Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning
Machine learning exhibits excellent performance in terms of predictive power. We aimed to construct an interpretable machine learning model utilizing National Health and Nutrition Examination Survey data to investigate the relationship between heavy metal exposure and cardiovascular disease (CVD). A...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Ecotoxicology and Environmental Safety |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0147651324016464 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856906428481536 |
|---|---|
| author | Meiyue Shen Yine Zhang Runqing Zhan Tingwei Du Peixuan Shen Xiaochuan Lu Shengnan Liu Rongrong Guo Xiaoli Shen |
| author_facet | Meiyue Shen Yine Zhang Runqing Zhan Tingwei Du Peixuan Shen Xiaochuan Lu Shengnan Liu Rongrong Guo Xiaoli Shen |
| author_sort | Meiyue Shen |
| collection | DOAJ |
| description | Machine learning exhibits excellent performance in terms of predictive power. We aimed to construct an interpretable machine learning model utilizing National Health and Nutrition Examination Survey data to investigate the relationship between heavy metal exposure and cardiovascular disease (CVD). A total of 4600 adults were included in the analysis. The Least Absolute Shrinkage and Selection Operator regression method was employed to select relevant feature variables. Subsequently, six machine learning models were constructed, including random forest, decision tree, gradient boosting decision tree, k-nearest neighbor, support vector machine, and AdaBoost algorithms. Feature importance analysis, partial dependence plot, and shapley additive explanations were integrated to enhance the interpretability of the CVD prediction model. Among all models, the random forest exhibited the best performance, with an accuracy of 90 %, an area under the curve of 0.85, and an F1 score of 0.86. Urine cadmium (Cd), blood lead (Pb), urine thallium (Tl), and urine tungsten (W) were identified as the most significant predictors of CVD, with importance scores of 0.062, 0.057, 0.051, and 0.050, respectively. At the overall level, higher levels of urine Cd, blood Pb, and urine W were associated with an increased risk of CVD, whereas a lower level of urine Tl was linked to a reduced CVD risk. Additionally, the analysis of synergistic effects revealed that Cd was the predominant determinant of CVD risk. The random forest-based CVD prediction model demonstrated excellent predictive power and provided valuable insights for personalized patient care and optimal resource allocation in populations exposed to heavy metals. |
| format | Article |
| id | doaj-art-6a6db19fb882458584ba878354fe2294 |
| institution | Kabale University |
| issn | 0147-6513 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecotoxicology and Environmental Safety |
| spelling | doaj-art-6a6db19fb882458584ba878354fe22942025-02-12T05:29:50ZengElsevierEcotoxicology and Environmental Safety0147-65132025-01-01290117570Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learningMeiyue Shen0Yine Zhang1Runqing Zhan2Tingwei Du3Peixuan Shen4Xiaochuan Lu5Shengnan Liu6Rongrong Guo7Xiaoli Shen8Department of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, ChinaNingxia Center for Disease Control and Prevention, Yinchuan, ChinaQingdao Haici Hospital, Qingdao 266033, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, China; Ningxia Center for Disease Control and Prevention, Yinchuan, China; Qingdao Haici Hospital, Qingdao 266033, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, ChinaDepartment of Epidemiology and Health Statistics, School of Public Health, Qingdao University, Qingdao 266071, China; Correspondence to: Department of Epidemiology and Health Statistics, School of Public Health, Qingdao University, No. 308 Ningxia Rd, Qingdao 266071, China.Machine learning exhibits excellent performance in terms of predictive power. We aimed to construct an interpretable machine learning model utilizing National Health and Nutrition Examination Survey data to investigate the relationship between heavy metal exposure and cardiovascular disease (CVD). A total of 4600 adults were included in the analysis. The Least Absolute Shrinkage and Selection Operator regression method was employed to select relevant feature variables. Subsequently, six machine learning models were constructed, including random forest, decision tree, gradient boosting decision tree, k-nearest neighbor, support vector machine, and AdaBoost algorithms. Feature importance analysis, partial dependence plot, and shapley additive explanations were integrated to enhance the interpretability of the CVD prediction model. Among all models, the random forest exhibited the best performance, with an accuracy of 90 %, an area under the curve of 0.85, and an F1 score of 0.86. Urine cadmium (Cd), blood lead (Pb), urine thallium (Tl), and urine tungsten (W) were identified as the most significant predictors of CVD, with importance scores of 0.062, 0.057, 0.051, and 0.050, respectively. At the overall level, higher levels of urine Cd, blood Pb, and urine W were associated with an increased risk of CVD, whereas a lower level of urine Tl was linked to a reduced CVD risk. Additionally, the analysis of synergistic effects revealed that Cd was the predominant determinant of CVD risk. The random forest-based CVD prediction model demonstrated excellent predictive power and provided valuable insights for personalized patient care and optimal resource allocation in populations exposed to heavy metals.http://www.sciencedirect.com/science/article/pii/S0147651324016464Cardiovascular diseaseHeavy metalsMachine learningRandom forestAdaBoostPartial dependence plot |
| spellingShingle | Meiyue Shen Yine Zhang Runqing Zhan Tingwei Du Peixuan Shen Xiaochuan Lu Shengnan Liu Rongrong Guo Xiaoli Shen Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning Ecotoxicology and Environmental Safety Cardiovascular disease Heavy metals Machine learning Random forest AdaBoost Partial dependence plot |
| title | Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning |
| title_full | Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning |
| title_fullStr | Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning |
| title_full_unstemmed | Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning |
| title_short | Predicting the risk of cardiovascular disease in adults exposed to heavy metals: Interpretable machine learning |
| title_sort | predicting the risk of cardiovascular disease in adults exposed to heavy metals interpretable machine learning |
| topic | Cardiovascular disease Heavy metals Machine learning Random forest AdaBoost Partial dependence plot |
| url | http://www.sciencedirect.com/science/article/pii/S0147651324016464 |
| work_keys_str_mv | AT meiyueshen predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT yinezhang predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT runqingzhan predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT tingweidu predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT peixuanshen predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT xiaochuanlu predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT shengnanliu predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT rongrongguo predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning AT xiaolishen predictingtheriskofcardiovasculardiseaseinadultsexposedtoheavymetalsinterpretablemachinelearning |