Construction of environmental risk score beyond standard linear models using machine learning methods: application to metal mixtures, oxidative stress and cardiovascular disease in NHANES

Abstract

Background: There is growing concern of health effects of exposure to pollutant mixtures. We initially proposed an Environmental Risk Score (ERS) as a summary measure to examine the risk of exposure to multi-pollutants in epidemiologic research considering only pollutant main effects. We expand the ERS by consideration of pollutant-pollutant interactions using modern machine learning methods. We illustrate the multi-pollutant approaches to predicting a marker of oxidative stress (gamma-glutamyl transferase (GGT)), a common disease pathway linking environmental exposure and numerous health endpoints.

Methods: We examined 20 metal biomarkers measured in urine or whole blood from 6 cycles of the National Health and Nutrition Examination Survey (NHANES 2003-2004 to 2013-2014, n = 9664). We randomly split the data evenly into training and testing sets and constructed ERS's of metal mixtures for GGT using adaptive elastic-net with main effects and pairwise interactions (AENET-I), Bayesian additive regression tree (BART), Bayesian kernel machine regression (BKMR), and Super Learner in the training set and evaluated their performances in the testing set. We also evaluated the associations between GGT-ERS and cardiovascular endpoints.

Results: ERS based on AENET-I performed better than other approaches in terms of prediction errors in the testing set. Important metals identified in relation to GGT include cadmium (urine), dimethylarsonic acid, monomethylarsonic acid, cobalt, and barium. All ERS's showed significant associations with systolic and diastolic blood pressure and hypertension. For hypertension, one SD increase in each ERS from AENET-I, BART and SuperLearner were associated with odds ratios of 1.26 (95% CI, 1.15, 1.38), 1.17 (1.09, 1.25), and 1.30 (1.20, 1.40), respectively. ERS's showed non-significant positive associations with mortality outcomes.

Conclusions: ERS is a useful tool for characterizing cumulative risk from pollutant mixtures, with accounting for statistical challenges such as high degrees of correlations and pollutant-pollutant interactions. ERS constructed for an intermediate marker like GGT is predictive of related disease endpoints.

Keywords: Bayesian additive regression tree (BART); Bayesian kernel machine regression (BKMR); Cardiovascular disease; Elastic-net; Environmental risk score (ERS); Machine learning; Metals; Mixtures; Multipollutants; Super Learner.

Fig. 1

Schematic diagram of Environmental Risk Score (ERS) construction and analytical methods. AENET-I, adaptive elastic-net with main effects and pairwise interactions; BART, Bayesian additive regression tree; BKMR, Bayesian kernel machine regression; PRESS, predicted residual sums of squares; MSE, mean square error; MSPE, mean square prediction error; AUC, area under the receiver operating characteristics curve; OR, odds ratio; SBP/DBP, systolic and diastolic blood pressure; CVD, cardiovascular disease

Fig. 2

Heat map of Spearman correlations between metal biomarkers. Asterisk next to the metal names indicates metals measured in whole blood. As, arsenic; As III, arsenous acid; As V, arsenic acid; MMA, monomethylarsonic acid (MMA); DMA, dimethylarsonic acid; Mo, molybdenum

Fig. 3

Selected predictors of the main effects (diagonal cells) and pairwise interactions (off-diagonal combinations) for serum gamma-glutamyl transferase (GGT) in adaptive elastic net. Bubble size indicates the magnitude of the association. The number inside indicates p-value. Asterisk next to the metal names indicates metals measured in whole blood. As, arsenic; As III, arsenous acid; As V, arsenic acid; MMA, monomethylarsonic acid (MMA); DMA, dimethylarsonic acid; Mo, molybdenum

Fig. 4

Odds ratios (95% confidence intervals) of having high GGT (50 U/L and above) comparing the highest vs. the lowest quintiles of ERS and individual pollutants that compose the ERS in the testing set. All models were adjusted for age, BMI, creatinine, gender, race/ethnicity, smoking status and education