2017
Construction of environmental risk score beyond standard linear models using machine learning methods: application to metal mixtures, oxidative stress and cardiovascular disease in NHANES
Park S, Zhao Z, Mukherjee B. Construction of environmental risk score beyond standard linear models using machine learning methods: application to metal mixtures, oxidative stress and cardiovascular disease in NHANES. Environmental Health 2017, 16: 102. PMID: 28950902, PMCID: PMC5615812, DOI: 10.1186/s12940-017-0310-9.Peer-Reviewed Original ResearchConceptsEnvironmental risk scoreBayesian kernel machine regressionNational Health and Nutrition Examination SurveyHealth and Nutrition Examination SurveyRisk scoreAssociated with odds ratiosNutrition Examination SurveyAssociated with systolicExamination SurveyMulti-pollutant approachKernel machine regressionPollutant mixturesSD increaseEpidemiological researchDiastolic blood pressureMortality outcomesOdds ratioBayesian additive regression treesDisease endpointsHealth endpointsCumulative riskPositive associationEnvironmental exposuresIntermediate markersCardiovascular disease
2013
Statistical strategies for constructing health risk models with multiple pollutants and their interactions: possible choices and comparisons
Sun Z, Tao Y, Li S, Ferguson K, Meeker J, Park S, Batterman S, Mukherjee B. Statistical strategies for constructing health risk models with multiple pollutants and their interactions: possible choices and comparisons. Environmental Health 2013, 12: 85. PMID: 24093917, PMCID: PMC3857674, DOI: 10.1186/1476-069x-12-85.Peer-Reviewed Original ResearchConceptsMultipollutant modelsHealth impacts of environmental factorsEffect estimatesExposure-response associationsExposure to multiple pollutantsTime series designConsequence of environmental exposureSample sizeHealth impactsEnvironmental exposuresPresence of multicollinearityRisk predictionPotential interactive effectsInitial screeningPollutant mixturesImpact of environmental factorsSupervised principal component analysisModel dimensionsStatistical literatureData examplesTree-based methodsMultiple pollutantsVariable selectionSimulation studyReduce model dimension