Comparisons Among Machine Learning Models for the Prediction of Hypercholestrolemia Associated with Exposure to Lead, Mercury, and Cadmium

Overview

Journal Int J Environ Res Public Health

Publisher MDPI

Specialties Environmental Health
Public Health

Date 2019 Jul 28

PMID 31349672

Citations 2

Authors

Hyejin Park

Kisok Kim

Affiliations

Soon will be listed here.

Abstract

Lead, mercury, and cadmium are common environmental pollutants in industrialized countries, but their combined impact on hypercholesterolemia (HC) is poorly understood. The aim of this study was to compare the performance of various machine learning (ML) models to predict the prevalence of HC associated with exposure to lead, mercury, and cadmium. A total of 10,089 participants of the Korea National Health and Nutrition Examination Surveys 2008-2013 were selected and their demographic characteristics, blood concentration of metals, and total cholesterol levels were collected for analysis. For prediction, five ML models, including logistic regression (LR), k-nearest neighbors, decision trees, random forests, and support vector machines (SVM) were constructed and their predictive performances were compared. Of the five ML models, the SVM model was the most accurate and the LR model had the highest area under receiver operating characteristic (ROC) curve of 0.718 (95% CI: 0.688-0.748). This study shows the potential of various ML methods to predict HC associated with exposure to metals using population-based survey data.

Citing Articles

Misuse of Cardiac Lipid upon Exposure to Toxic Trace Elements-A Focused Review.

Renu K, Mukherjee A, Wanjari U, Vinayagam S, Veeraraghavan V, Vellingiri B Molecules. 2022; 27(17).

PMID: 36080424 PMC: 9457865. DOI: 10.3390/molecules27175657.

Machine Learning Methods for Hypercholesterolemia Long-Term Risk Prediction.

Dritsas E, Trigka M Sensors (Basel). 2022; 22(14).

PMID: 35891045 PMC: 9322993. DOI: 10.3390/s22145365.

References

Fujiyoshi N, Arima H, Satoh A, Ojima T, Nishi N, Okuda N . Associations between Socioeconomic Status and the Prevalence and Treatment of Hypercholesterolemia in a General Japanese Population: NIPPON DATA2010. J Atheroscler Thromb. 2018; 25(7):606-620. PMC: 6055037. DOI: 10.5551/jat.42531. View

Kim J, Kim S, Bae M, Kim J, Cho K . Cadmium exposure exacerbates severe hyperlipidemia and fatty liver changes in zebrafish via impairment of high-density lipoproteins functionality. Toxicol In Vitro. 2017; 47:249-258. DOI: 10.1016/j.tiv.2017.11.007. View

Poursafa P, Ataee E, Motlagh M, Ardalan G, Tajadini M, Yazdi M . Association of serum lead and mercury level with cardiometabolic risk factors and liver enzymes in a nationally representative sample of adolescents: the CASPIAN-III study. Environ Sci Pollut Res Int. 2014; 21(23):13496-502. DOI: 10.1007/s11356-014-3238-4. View

Kim J, Kang J . The lead accumulation and hematological findings in juvenile rock fish Sebastes schlegelii exposed to the dietary lead (II) concentrations. Ecotoxicol Environ Saf. 2015; 115:33-9. DOI: 10.1016/j.ecoenv.2015.02.009. View

Choi Y, Park S . Environmental Exposures to Lead, Mercury, and Cadmium and Hearing Loss in Adults and Adolescents: KNHANES 2010-2012. Environ Health Perspect. 2017; 125(6):067003. PMC: 5743444. DOI: 10.1289/EHP565. View

Diacomanolis V, Noller B, Ng J . Bioavailability and pharmacokinetics of arsenic are influenced by the presence of cadmium. Chemosphere. 2014; 112:203-9. DOI: 10.1016/j.chemosphere.2014.04.013. View

Zhou Z, Lu Y, Pi H, Gao P, Li M, Zhang L . Cadmium Exposure is Associated with the Prevalence of Dyslipidemia. Cell Physiol Biochem. 2016; 40(3-4):633-643. DOI: 10.1159/000452576. View

Zhuang P, Lu H, Li Z, Zou B, McBride M . Multiple exposure and effects assessment of heavy metals in the population near mining area in South China. PLoS One. 2014; 9(4):e94484. PMC: 3984172. DOI: 10.1371/journal.pone.0094484. View

He L, Chen Z, Dai B, Li G, Zhu G . Low-level lead exposure and cardiovascular disease: the roles of telomere shortening and lipid disturbance. J Toxicol Sci. 2018; 43(11):623-630. DOI: 10.2131/jts.43.623. View

10.

Cho Y . Fish consumption, mercury exposure, and the risk of cholesterol profiles: findings from the Korea National Health and Nutrition Examination Survey 2010-2011. Environ Health Toxicol. 2017; 32:e2017014. PMC: 5704572. DOI: 10.5620/eht.e2017014. View

11.

Hong D, Cho S, Park S, Kim S, Park S . Hair mercury level in smokers and its influence on blood pressure and lipid metabolism. Environ Toxicol Pharmacol. 2013; 36(1):103-7. DOI: 10.1016/j.etap.2013.03.007. View

12.

Al-Zubaidi E, Rabee A . The risk of occupational exposure to mercury vapor in some public dental clinics of Baghdad city, Iraq. Inhal Toxicol. 2017; 29(9):397-403. DOI: 10.1080/08958378.2017.1369601. View

13.

Tsai T, Kuo C, Pan W, Wu T, Lin P, Wang S . Type 2 diabetes occurrence and mercury exposure - From the National Nutrition and Health Survey in Taiwan. Environ Int. 2019; 126:260-267. DOI: 10.1016/j.envint.2019.02.038. View

14.

Houston M . The role of mercury and cadmium heavy metals in vascular disease, hypertension, coronary heart disease, and myocardial infarction. Altern Ther Health Med. 2007; 13(2):S128-33. View

15.

Galatzer-Levy I, Ma S, Statnikov A, Yehuda R, Shalev A . Utilization of machine learning for prediction of post-traumatic stress: a re-examination of cortisol in the prediction and pathways to non-remitting PTSD. Transl Psychiatry. 2017; 7(3):e0. PMC: 5416681. DOI: 10.1038/tp.2017.38. View

16.

Abdel-Moneim A, El-Toweissy M, Ali A, Awad Allah A, Darwish H, Sadek I . Curcumin Ameliorates Lead (Pb(2+))-Induced Hemato-Biochemical Alterations and Renal Oxidative Damage in a Rat Model. Biol Trace Elem Res. 2015; 168(1):206-20. DOI: 10.1007/s12011-015-0360-1. View

17.

Zhang Y, Xu C, Fu Z, Shu Y, Zhang J, Lu C . Associations between total mercury and methyl mercury exposure and cardiovascular risk factors in US adolescents. Environ Sci Pollut Res Int. 2017; 25(7):6265-6272. DOI: 10.1007/s11356-017-0905-2. View

18.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

19.

Furey T, Cristianini N, Duffy N, Bednarski D, Schummer M, Haussler D . Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics. 2000; 16(10):906-14. DOI: 10.1093/bioinformatics/16.10.906. View

20.

Trevino S, Waalkes M, Flores Hernandez J, Leon-Chavez B, Aguilar-Alonso P, Brambila E . Chronic cadmium exposure in rats produces pancreatic impairment and insulin resistance in multiple peripheral tissues. Arch Biochem Biophys. 2015; 583:27-35. DOI: 10.1016/j.abb.2015.07.010. View