Bayesian Nonparametric Cost-Effectiveness Analyses: Causal Estimation and Adaptive Subgroup Discovery

Cost-effectiveness analyses (CEAs) are at the center of health economic decision making. While these analyses help policy analysts and economists determine coverage, inform policy, and guide resource allocation, they are statistically challenging for several reasons. Cost and effectiveness are correlated and follow complex joint distributions which are difficult to capture parametrically. Effectiveness (often measured as increased survival time) and accumulated cost tends to be right-censored in many applications. Moreover, CEAs are often conducted using observational data with non-random treatment assignment. Policy-relevant causal estimation therefore requires robust confounding control. Finally, current CEA methods do not address cost-effectiveness heterogeneity in a principled way - often presenting population-averaged estimates even though significant effect heterogeneity may exist. Motivated by these challenges, we develop a nonparametric Bayesian model for joint cost-survival distributions in the presence of censoring. Our approach utilizes a joint Enriched Dirichlet Process prior on the covariate effects of cost and survival time, while using a Gamma Process prior on the baseline survival time hazard. Causal CEA estimands, with policy-relevant interpretations, are identified and estimated via a Bayesian nonparametric g-computation procedure. Finally, we outline how the induced clustering of the Enriched Dirichlet Process can be used to adaptively detect presence of subgroups with different cost-effectiveness profiles. We outline an MCMC procedure for full posterior inference and evaluate frequentist properties via simulations. We use our model to assess the cost-efficacy of chemotherapy versus radiation adjuvant therapy for treating endometrial cancer in the SEER-Medicare database.

[1]  Anastasios A. Tsiatis,et al.  Estimating medical costs with censored data , 2000 .

[2]  Michael J. Daniels,et al.  A framework for Bayesian nonparametric inference for causal effects of mediation , 2017, Biometrics.

[3]  Raul Cano.  On The Bayesian Bootstrap , 1992 .

[4]  Michael J Daniels,et al.  Bayesian nonparametric generative models for causal inference with missing at random covariates , 2017, Biometrics.

[5]  J. Robins.  A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

[6]  Dandan Xu,et al.  A Bayesian nonparametric approach to causal inference on quantiles , 2018, Biometrics.

[7]  D. Heitjan,et al.  Estimating cost-effectiveness from claims and registry data with measured and unmeasured confounders , 2019, Statistical methods in medical research.

[8]  J. Rosenthal,et al.  Optimal scaling for various Metropolis-Hastings algorithms , 2001 .

[9]  Abdus S Wahed,et al.  Bayesian Nonparametric Estimation for Dynamic Treatment Regimes With Sequential Transition Times , 2014, Journal of the American Statistical Association.

[10]  David B. Dunson,et al.  Improving prediction from dirichlet process mixtures via enrichment , 2014, J. Mach. Learn. Res..

[11]  Michael J Daniels,et al.  A Bayesian nonparametric approach to marginal structural models for point treatments and a continuous or survival outcome. , 2017, Biostatistics.

[12]  D. Lin,et al.  Linear regression analysis of censored medical costs. , 2000, Biostatistics.

[13]  Yijian Huang,et al.  Calibration Regression of Censored Lifetime Medical Cost , 2002 .

[14]  Jennifer L. Hill,et al.  Bayesian Nonparametric Modeling for Causal Inference , 2011 .

[15]  P. Richard Hahn,et al.  Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects , 2017, 1706.09523.

[16]  D. B. Dahl.  Bayesian Inference for Gene Expression and Proteomics: Model-Based Clustering for Expression Data via a Dirichlet Process Mixture Model , 2006 .

[17]  Stephen G. Walker,et al.  Markov beta and gamma processes for modelling hazard rates , 2002 .

[18]  Radford M. Neal.  Markov Chain Sampling Methods for Dirichlet Process Mixture Models , 2000 .

[19]  Gianluca Baio,et al.  Bayesian models for cost-effectiveness analysis in the presence of structural zero costs , 2013, Statistics in medicine.

[20]  Donald B. Rubin,et al.  Bayesian Inference for Causal Effects: The Role of Randomization , 1978 .

[21]  Arman Oganisian,et al.  A Bayesian nonparametric model for zero‐inflated outcomes: Prediction, clustering, and causal estimation , 2018, Biometrics.

[22]  D. Lin,et al.  Regression analysis of incomplete medical cost data , 2003, Statistics in medicine.

[23]  M. Stephens.  Dealing with label switching in mixture models , 2000 .

[24]  S. Athey,et al.  Estimating Treatment Effects with Causal Forests: An Application , 2019, Observational Studies.

[25]  Thomas A Louis,et al.  Individualized treatment effects with censored data via fully nonparametric Bayesian accelerated failure time models. , 2017, Biostatistics.

[26]  Nandita Mitra,et al.  A doubly robust approach for cost–effectiveness estimation from observational data , 2018, Statistical methods in medical research.