Machine learning prediction of exposure to acrylamide based on modelling of association between dietary exposure and internal biomarkers
Wan X, Zhang Y, Gao S, Shen X, Jia W, Pan X, Zhuang P, Jiao J, Zhang Y. Machine learning prediction of exposure to acrylamide based on modelling of association between dietary exposure and internal biomarkers. Food And Chemical Toxicology 2022, 170: 113498. PMID: 36328216, DOI: 10.1016/j.fct.2022.113498.Peer-Reviewed Original ResearchMeSH KeywordsAcetylcysteineAcrylamideAgedBiomarkersDietary ExposureHumansMachine LearningMiddle AgedConceptsDietary exposureElderly populationInternal exposureTotal energy intakeDietary acrylamide exposureChinese elderly populationAverage dietary intakeN-acetylExposure assessmentRegression modelsUrinary biomarkersDietary intakeUrinary contentAcrylamide exposureChinese cohortPhysical activityAccurate exposure assessmentEnergy intakeElderly participantsPotential health risksL-cysteineImportant covariatesLinear regression modelsHealth risksExposureAssociations of 3-monochloropropane-1,2-diol and glycidol with prevalence of metabolic syndrome: Findings from Lanxi Nutrition and Safety Study
Wan X, Jia W, Zhuang P, Wu F, Zhang Y, Shen X, Liu X, Zheng W, Jiao J, Zhang Y. Associations of 3-monochloropropane-1,2-diol and glycidol with prevalence of metabolic syndrome: Findings from Lanxi Nutrition and Safety Study. Environmental Research 2022, 209: 112746. PMID: 35063427, DOI: 10.1016/j.envres.2022.112746.Peer-Reviewed Original ResearchConceptsMetS prevalenceMetS casesRisk factorsAdult Treatment Panel III criteriaNational Cholesterol Education ProgramCholesterol Education ProgramBehavioral risk factorsPotential risk factorsUrinary creatinine contentPositive associationChinese elderly peoplePoisson regression modelsHypertriglyceridemia prevalencePrevalent MetSMetabolic syndromeUrinary biomarkersLowest quartileHigh prevalenceRelative riskElderly populationMercapturic acidsDietary exposurePrevalenceSafety studiesStrong positive association