Accounting for measurement error to assess the effect of air pollution on omic signals

Autoři: Erica Ponzi aff001;  Paolo Vineis aff003;  Kian Fan Chung aff005;  Marta Blangiardo aff003
Působiště autorů: Department of Biostatistics, Epidemiology, Biostatistics and Prevention Institute, University of Zürich, Hirschengraben 84, 8001 Zürich, Switzerland aff001;  Department of Biostatistics, Oslo Center for Epidemiology and Biostatistics, University of Oslo, Norway aff002;  Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, London, United Kingdom aff003;  Italian Institute for Genomic Medicine (IIGM), Turin, Italy aff004;  National Heart and Lung Institute, Imperial College London, United Kingdom aff005;  Royal Brompton and Harefield NHS Trust, London, United Kingdom aff006
Vyšlo v časopise: PLoS ONE 15(1)
Kategorie: Research Article
doi: 10.1371/journal.pone.0226102


Studies on the effects of air pollution and more generally environmental exposures on health require measurements of pollutants, which are affected by measurement error. This is a cause of bias in the estimation of parameters relevant to the study and can lead to inaccurate conclusions when evaluating associations among pollutants, disease risk and biomarkers. Although the presence of measurement error in such studies has been recognized as a potential problem, it is rarely considered in applications and practical solutions are still lacking. In this work, we formulate Bayesian measurement error models and apply them to study the link between air pollution and omic signals. The data we use stem from the “Oxford Street II Study”, a randomized crossover trial in which 60 volunteers walked for two hours in a traffic-free area (Hyde Park) and in a busy shopping street (Oxford Street) of London. Metabolomic measurements were made in each individual as well as air pollution measurements, in order to investigate the association between short-term exposure to traffic related air pollution and perturbation of metabolic pathways. We implemented error-corrected models in a classical framework and used the flexibility of Bayesian hierarchical models to account for dependencies among omic signals, as well as among different pollutants. Models were implemented using traditional Markov Chain Monte Carlo (MCMC) simulative methods as well as integrated Laplace approximation. The inclusion of a classical measurement error term resulted in variable estimates of the association between omic signals and traffic related air pollution measurements, where the direction of the bias was not predictable a priori. The models were successful in including and accounting for different correlation structures, both among omic signals and among different pollutant exposures. In general, more associations were identified when the correlation among omics and among pollutants were modeled, and their number increased when a measurement error term was additionally included in the multivariate models (particularly for the associations between metabolomics and NO2).

Klíčová slova:

Air pollution – Coronary heart disease – Chronic obstructive pulmonary disease – Metabolic pathways – Metabolites – Metabolomics – Normal distribution – Pollutants


1. Elliott P, Cuzick J, English D, Stern R. Geographical and Environmental epidemiology: methods for small-area studies. Press OU, editor. New York, NY: Oxford Univ Press; 1992.

2. Pekkanen J, Pearce N. Environmental epidemiology: challenges and opportunities. Environmental Health Perspectives. 2001;109:1–5. doi: 10.1289/ehp.011091 11171517

3. Baker D, Nieuwenhuijsen M. Environmental Epidemiology: Study Methods and Applications. Baker Dean N M, editor. Dean Baker, Mark Nieuwenhuijsen; 2008.

4. Rhomberg LR, Chandalia JK, Long C, Goodman JE. Measurement error in environmental epidemiology and the shape of exposure-response curves. Critical Reviews in Toxicology. 2011;41(8):651–671. doi: 10.3109/10408444.2011.563420 21823979

5. Edwards JK, Keil AP. Measurement error and environmental epidemiology: a policy perspective. Current Environmental Health Reports. 2017;4(1):79–88. doi: 10.1007/s40572-017-0125-4 28138941

6. Shaw PA, Deffner V, Keogh RH, Tooze JA, Dodd KW, Kuechenhoff H, et al. Epidemiologic analyses with error-prone exposures: review of current practice and recommendations. Annals of Epidemiology. 2018;28:821–828. doi: 10.1016/j.annepidem.2018.09.001 30316629

7. Brakenhoff TB, Mitroiu M, Keogh RH, Moons KGM, Groenwold RHH, van Smeden M. Measurement error is often neglected in medical literature: a systematic review. Journal of Clinical Epidemiology. 2018;98:89–97. doi: 10.1016/j.jclinepi.2018.02.023 29522827

8. Mallick B, Hoffman FO, Carroll RJ. Semiparametric regression modeling with mixtures of Berkson and classical error, with application to fallout from the Nevada test site. Biometrics. 2002;58:13–20. doi: 10.1111/j.0006-341x.2002.00013.x 11890308

9. Gryparis A, Coull BA, Schwarzt J. Controlling for confounders in the presence of measurement error in hierarchical models; a Bayesian approach. Journal of Exposure Science and Environmental Epidemiology. 2007;17:S20–S28. doi: 10.1038/sj.jes.7500624 18079761

10. Baxter LK, Wright RJ, Paciorek CJ, Laden F, Suh HH, Levy JI. Effects of exposure measurement error in the analysis of health effects from traffic-related air pollution. Journal of Exposure Science and Environmental Epidemiology. 2010;20:101–11. doi: 10.1038/jes.2009.5 19223939

11. Goldman GT, Mulholland JA, Russell AG, Strickland MJ, Klein M, Waller LA, et al. Impact of exposure measurement error in air pollution epidemiology: effect of error type in time-series studies. Environmental Health. 2011;10(61). doi: 10.1186/1476-069X-10-61 21696612

12. Zeger SL, Thomas D, Dominici F, Samet JM, Schwartz J, Dockery D, et al. Exposure Measurement error in time-series studies of air pollution: concepts and consequences. Environmental Health Perspectives. 2000;108:419–426. doi: 10.1289/ehp.00108419 10811568

13. Alexeeff SE, Carroll RJ, Coull B. Spatial measurement error and correction by spatial SIMEX in linear regression models when using predicted air pollution exposures. Biostatistics. 2016;17:377–389. doi: 10.1093/biostatistics/kxv048 26621845

14. Van Roosbroeck S, Li R, Hoek G, Lebret E, Brunekeef B, Spiegelmann D. Traffic-related outdoor air pollution and respiratory suymptoms in children: the impact of adjustment for exposure measurement error. Epidemiology. 2006;368:174–184.

15. Gryparis A, Zeka A, Schwartz J, Coull BA. Measurement error caused by spatial misalignment in environmental epidemiology. Biostatistics. 2009;10:258–274. doi: 10.1093/biostatistics/kxn033 18927119

16. Sinharay R, Gong J, Barratt B, Ohman-Strickland P, Ernst S, Kelly F, et al. Respiratory and cardiovascular responses to walking down a traffic-polluted road compared with walking in a traffic-free area in participants aged 60 years and older with chronic lung or heart disease and age-matched healthy controls: a randomised, crossover study. Lancet. 2017;391:339–349. doi: 10.1016/S0140-6736(17)32643-0 29221643

17. van Veldhoven K, Kiss A, Keski-Rahkonen P, Robinot N, Scalbert A, Cullinan P, et al. Impact of short-term traffic-related air pollution on the metabolome—Results from two metabolome-wide experimental studies. Environment International. 2019;123:124–131. 30522001

18. Rue H, Martino S, Chopin N. Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion). Journal of the Royal Statistical Society Series B (Statistical Methodology). 2009;71:319–392.

19. Muff S, Riebler A, Held L, Rue H, Saner P. Bayesian Analysis of Measurement Error Models Using Integrated Nested Laplace Approximations. Journal of the Royal Statistical Society- Applied Statistics. 2015;64:231–252. doi: 10.1111/rssc.12069

20. Muff S, Ott M, Braun J, Held L. Bayesian Two-Component Measurement Error Modelling for Survival Analysis Using INLA—A Case Study on Cardiovascular Disease Mortality in Switzerland. Computational Statistics and Data Analysis. 2017;113:177–193. doi: 10.1016/j.csda.2017.03.001

21. Vineis P, Chadeau-Hyam M, Gmuender H, Gulliver J, Herceg Z, Kleinjans J, et al. The exposome in practice: Design of the EXPOsOMICS project. International Journal of Hygiene and Environmental Health. 2017;220:142–151. doi: 10.1016/j.ijheh.2016.08.001 27576363

22. Newton MA, Noueiry A, Sarkar D, Ahlquist P. Detecting differential gene expression with a semiparametric hierarchical mixture method. Biostatistics. 2004;5(2):155–176. doi: 10.1093/biostatistics/5.2.155 15054023

23. Ventrucci M, Scott EM, Cocchi D. Multiple testing on standard mortality ratios: a Bayesian hierarchical model for FDR estimation. Biostatistics. 2011;12(1):51–67. doi: 10.1093/biostatistics/kxq040 20577014

24. Carroll RJ, Ruppert D, Stefanski LA, Crainiceanu CM. Measurement error in nonlinear models, a modern perspective. Boca Raton: Chapman and Hall; 2006.

25. Stephens DA, Dellaportas P. Bayesian analysis of generalised linear models with covariate measurement error. In: Bernardo JM, Berger JO, Dawid AP, Smith AFM, editors. Bayesian Statistics 4. Oxford Univ Press; 1992.

26. Richardson S, Gilks WR. Conditional independence models for epidemiological studies with covariate measurement error. Statistics in Medicine. 1993;12:1703–1722. doi: 10.1002/sim.4780121806 8248663

27. Coker E, Liverani S, Ghosh JK, Jerrett M, Beckermann B, Li A, et al. Multi-pollutant exposure profiles associated with term low birth weight in Los Angeles County. Environment International. 2016;91:1–13. doi: 10.1016/j.envint.2016.02.011 26891269

28. Huang G, Lee D amd Scott EM. Multivariate space-time modelling of multiple air pollutants and their health effects accounting for exposure uncertainty. Statistics in Medicine. 2018;37:1134–1148. doi: 10.1002/sim.7570 29205447

29. Gustafson P. On Model Expansion, Model Contraction, Identifiability and Prior Information: Two Illustrative Scenarios Involving Mismeasured Variables. Statistical Science. 2005;20:111–140. doi: 10.1214/088342305000000098

30. Blangiardo M, Cameletti M, Baio G, Rue H. Spatial and Spatio-temporal models with R-INLA. Spatial and spatio-temporal epidemiology. 2013;7:39–55. doi: 10.1016/j.sste.2013.07.003 24377114

Článek vyšel v časopise


2020 Číslo 1