Skip to main content

Data Science in Environmental Health Research

Abstract

Purpose of Review

Data science is an exploding trans-disciplinary field that aims to harness the power of data to gain information or insights on researcher-defined topics of interest. In this paper, we review how data science can help advance environmental health research.

Recent Findings

We discuss the concepts of computationally scalable handling of big data and the design of efficient research data platforms and how data science can provide solutions for methodological challenges in environmental health research, such as high-dimensional outcomes and exposures and prediction models. Finally, we discuss tools for reproducible research.

Summary

In this paper, we present opportunities to improve environmental research capabilities by embracing data science and the pitfalls that environmental health researchers should avoid when employing data scientific approaches. Throughout the paper, we emphasize the need for environmental health researchers to collaborate more closely with biostatisticians and data scientists to ensure robust and interpretable results.

This is a preview of subscription content, access via your institution.

References

Papers of particular interest, published recently, have been highlighted as: • Of importance •• Of major importance

  1. •• Blei DM, Smyth P. Science and data science. Proc Natl Acad Sci. 2017;114(33):8689–92. This paper discusses data science from the statistical, computational, and human perspective and why scientists should care about data science.

    CAS  Article  Google Scholar 

  2. Jordan MI, et al. On statistics, computation and scalability. Bernoulli. 2013;19(4):1378–90.

    Article  Google Scholar 

  3. Mahalingaiah S, Lane KJ, Kim C, Cheng JJ, Hart JE. Impacts of air pollution on gynecologic disease: infertility, menstrual irregularity, uterine fibroids, and endometriosis: a systematic review and commentary. Curr Epidemiol Rep. 2018;5(3):197–204.

    Article  Google Scholar 

  4. • Gibson EA, Goldsmith JA, Kioumourtzoglou M-A. Complex mixtures, complex analyses: an emphasis on interpretable results. Curr Environ Health Rep. 2019;6(2):53–61. This paper discusses methods to address exposure to environmental mixtures in health studies—one of the areas where environmental health research is already embracing data science analytic approaches—and discusses advantages and pitfalls for the specific application in mixtures analyses.

    CAS  Article  Google Scholar 

  5. Manrai AK, Cui Y, Bushel PR, Hall M, Karakitsios S, Mattingly CJ, et al. Informatics and data analytics to support exposome-based discovery for public health. Annu Rev Public Health. 2017;38(1):279–94.

    Article  Google Scholar 

  6. Lankadurai BP, Nagato EG, Simpson MJ. Environmental metabolomics: an emerging approach to study organism responses to environmental stressors. Environ Rev. 2013;21(3):180–205.

    CAS  Article  Google Scholar 

  7. Di Q, Wang Y, Zanobetti A, Wang Y, Koutrakis P, Choirat C, et al. Air pollution and mortality in the Medicare population. N Engl J Med. 2017;376(26):2513–22.

    CAS  Article  Google Scholar 

  8. Luraschi J, Kuo K, Ushey K, Allaire JJ, The Apache Software Foundation. sparklyr: R interface to Apache Spark. 2019. https://CRAN.R-project.org/package=sparklyr. R package version 1.0.0.

  9. Owczarz W, Zlatev Z. Parallel matrix computations in air pollution modelling. Parallel Comput. 2002;28(2):355–68.

    Article  Google Scholar 

  10. Brown J, Wásniewski J, Zlatev Z. Running air pollution models on massively parallel machines. Parallel Comput. 1995;21(6):971–91.

    Article  Google Scholar 

  11. Molnar F Jr, Szakaly T, Meszaros R, Lagzi I. Air pollution modelling using a graphics processing unit with CUDA. Comput Phys Commun. 2010;181(1):105–12.

    CAS  Article  Google Scholar 

  12. Flaumenhaft Y, Ben-Assuli O. Personal health records, global policy and regulation review. Health Policy. 2018;122(8):815–26 ISSN 0168-8510.

    Article  Google Scholar 

  13. •• Patel CJ, Pho N, McDuffie M, Easton-Marks J, Kothari C, Kohane IS, et al. A database of human exposomes and phenomes from the US National Health and Nutrition Examination Survey. Sci Data. 2016;3:160096. This paper presents the successful integration of multiple publicly available datasets into a unified research data platform.

    CAS  Article  Google Scholar 

  14. Robinson O, Tamayo I, De Castro M, Valentin A, Giorgis-Allemand L, Krog NH, et al. The urban exposome during pregnancy and its socioeconomic determinants. Environ Health Perspect. 2018;126(7):077005.

    Article  Google Scholar 

  15. Nieuwenhuijsen MJ, Agier L, Basagaña X, Urquiza J, Tamayo-Uria I, Giorgis-Allemand L, et al. Influence of the urban exposome on birth weight. Environ Health Perspect. 2019;127(4):047007.

    Article  Google Scholar 

  16. Raisaro JL, Troncoso-Pastoriza J, Misbach M, Sousa JS, Pradervand S, Missiaglia E, et al. MedCo: Enabling secure and privacy-preserving exploration of distributed clinical and genomic data. IEEE/ACM Trans Comput Biol Bioinform. 2018:1. https://doi.org/10.1109/TCBB.2018.2854776 ISSN 1545-5963. https://ieeexplore.ieee.org/document/8410926/.

  17. Madhyastha TM, Koh N, Day TKM, Hernández-Fernández M, Kelley A, Peterson DJ, et al. Running neuroimaging applications on amazon web services: how, when, and at what cost? Front Neuroinform. 2017;11:63.

    Article  Google Scholar 

  18. Weber N, Liou D, Dommer J, MacMenamin P, Quiñones M, Misner I, et al. Nephele: a cloud platform for simplified, standardized and reproducible microbiome data analysis. Bioinformatics. 2017;34(8):1411–3.

    Article  Google Scholar 

  19. Frei P, Mohler E, Bürgi A, Fröhlich J, Neubauer G, Braun-Fahrländer C, et al. A prediction model for personal radio frequency electromagnetic field exposure. Sci Total Environ. 2009;408(1):102–8.

    CAS  Article  Google Scholar 

  20. Boeije G, Vanrolleghem P, Matthies M. A geo-referenced aquatic exposure prediction methodology for down-the drain chemicals. Water Sci Technol. 1997;36(5):251–8.

    CAS  Article  Google Scholar 

  21. Kloog I, Nordio F, Coull BA, Schwartz J. Predicting spatiotemporal mean air temperature using MODIS satellite surface temperature measurements across the northeastern USA. Remote Sens Environ. 2014;150:132–9.

    Article  Google Scholar 

  22. Kloog I, Chudnovsky AA, Just AC, Nordio F, Koutrakis P, Coull BA, et al. A new hybrid spatio-temporal model for estimating daily multi-year PM2.5 concentrations across northeastern USA using high resolution aerosol optical depth data. Atmos Environ. 2014;95:581–90.

    CAS  Article  Google Scholar 

  23. Van Donkelaar A, Martin RV, Spurr RJD, Burnett RT. High resolution satellite-derived PM2.5 from optimal estimation and geographically weighted regression over north America. Environ Sci Technol. 2015;49(17):10482–91.

    Article  Google Scholar 

  24. Al-Hamdan MZ, Crosson WL, Limaye AS, Rickman DL, Quattrochi DA, Estes MG Jr, et al. Methods for characterizing fine particulate matter using ground observations and remotely sensed data: potential use for environmental public health surveillance. J Air Waste Manage Assoc. 2009;59(7):865–81.

    CAS  Article  Google Scholar 

  25. Yanosky JD, Paciorek CJ, Laden F, Hart JE, Puett RC, Liao D, et al. Spatio-temporal modeling of particulate air pollution in the conterminous United States using geographic and meteorological predictors. Environ Health. 2014;13(1):63.

    Article  Google Scholar 

  26. Bi J, Belle JH, Wang Y, Lyapustin AI, Wildani A, Liu Y. Impacts of snow and cloud covers on satellite-derived PM2.5 levels. Remote Sens Environ. 2019;221:665–74.

    Article  Google Scholar 

  27. Di Q, Kloog I, Koutrakis P, Lyapustin A, Wang Y, Schwartz J. Assessing PM2.5 exposures with high spatiotemporal resolution across the continental United States. Environ Sci Technol. 2016;50(9):4712–21.

    CAS  Article  Google Scholar 

  28. Chipman HA, George EI, McCulloch RE. Bayesian ensemble learning. In: Advances in neural information processing systems; 2007. p. 265–72.

    Google Scholar 

  29. Hoeting, Jennifer A., David Madigan, Adrian E. Raftery, and Chris T. Volinsky. "Bayesian Model Averaging: A Tutorial." Stat Sci, 1999, 14(4): 382-401. http://www.jstor.org/stable/2676803.

  30. Li L, Zhang J, Qiu W, Wang J, Fang Y. An ensemble spatiotemporal model for predicting PM2.5 concentrations. Int J Environ Res Public Health. 2017;14(5):549.

    Article  Google Scholar 

  31. Shaddick G, Thomas ML, Green A, Brauer M, van Donkelaar A, Burnett R, et al. Data integration model for air quality: a hierarchical approach to the global estimation of exposures to ambient air pollution. J R Stat Soc: Ser C: Appl Stat. 2018;67(1):231–53.

    Article  Google Scholar 

  32. Hong KY, Pinheiro PO, Minet L, Hatzopoulou M, Weichenthal S. Extending the spatial scale of land use regression models for ambient ultrafine particles using satellite images and deep convolutional neural networks. Environ Res. 2019;176:108513.

    CAS  Article  Google Scholar 

  33. Lee D, Mukhopadhyay S, Rushworth A, Sahu SK. A rigorous statistical framework for spatio-temporal pollution prediction and estimation of its long-term impact on health. Biostatistics. 2016;18(2):370–85.

    Google Scholar 

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

  35. Sheppard L, Burnett RT, Szpiro AA, Kim S-Y, Jerrett M, Pope CA, et al. Confounding and exposure measurement error in air pollution epidemiology. Air Qual Atmos Health. 2012;5(2):203–16.

    Article  Google Scholar 

  36. Liu J, Paisley J, Kioumourtzoglou M-A, Coull BA. Adaptive and calibrated ensemble learning with dependent tail-free process. BNP @ NeurIPS. 2018.

  37. Jeremiah Zhe Liu, John Paisley, Marianthi-Anna Kioumourtzoglou, and Brent A. Coull. Adaptive ensemble learning of spatiotemporal processes with calibrated predictive uncertainty: a bayesian nonparametric approach. 2019. arXiv:1904.00521 [stat.ME].

  38. Bobb JF, Obermeyer Z, Wang Y, Dominici F. Cause-specific risk of hospital admission related to extreme heat in older adults. JAMA. 2014;312(24):2659–67.

    CAS  Article  Google Scholar 

  39. Krall JR, Chang HH, Waller LA, Mulholland JA, Winquist A, Talbott EO, et al. A multicity study of air pollution and cardiorespiratory emergency department visits: comparing approaches for combining estimates across cities. Environ Int. 2018;120:312–20.

    CAS  Article  Google Scholar 

  40. Gelman A, Stern HS, Carlin JB, Dunson DB, Vehtari A, Rubin DB. Bayesian data analysis. Chapman and Hall/CRC; 2013.

  41. Gelman A, Hill J. Data analysis using regression and multilevel/hierarchical models. Cambridge university press; 2006.

  42. Blei DM, Kucukelbir A, McAuliffe JD. Variational inference: a review for statisticians. J Am Stat Assoc. 2017;112(518):859–77.

    CAS  Article  Google Scholar 

  43. Hoffman MD, Blei DM, Wang C, Paisley J. Stochastic variational inference. J Mach Learn Res. 2013;14(1):1303–47.

    Google Scholar 

  44. Van der Laan MJ, Gruber S. Collaborative double robust targeted maximum likelihood estimation. Int J Biostat. 2010 May 17;6(1):Article 17. doi: https://doi.org/10.2202/1557-4679.1181.

  45. De Luna X, Waernbaum I, Richardson TS. Covariate selection for the nonparametric estimation of an average treatment effect. Biometrika. 2011;98(4):861–75.

    Article  Google Scholar 

  46. Vansteelandt S, Bekaert M, Claeskens G. On model selection and model misspecification in causal inference. Stat Methods Med Res. 2012;21(1):7–30.

    Article  Google Scholar 

  47. Wang C, Parmigiani G, Dominici F. Bayesian effect estimation accounting for adjustment uncertainty. Biometrics. 2012;68(3):661–71.

    Article  Google Scholar 

  48. Zigler CM, Dominici F. Uncertainty in propensity score estimation: Bayesian methods for variable selection and model-averaged causal effects. J Am Stat Assoc. 2014;109(505):95–107.

    CAS  Article  Google Scholar 

  49. Trevor H, Tibshirani R, Friedman JH. The elements of statistical learning: data mining, inference, and prediction. Springer Series in Statistics; 2009.

  50. James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning. New York: Springer; 2013.

    Book  Google Scholar 

  51. Greenland S, Robins JM, Pearl J, et al. Confounding and collapsibility in causal inference. Stat Sci. 1999;14(1):29–46.

    Article  Google Scholar 

  52. Hernán MA, Clayton D, Keiding N. The Simpson’s paradox unraveled. Int J Epidemiol. 2011;40(3):780–5.

    Article  Google Scholar 

  53. Antonelli, Joseph; Parmigiani, Giovanni; Dominici, Francesca. High-Dimensional Confounding Adjustment Using Continuous Spike and Slab Priors. Bayesian Anal, 2019, 14(3):805--828. doi:https://doi.org/10.1214/18-BA1131.

  54. Belloni A, Chernozhukov V, Hansen C. Inference on treatment effects after selection among high-dimensional controls. Rev Econ Stud. 2014;81(2):608–50.

    Article  Google Scholar 

  55. Ertefaie, A., Asgharian, M. & Stephens, D. (2017). Variable Selection in Causal Inference using a Simultaneous Penalization Method. Journal of Causal Inference, 6(1), pp. -. Retrieved 9 Jul. 2019, from https://doi.org/10.1515/jci-2017-0010. https://www.degruyter.com/view/j/jci.ahead-of-print/jci-2017-0010/jci-2017-0010.xml

  56. Farrell MH. Robust inference on average treatment effects with possibly more covariates than observations. J Econ. 2015;189(1):1–23.

    Article  Google Scholar 

  57. Wilson A, Reich BJ. Confounder selection via penalized credible regions. Biometrics. 2014;70(4):852–61.

    Article  Google Scholar 

  58. Antonelli J, Cefalu M, Palmer N, Agniel D. Doubly robust matching estimators for high dimensional confounding adjustment. Biometrics. 2018;74(4):1171–9.

    Article  Google Scholar 

  59. VanderWeele TJ, Ding P. Sensitivity analysis in observational research: introducing the e-value. Ann Intern Med. 2017;167(4):268–74.

    Article  Google Scholar 

  60. Haneuse S, VanderWeele TJ, Arterburn D. Using the e-value to assess the potential effect of unmeasured confounding in observational studies. JAMA. 2019;321(6):602–3.

    Article  Google Scholar 

  61. Hamra GB, Buckley JP. Environmental exposure mixtures: questions and methods to address them. Curr Epidemiol Rep. 2018;5(2):160–5.

    Article  Google Scholar 

  62. Stafoggia M, Breitner S, Hampel R, Basagaña X. Statistical approaches to address multi-pollutant mixtures and multiple exposures: the state of the science. Curr Environ Health Rep. 2017;4(4):481–90.

    CAS  Article  Google Scholar 

  63. Huang H, AolinWang RM-F, Lam J, Sirota M, Padula A, Woodruff TJ. Cumulative risk and impact modeling on environmental chemical and social stressors. Curr Environ Health Rep. 2018;5(1):88–99.

    CAS  Article  Google Scholar 

  64. Bellavia A, James-Todd T, Williams PL. Approaches for incorporating environmental mixtures as mediators in mediation analysis. Environ Int. 2019;123:368–74.

    Article  Google Scholar 

  65. •• National Academies of Sciences, Engineering and Medicine. Reproducibility and replicability in science. The National Academies Press, Washington, DC, 2019. ISBN 978-0-309-48613-2. https://doi.org/10.17226/25303. https://www.nap.edu/catalog/25303/reproducibility-and-replicability-in-science. This report defines the terms “reproducibility” and “replicability” for intended use across all fields of science.

  66. Daniel Krewski RT, Burnett M, Goldberg K, Hoover J, Siemiatycki MA, White W. Reanalysis of the Harvard Six Cities Study, Part I: Validation and replication. Inhal Toxicol. 2005. ISSN 08958378;17(7–8):335–42. https://doi.org/10.1080/08958370590929402.

    CAS  Article  Google Scholar 

  67. Peng RD. Reproducible research in computational science. Science. 2011;334(6060):1226–7.

    CAS  Article  Google Scholar 

  68. •• Wilkinson MD, Dumontier M, Aalbersberg IJJ, Appleton G, Axton M, Baak A, et al. Comment: The FAIR guiding principles for scientific data management and stewardship. Sci Data. 2016;3:1–9. https://doi.org/10.1038/sdata.2016.18 ISSN 20524463. This paper presents four principles to improve infrastructure supporting the reuse of scholarly data.

    Article  Google Scholar 

  69. Henneman LRF, Choirat C, Ivey C, Cummiskey K, Zigler CM. Characterizing population exposure to coal emissions sources in the United States using the Hyads model. Atmos Environ. 2019;203:271–80.

    CAS  Article  Google Scholar 

  70. Perkel JM. A toolkit for data transparency. Nature. 2018;560(7719):513–5. https://doi.org/10.1038/d41586-018-05990-5 ISSN 0028-0836. URL http://www.nature.com/articles/d41586-018-05990-5.

    CAS  Article  PubMed  Google Scholar 

  71. Beaulieu-Jones BK, Greene CS. Reproducibility of computational workflows is automated using continuous analysis. Nat Biotechnol. 2017;35(4):342–6 ISSN 1546-1696.

    CAS  Article  Google Scholar 

  72. Code Ocean — Discover & Run Scientific Code. URL https://codeocean.com/.

  73. Binder (beta). URL https://mybinder.org/.

  74. Renku. URL https://renkulab.io/.

  75. Brinckman A, Chard K, Gaffney N, Hategan M, Jones MB, Kowalik K, et al. Computing environments for reproducibility: capturing the whole tale. Futur Gener Comput Syst. 2019. ISSN 0167739X;94:854–67. https://doi.org/10.1016/j.future.2017.12.029.

    Article  Google Scholar 

  76. Pastrana E, Swaminathan S. Nature research journals trial new tools to enhance code peer review and publication. 2018. http://blogs.nature.com/ofschemesandmemes/2018/08/01/nature-research-journals-trial-new-tools-to-enhance-code-peer-review-and-publication.

  77. Dwork C. Differential privacy. In: Proceedings of the 33rd International Conference on Automata, Languages and Programming - Volume Part II, ICALP’06, pages 1–12, Berlin, Heidelberg, 2006. Springer-Verlag. ISBN 3-540-35907-9, 978-3-540-35907-4.

  78. edX. Courses taught by Rafael Irizarry. https://www.edx.org/bio/rafael-irizarry.

  79. Coursera. Courses taught by Jeff Leek. https://www.coursera.org/instructor/~694443.

Download references

Funding

This work was supported by NIEHS P30 ES009089 and R01 ES028805. This work was partially supported by HEI grant 4953-RFA14-3/16-4; the Health Effects Institute (HEI) is an organization jointly funded by the United States Environmental Protection Agency (EPA) (Assistance Award No.CR-83467701) and certain motor vehicle and engine manufacturers.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Marianthi-Anna Kioumourtzoglou.

Ethics declarations

Conflict of Interest

The authors declare no conflict of interest.

Human and Animal Rights and Informed Consent

This article does not contain any studies with human or animal subjects performed by the authors.

Disclaimer

The contents of this article do not necessarily reflect the views of HEI, or its sponsors, nor do they necessarily reflect the views and policies of the EPA or motor vehicle and engine manufacturers.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the Topical Collection on Environmental Epidemiology

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Choirat, C., Braun, D. & Kioumourtzoglou, MA. Data Science in Environmental Health Research. Curr Epidemiol Rep 6, 291–299 (2019). https://doi.org/10.1007/s40471-019-00205-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40471-019-00205-5

Keywords

  • Data science
  • Big data
  • Environmental health research
  • Reproducibility
  • Environmental mixtures
  • High-dimensional
  • Research data platforms