PMID- 28950902
OWN - NLM
STAT- MEDLINE
DCOM- 20171227
LR  - 20190610
IS  - 1476-069X (Electronic)
IS  - 1476-069X (Linking)
VI  - 16
IP  - 1
DP  - 2017 Sep 26
TI  - Construction of environmental risk score beyond standard linear models using 
      machine learning methods: application to metal mixtures, oxidative stress and 
      cardiovascular disease in NHANES.
PG  - 102
LID - 10.1186/s12940-017-0310-9 [doi]
LID - 102
AB  - 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.
FAU - Park, Sung Kyun
AU  - Park SK
AD  - Department of Epidemiology, School of Public Health, University of Michigan, 1415 
      Washington Heights, Ann Arbor, MI, 48109, USA. sungkyun@umich.edu.
AD  - Department of Environmental Health Sciences, School of Public Health, University 
      of Michigan, Ann Arbor, MI, USA. sungkyun@umich.edu.
FAU - Zhao, Zhangchen
AU  - Zhao Z
AD  - Department of Biostatistics, School of Public Health, University of Michigan, Ann 
      Arbor, MI, USA.
FAU - Mukherjee, Bhramar
AU  - Mukherjee B
AD  - Department of Epidemiology, School of Public Health, University of Michigan, 1415 
      Washington Heights, Ann Arbor, MI, 48109, USA.
AD  - Department of Biostatistics, School of Public Health, University of Michigan, Ann 
      Arbor, MI, USA.
LA  - eng
GR  - T42 OH008455/OH/NIOSH CDC HHS/United States
GR  - P30 ES017885/ES/NIEHS NIH HHS/United States
GR  - R01 ES026578/ES/NIEHS NIH HHS/United States
GR  - R21 ES020811/ES/NIEHS NIH HHS/United States
GR  - P30 DK020572/DK/NIDDK NIH HHS/United States
GR  - R01 ES026964/ES/NIEHS NIH HHS/United States
GR  - U01 AG017719/AG/NIA NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, U.S. Gov't, Non-P.H.S.
PT  - Research Support, U.S. Gov't, P.H.S.
DEP - 20170926
PL  - England
TA  - Environ Health
JT  - Environmental health : a global access science source
JID - 101147645
RN  - 0 (Environmental Pollutants)
RN  - 0 (Metals)
SB  - IM
MH  - Adult
MH  - Aged
MH  - Cardiovascular Diseases/chemically induced/*epidemiology
MH  - Environmental Pollutants/*adverse effects
MH  - Female
MH  - Humans
MH  - *Linear Models
MH  - *Machine Learning
MH  - Male
MH  - Metals/*adverse effects
MH  - Middle Aged
MH  - Oxidative Stress/*drug effects
MH  - Prevalence
MH  - Risk Assessment/*methods
MH  - United States/epidemiology
MH  - Young Adult
PMC - PMC5615812
OTO - NOTNLM
OT  - Bayesian additive regression tree (BART)
OT  - Bayesian kernel machine regression (BKMR)
OT  - Cardiovascular disease
OT  - Elastic-net
OT  - Environmental risk score (ERS)
OT  - Machine learning
OT  - Metals
OT  - Mixtures
OT  - Multipollutants
OT  - Super Learner
COIS- ETHICS APPROVAL AND CONSENT TO PARTICIPATE: NHANES is a publicly available data 
      set and all participants in NHANES provide written informed consent, consistent 
      with approval by the National Center for Health Statistics Institutional Review 
      Board. CONSENT FOR PUBLICATION: Not Applicable. COMPETING INTERESTS: The authors 
      declare that they have no competing interests. PUBLISHER'S NOTE: Springer Nature 
      remains neutral with regard to jurisdictional claims in published maps and 
      institutional affiliations.
EDAT- 2017/09/28 06:00
MHDA- 2017/12/28 06:00
PMCR- 2017/09/26
CRDT- 2017/09/28 06:00
PHST- 2017/06/01 00:00 [received]
PHST- 2017/09/21 00:00 [accepted]
PHST- 2017/09/28 06:00 [entrez]
PHST- 2017/09/28 06:00 [pubmed]
PHST- 2017/12/28 06:00 [medline]
PHST- 2017/09/26 00:00 [pmc-release]
AID - 10.1186/s12940-017-0310-9 [pii]
AID - 310 [pii]
AID - 10.1186/s12940-017-0310-9 [doi]
PST - epublish
SO  - Environ Health. 2017 Sep 26;16(1):102. doi: 10.1186/s12940-017-0310-9.