Display options
Cite
Lee KH, Dominici F, Schrag D, et al. Hierarchical models for semi-competing risks data with application to quality of end-of-life care for pancreatic cancer. J Am Stat Assoc. 2016;111(515):1075-1095doi: 10.1080/01621459.2016.1164052.
Lee, K. H., Dominici, F., Schrag, D., & Haneuse, S. (2016). Hierarchical models for semi-competing risks data with application to quality of end-of-life care for pancreatic cancer. Journal of the American Statistical Association, 111(515), 1075-1095. https://doi.org/10.1080/01621459.2016.1164052
Lee, Kyu Ha, et al. "Hierarchical models for semi-competing risks data with application to quality of end-of-life care for pancreatic cancer." Journal of the American Statistical Association vol. 111,515 (2016): 1075-1095. doi: https://doi.org/10.1080/01621459.2016.1164052
Lee KH, Dominici F, Schrag D, Haneuse S. Hierarchical models for semi-competing risks data with application to quality of end-of-life care for pancreatic cancer. J Am Stat Assoc. 2016;111(515):1075-1095. doi: 10.1080/01621459.2016.1164052. Epub 2016 Oct 18. PMID: 28303074; PMCID: PMC5347153.
Copy Download .nbib Format: NLM
Share it on

J Am Stat Assoc. 2016;111(515):1075-1095. doi: 10.1080/01621459.2016.1164052. Epub 2016 Oct 18.

Hierarchical models for semi-competing risks data with application to quality of end-of-life care for pancreatic cancer.

Journal of the American Statistical Association

Kyu Ha Lee, Francesca Dominici, Deborah Schrag, Sebastien Haneuse

Affiliations

  1. Epidemiology and Biostatistics Core, The Forsyth Institute, Department of Oral Health Policy and Epidemiology, Harvard School of Dental Medicine.
  2. Department of Biostatistics, Harvard T.H. Chan School of Public Health.
  3. Department of Medical Oncology, Dana Farber Cancer Institute.

PMID: 28303074 PMCID: PMC5347153 DOI: 10.1080/01621459.2016.1164052

Abstract

Readmission following discharge from an initial hospitalization is a key marker of quality of health care in the United States. For the most part, readmission has been studied among patients with 'acute' health conditions, such as pneumonia and heart failure, with analyses based on a logistic-Normal generalized linear mixed model (Normand et al., 1997). Naïve application of this model to the study of readmission among patients with 'advanced' health conditions such as pancreatic cancer, however, is problematic because it ignores death as a competing risk. A more appropriate analysis is to imbed such a study within the semi-competing risks framework. To our knowledge, however, no comprehensive statistical methods have been developed for cluster-correlated semi-competing risks data. To resolve this gap in the literature we propose a novel hierarchical modeling framework for the analysis of cluster-correlated semi-competing risks data that permits parametric or non-parametric specifications for a range of components giving analysts substantial flexibility as they consider their own analyses. Estimation and inference is performed within the Bayesian paradigm since it facilitates the straightforward characterization of (posterior) uncertainty for all model parameters, including hospital-specific random effects. Model comparison and choice is performed via the deviance information criterion and the log-pseudo marginal likelihood statistic, both of which are based on a partially marginalized likelihood. An efficient computational scheme, based on the Metropolis-Hastings-Green algorithm, is developed and had been implemented in the SemiCompRisks R package. A comprehensive simulation study shows that the proposed framework performs very well in a range of data scenarios, and outperforms competitor analysis strategies. The proposed framework is motivated by and illustrated with an on-going study of the risk of readmission among Medicare beneficiaries diagnosed with pancreatic cancer. Using data on n=5,298 patients at

Keywords: Bayesian survival analysis; cluster-correlated data; illness-death models; reversible jump Markov chain Monte Carlo; semi-competing risks; shared frailty

References

  1. J R Stat Soc Ser C Appl Stat. 2015 Feb 1;64(2):253-273 - PubMed
  2. Biometrics. 2000 Dec;56(4):1007-15 - PubMed
  3. Biostatistics. 2012 Jul;13(3):371-83 - PubMed
  4. Stat Med. 2006 Dec 30;25(24):4267-78 - PubMed
  5. Circ Cardiovasc Qual Outcomes. 2011 Mar;4(2):243-52 - PubMed
  6. Lifetime Data Anal. 2014 Jan;20(1):76-105 - PubMed
  7. Biometrics. 2011 Jun;67(2):415-26 - PubMed
  8. Biometrics. 2008 Mar;64(1):172-9 - PubMed
  9. Health Aff (Millwood). 2014 Oct;33(10):1793-800 - PubMed
  10. Gastroenterol Clin North Am. 2012 Mar;41(1):143-57 - PubMed
  11. Biometrics. 2007 Mar;63(1):96-108 - PubMed
  12. Stat Med. 2014 Dec 20;33(29):5111-25 - PubMed
  13. Biometrics. 2009 Sep;65(3):962-9 - PubMed
  14. Lifetime Data Anal. 2014 Apr;20(2):234-51 - PubMed
  15. Stat Med. 2007 Nov 10;26(25):4657-78 - PubMed
  16. Biometrika. 2012 Mar;99(1):167-184 - PubMed
  17. Biometrics. 2011 Mar;67(1):270-9 - PubMed
  18. J Natl Cancer Inst. 2011 Jun 8;103(11):853-62 - PubMed
  19. Implement Sci. 2010 Nov 17;5:88 - PubMed
  20. Stat Med. 2007 Apr 30;26(9):2088-112 - PubMed
  21. Biometrics. 2010 Sep;66(3):716-25 - PubMed
  22. J Natl Cancer Inst. 2011 Jan 19;103(2):117-28 - PubMed
  23. Biostatistics. 2007 Jul;8(3):526-45 - PubMed
  24. J Clin Oncol. 2015 Feb 10;33(5):455-64 - PubMed
  25. N Engl J Med. 2011 Dec 15;365(24):2287-95 - PubMed
  26. Stat Med. 2007 May 20;26(11):2389-430 - PubMed
  27. Biometrics. 1995 Sep;51(3):843-52 - PubMed
  28. Med Care. 2012 Dec;50(12):1109-18 - PubMed
  29. Biostatistics. 2008 Jul;9(3):400-10 - PubMed
  30. Biometrika. 2011 Mar;98(1):147-162 - PubMed
  31. Stat Med. 2014 Sep 20;33(21):3601-28 - PubMed
  32. PLoS Med. 2012 Feb;9(2):e1001181 - PubMed
  33. Arch Intern Med. 1997 Jan 13;157(1):99-104 - PubMed
  34. BMC Med Res Methodol. 2012 Jun 15;12:79 - PubMed
  35. JAMA. 2011 Feb 16;305(7):675-81 - PubMed

Publication Types

Grant support