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.
Highlights
People can be exposed to high levels of toxic metals from numerous sources, including contaminated air, water, soil, and food [1]
We presented an empirical comparison of five different techniques for outperformed the decision trees (DT) and k-nearest neighbor (KNN) techniques, achieving overall accuracies of >0.86 and area under the estimating the risk of HC using Korea National Health and Nutrition Examination Survey (KNHANES) data on 10,089 participants
The results of our study show that complex machine learning (ML) models, such as support vector machines (SVM), tend to outperform outperformed the DT and KNN techniques, achieving overall accuracies of >0.86 and area under the simpler models such as DT when predicting HC associated with exposure to heavy metals
Summary
People can be exposed to high levels of toxic metals from numerous sources, including contaminated air, water, soil, and food [1]. The general population is often exposed to these metals simultaneously, most studies concerning the health effects of these metals have been carried out on animals, or on human populations with relatively high levels of exposure to individual metals [3,4,5]. Few epidemiological studies have addressed the biological effects of low levels of exposure to mixtures of these metals, with regard to possible interactions between metals. There are many experimental and epidemiological studies showing that exposure to lead alters the concentration of total cholesterol in serum [9,10,11] and a strong positive association between blood concentration of mercury and serum total cholesterol level [12,13,14]. We lack information on the effect of combined exposure to these metal mixtures on cholesterol metabolism in the general population
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
