Bayesian Analysis

A Decision-Theoretic Comparison of Treatments to Resolve Air Leaks After Lung Surgery Based on Nonparametric Modeling

Yanxun Xu, Peter F. Thall, Peter Müller, and Mehran J. Reza

Full-text: Open access


We propose a Bayesian nonparametric utility-based group sequential design for a randomized clinical trial to compare a gel sealant to standard care for resolving air leaks after pulmonary resection. Clinically, resolving air leaks in the days soon after surgery is highly important, since longer resolution time produces undesirable complications that require extended hospitalization. The problem of comparing treatments is complicated by the fact that the resolution time distributions are skewed and multi-modal, so using means is misleading. We address these challenges by assuming Bayesian nonparametric probability models for the resolution time distributions and basing the comparative test on weighted means. The weights are elicited as clinical utilities of the resolution times. The proposed design uses posterior expected utilities as group sequential test criteria. The procedure’s frequentist properties are studied by extensive simulations.

Article information

Bayesian Anal., Volume 12, Number 3 (2017), 639-652.

First available in Project Euclid: 26 July 2016

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Bayesian nonparametric clinical trial mesothelioma utility function

Creative Commons Attribution 4.0 International License.


Xu, Yanxun; Thall, Peter F.; Müller, Peter; Reza, Mehran J. A Decision-Theoretic Comparison of Treatments to Resolve Air Leaks After Lung Surgery Based on Nonparametric Modeling. Bayesian Anal. 12 (2017), no. 3, 639--652. doi:10.1214/16-BA1016.

Export citation


  • Allen, M. S., Wood, D. E., Hawkinson, R. W., Harpole, D. H., McKenna, R. J., Walsh, G. L., Vallieres, E., Miller, D. L., Nichols, F. C., Smythe, W. R., et al. (2004). “Prospective randomized study evaluating a biodegradable polymeric sealant for sealing intraoperative air leaks that occur during pulmonary resection.” The Annals of Thoracic Surgery, 77(5): 1792–1801.
  • Barrientos, A. F., Jara, A., Quintana, F. A., et al. (2012). “On the support of MacEachern’s dependent Dirichlet processes and extensions.” Bayesian Analysis, 7(2): 277–310.
  • Bellman, R. E. (1957). Dynamic Programming. Princeton University Press.
  • De Iorio, M., Müller, P., Rosner, G. L., and MacEachern, S. N. (2004). “An ANOVA model for dependent random measures.” Journal of the American Statistical Association, 99(465): 205–215.
  • Dunson, D. B. and Peddada, S. D. (2008). “Bayesian nonparametric inference on stochastic ordering.” Biometrika, 95(4): 859–874.
  • Ferguson, T. S. (1973). “A Bayesian analysis of some nonparametric problems.” The Annals of Statistics, 209–230.
  • Fink, D. (1997). “A compendium of conjugate priors.” See, 46.
  • Gelfand, A. E. and Kottas, A. (2001). “Nonparametric Bayesian modeling for stochastic order.” Annals of the Institute of Statistical Mathematics, 53(4): 865–876.
  • Hjort, N. L., Holmes, C., Müller, P., and Walker, S. (2010). Bayesian Nonparametrics. Cambridge, UK: Cambridge University Press.
  • Hoff, P. D. (2003). “Bayesian methods for partial stochastic orderings.” Biometrika, 90(2): 303–317.
  • Ishwaran, H. and James, L. F. (2001). “Gibbs sampling methods for stick-breaking priors.” Journal of the American Statistical Association, 96(453).
  • Ishwaran, H. and James, L. F. (2002). “Approximate Dirichlet Process computing in finite normal mixtures.” Journal of Computational and Graphical Statistics, 11(3).
  • Klijian, A. (2012). “A novel approach to control air leaks in complex lung surgery: a retrospective review.” Journal of Cardiothoracic Surgery, 7: 49–54.
  • Kobayashi, H., Sekine, T., Nakamura, T., and Shimizu, Y. (2001). “In vivo evaluation of a new sealant material on a rat lung air leak model.” Journal of Biomedical Materials Research, 58(6): 658–665.
  • Lee, J., Thall, P. F., Ji, Y., and Müller, P. (2015). “Bayesian dose-finding in two treatment cycles based on the joint utility of efficacy and toxicity.” Journal of the American Statistical Association, 110(510): 711–722.
  • Lehmann, E. L. and Romano, J. P. (2006). Testing Statistical Hypotheses. Springer Science & Business Media.
  • MacEachern, S. (1999). “Dependent nonparametric processes.” In ASA Proceedings of the Section on Bayesian Statistical Science. Alexandria, VA: American Statistical Association.
  • Merritt, R. E., Singhal, S., and Shrager, J. B. (2010). “Evidence-based suggestions for management of air leaks.” Thoracic Surgery Clinics, 20(3): 435–448.
  • Neal, R. M. (2000). “Markov chain sampling methods for Dirichlet process mixture models.” Journal of Computational and Graphical Statistics, 9(2): 249–265.
  • Randles, R. H. and Wolfe, D. A. (1979). Introduction to the Theory of Nonparametric Statistics, volume 1. New York: Wiley.
  • Serra-Mitjans, M. and Belda-Sanchís, J. (2005). “Surgical sealant for preventing air leaks after pulmonary resections in patients with lung cancer.” The Cochrane Library.
  • Singhal, S., Ferraris, V. A., Bridges, C. R., Clough, E. R., Mitchell, J. D., Fernando, H. C., and Shrager, J. B. (2010). “Management of alveolar air leaks after pulmonary resection.” The Annals of Thoracic Surgery, 89(4): 1327–1335.
  • Thall, P. F. and Nguyen, H. Q. (2012). “Adaptive randomization to improve utility-based dose-finding with bivariate ordinal outcomes.” Journal of Biopharmaceutical Statistics, 22(4): 785–801.
  • Xu, D., Thall, P. F., Müller, P., and Reza, M. J. (2016). “Supplement: A decision-theoretic comparison of treatments to resolve air leaks after lung surgery based on nonparametric modeling.” Bayesian Analysis.

Supplemental materials

  • Supplementary Material: Supplement: A Decision-Theoretic Comparison of Treatments to Resolve Air Leaks After Lung Surgery Based on Nonparametric Modeling. It includes all the MCMC implementation details, model assessment simulation, more trial simulation results, and sensitivity analyses.