BIOMETRIC PRACTICE
Double robust estimation for multiple unordered treatments and clustered observations: Evaluating drug-eluting coronary artery stents
Sherri Rose,
Sharon-Lise Normand,
Corresponding Author
Sherri Rose
Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts, U.S.A.
email: [email protected]Search for more papers by this authorSharon-Lise Normand
Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts, U.S.A.
Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, U.S.A.
Search for more papers by this authorSherri Rose,
Sharon-Lise Normand,
Corresponding Author
Sherri Rose
Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts, U.S.A.
email: [email protected]Search for more papers by this authorSharon-Lise Normand
Department of Health Care Policy, Harvard Medical School, Boston, Massachusetts, U.S.A.
Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, U.S.A.
Search for more papers by this authorSummary
Postmarket comparative effectiveness and safety analyses of therapeutic treatments typically involve large observational cohorts. We propose double robust machine learning estimation techniques for implantable medical device evaluations where there are more than two unordered treatments and patients are clustered in hospitals. This flexible approach also accommodates high-dimensional covariates drawn from clinical databases. The Massachusetts Data Analysis Center percutaneous coronary intervention cohort is used to assess the composite outcome of 10 drug-eluting stents among adults implanted with at least one drug-eluting stent in Massachusetts. We find remarkable discrimination between stents. A simulation study designed to mimic this coronary intervention cohort is also presented and produced similar results.
Supporting Information
Additional Supporting Information may be found in the online version of this article.
| Filename | Description |
|---|---|
| biom12927-sup-0001-SuppData-S1.pdf137.2 KB | Supplementary Data S1. |
| biom12927-sup-0002-SuppDataCode-S1.zip162.2 KB | Supplementary Data Code S1. |
Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.
References
- Balzer, L. B., Zheng, W., van der Laan, M. J., and Petersen, M. L. (2017). A New Approach to Hierarchical Data Analysis: Targeted Maximum Likelihood Estimation of Cluster-Based Effects Under Interference. https://arxiv.org/abs/1706.02675 (accessed September 1, 2017).
- Bates, D., Maechler, M., Bolker, B., Walker, S., Christensen, R. H. B., Singmann, H., et al. (2017). lme4: Linear Mixed-Effects Models. R package version 1. 1–13.
- Cutler, D. and Ly, D. (2011). The (paper) work of medicine: understanding international medical costs. The Journal of Economic Perspectives 25, 3.
- Daniel, G., Colvin, H., Khaterzai, S., McClellan, M., and Aurora, P. (2015). Strengthening Patient Care: Building an Effective National Medical Device Surveillance System. http://bit.ly/2xEL2Wb (accessed September 1, 2017).
- Diggle, P., Heagerty, P., Liang, K.-Y., and Zeger, S. (2002). Analysis of Longitudinal Data. Oxford Statistical Science Series.
- Frakt, A. (2016). Why medical devices aren't safer. The New York Timeshttp://www.nytimes.com/2016/04/19/upshot/why-medical-devices-arent-safer.html (accessed September 1, 2017).
- Friedman, J., Hastie, T., and Tibshirani, R. (2010). glmnet: Lasso and Elastic-Net Regularized Generalized Linear Models. R package version 2. 0–2.
- Gelman, A. and Hill, J. (2007). Data Analysis Using Regression and Multilevel/Hierarchical Models. New York, NY, USA: Cambridge University Press.
- Goetgeluk, S. and Vansteelandt, S. (2008). Conditional generalized estimating equations for the analysis of clustered and longitudinal data. Biometrics 64, 772–780.
- Gruber, S. and van der Laan, M. (2012). tmle: An r package for targeted maximum likelihood estimation. Journal of Statistical Software 51, 1–35.
- Hernan, M., Brumback, B., and Robins, J. (2000). Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology 11, 561–570.
- Imbens, G. (2000). The role of the propensity score in estimating dose-response functions. Biometrika 87, 706–710.
- Krucoff, M., Sedrakyan, A., and Normand, S.-L. (2015). Bridging unmet medical device ecosystem needs with strategically coordinated registries networks. Journal of the American Medical Association 314, 1691–1692.
- Krumholz, H. M., Brindis, R. G., Brush, J. E., Cohen, D. J., Epstein, A. J., Furie, K., et al. (2006). Standards for statistical models used for public reporting of health outcomes. Circulation 113, 456–462.
- Laird, N. M. and Ware, J. H. (1982). Random-effects models for longitudinal data. Biometrics 38, 963–974.
- Li, Y., Propert, K., and Rosenbaum, P. (2001). Balanced risk set matching. Journal of the American Statistical Association 96, 870–882.
- Liang, K.-Y. and Zeger, S. L. (1986). Longitudinal data analysis using generalized linear models. Biometrika 73, 13–22.
- Liaw, A. and Wiener, M. (2002). Classification and regression by randomforest. R News 2, 18–22.
- Localio, A. R., Berlin, J. A., Ten Have, T. R., and Kimmel, S. E. (2001). Adjustments for center in multicenter studies: an overview. Annals of Internal Medicine 135, 112–123.
- Lopez, M. and Gutman, R. (2017). Estimation of causal effects with multiple treatments: a review and new ideas. Statistical Science 32, 432–454.
- Massachusetts Data Analysis Center (2016). Cardiac Study Annual Reports. http://www.massdac.org/index.php/reports/cardiac-study-annual (Accessed September 1, 2017).
- Normand, S.-L. T., Glickman, M. E., and Gatsonis, C. A. (1997). Statistical methods for profiling providers of medical care: issues and applications. Journal of the American Statistical Association 92, 803–814.
- Petersen, M., Deeks, S., Martin, J., and van der Laan, M. (2007). History-adjusted marginal structural models to estimate time-varying effect modification. American Journal of Epidemiology 166, 985–993.
- Petersen, M., Porter, K., Gruber, S., Wang, Y., and van der Laan, M. (2012). Diagnosing and responding to violations in the positivity assumption. Statistical Methods for Medical Research 21, 31–54.
- Polley, E. and van der Laan, M. (2013). SuperLearner. R package version 2.0-10.
- Porter, K. E., Gruber, S., van der Laan, M. J., and Sekhon, J. S. (2011). The relative performance of targeted maximum likelihood estimators. The International Journal of Biostatistics 7, 1.
- Raftery, A., Madigan, D., and Hoeting, J. (1997). Bayesian model averaging for linear regression models. Journal of the American Statistical Association 92, 179–191.
- Raudenbush, S. W. and Bryk, A. S. (2002). Hierarchical Linear Models: Applications and Data Analysis Methods. Thousand Oaks, CA: Sage.
- Ren, S., Lai, H., Tong, W., Aminzadeh, M., Hou, X., and Lai, S. (2010). Nonparametric bootstrapping for hierarchical data. Journal of Applied Statistics 37, 1487–1498.
- Resnic, F. and Normand, S. (2012). Postmarketing surveillance of medical devicesfilling in the gaps. New England Journal of Medicine 366, 875–877.
- Robins, J. (1986). A new approach to causal inference in mortality studies with sustained exposure periods–Application to control of the healthy worker survivor effect. Mathematical Modelling 7, 1393–1512.
- Robins, J. (1998). Marginal structural models. In 1997 Proceedings of the American Statistical Association, Section on Bayesian Statistical Science, 1–10. Alexandria, VA: American Statistical Association.
- Rosenblum, M. and van der Laan, M. (2010). Targeted maximum likelihood estimation of the parameter of a marginal structural model. International Journal of Biostatistics 6, Article 19.
- Schneeweiss, S., Rassen, J., Glynn, R., Avorn, J., Mogun, H., and Brookhart, M. (2009). High-dimensional propensity score adjustment in studies of treatment effects using health care claims data. Epidemiology 20, 512.
- Schnitzer, M. E., van der Laan, M. J., Moodie, E. E., and Platt, R. W. (2014). Effect of breastfeeding on gastrointestinal infection in infants: A targeted maximum likelihood approach for clustered longitudinal data. The Annals of Applied Statistics 8, 703.
- Schnitzer, M., van der Laan, M., Moodie, E., and Platt, R. (2018). LTMLE with clustering. In Targeted Learning in Data Science: Causal Inference for Complex Longitudinal Studies, M. J. van der Laan and S. Rose (eds), Berlin Heidelberg New York: Springer.
- Sedrakyan, A., Graves, S., Bordini, B., Pons, M., Havelin, L., Mehle, S., et al. (2014). Comparative effectiveness of ceramic-on-ceramic implants in stemmed hip replacement. The Journal of Bone & Joint Surgery 96, 34–41.
- Siontis, G., Piccolo, R., Praz, F., Valgimigli, M., Räber, L., Mavridis, D., et al. (2016). Percutaneous coronary interventions for the treatment of stenoses in small coronary arteries: A network meta-analysis. Journal of the American College of Cardiology: Cardiovascular Interventions 9, 1324–1334.
- Stettler, C., Allemann, S., Wandel, S., Kastrati, A., Morice, M., Schomig, A., et al. (2008). Drug eluting and bare metal stents in people with and without diabetes: Collaborative network meta-analysis. The BMJ 337, a1331.
- Tchernis, R., Horvitz-Lennon, M., and Normand, S. (2005). On the use of discrete choice models for causal inference. Statistics in Medicine 24, 2197–2212.
- van der Laan, M., Polley, E., and Hubbard, A. (2007). Super learner. Statistical Applications in Genetics and Molecular Biology 6, Article 25.
-
van der Laan, M. and
Robins, J.
(2003).
Unified Methods for Censored Longitudinal Data and Causality.
Berlin Heidelberg New York: Springer.
10.1007/978-0-387-21700-0 Google Scholar
- van der Laan, M. and Rose,S. (2011). Targeted Learning: Causal Inference for Observational and Experimental Data. Berlin Heidelberg New York: Springer.
-
van der Laan, M. and
Rose, S.
(2018).
Targeted Learning in Data Science: Causal Inference for Complex
Longitudinal Studies.
Berlin Heidelberg New York: Springer.
10.1007/978-3-319-65304-4 Google Scholar
-
van der Laan, M. and
Rubin, D. B.
(2006).
Targeted maximum likelihood learning.
International Journal of Biostatistics
2, Article 11.
10.2202/1557-4679.1043 Google Scholar
- Zetterqvist, J., Vansteelandt, S., Pawitan, Y., and Sjölander, A. (2016). Doubly robust methods for handling confounding by cluster. Biostatistics 17, 264–276.
