Ya Xu
Man Luo
author_sort Hui Jin
collection DOAJ
description BackgroundEnvironmental exposure to heavy metals, such as arsenic, cadmium, and lead, is a known risk factor for cardiovascular diseases.ObjectiveWe aim to examine the associations between heavy metal exposure and the mortality of patients with cardiovascular diseases.MethodsWe 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.ResultsGradientBoostingSurvival (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.ConclusionMachine 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.
format Article
id doaj-art-f6b725b0affe4e86a8044ffbf788e166
institution OA Journals
issn 2296-2565
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-f6b725b0affe4e86a8044ffbf788e1662025-08-20T01:55:22ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-05-011310.3389/fpubh.2025.15827791582779Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levelsHui Jin0Ling Zhang1Yan Sun2Ya Xu3Man Luo4Mental Health Center, West China Hospital, Sichuan University, Chengdu, Sichuan, ChinaHuai’an No. 3 People’s Hospital, Huaian Second Clinical College, Xuzhou Medical University, Huai’an, Jiangsu, ChinaNanjing Jiangbei Hospital, Affiliated Nanjing Jiangbei Hospital of Xinglin College, Nantong University, Nanjing, Jiangsu, ChinaNanjing Jiangbei Hospital, Affiliated Nanjing Jiangbei Hospital of Xinglin College, Nantong University, Nanjing, Jiangsu, ChinaHuai’an TCM Hospital Affiliated to Nanjing University of Chinese Medicine, Huai'an, Jiangsu, ChinaBackgroundEnvironmental exposure to heavy metals, such as arsenic, cadmium, and lead, is a known risk factor for cardiovascular diseases.ObjectiveWe aim to examine the associations between heavy metal exposure and the mortality of patients with cardiovascular diseases.MethodsWe 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.ResultsGradientBoostingSurvival (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.ConclusionMachine 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.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1582779/fullinterpretable machine learningheavy metalscardiovascular diseasemortalitySHAP
spellingShingle Hui Jin
Ling Zhang
Yan Sun
Ya Xu
Man Luo
Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
Frontiers in Public Health
interpretable machine learning
heavy metals
cardiovascular disease
mortality
SHAP
title Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
title_full Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
title_fullStr Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
title_full_unstemmed Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
title_short Developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
title_sort developing machine learning models for predicting cardiovascular disease survival based on heavy metal serum and urine levels
topic interpretable machine learning
heavy metals
cardiovascular disease
mortality
SHAP
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1582779/full
work_keys_str_mv AT huijin developingmachinelearningmodelsforpredictingcardiovasculardiseasesurvivalbasedonheavymetalserumandurinelevels
AT lingzhang developingmachinelearningmodelsforpredictingcardiovasculardiseasesurvivalbasedonheavymetalserumandurinelevels
AT yansun developingmachinelearningmodelsforpredictingcardiovasculardiseasesurvivalbasedonheavymetalserumandurinelevels
AT yaxu developingmachinelearningmodelsforpredictingcardiovasculardiseasesurvivalbasedonheavymetalserumandurinelevels
AT manluo developingmachinelearningmodelsforpredictingcardiovasculardiseasesurvivalbasedonheavymetalserumandurinelevels