A Bayesian model for spatial partly interval-censored data

Abstract

Partly interval-censored data often occur in cancer clinical trials and have been analyzed as right-censored data. Patients’ geographic information sometimes is also available and can be useful in testing treatment effects and predicting survivorship. We propose a Bayesian semiparametric method for analyzing partly interval-censored data with areal spatial information under the proportional hazards model. A simulation study is conducted to compare the performance of the proposed method with the main method currently available in the literature and the traditional Cox proportional hazards model for right-censored data. The method is illustrated through a leukemia survival data set and a dental health data set. The proposed method will be especially useful for analyzing progression-free survival in multi-regional cancer clinical trials.

Keywords:

• Bayesian semiparametric
• Conditionally autoregressive prior
• Partly interval-censored data
• Proportional hazards model
• Spatial frailty

Acknowledgments

We thank Dr Emmanuel Lesaffre and Dr Dominique Declerck for allowing us to use the Signal Tandmobiel data and reviewing the analysis result. We also greatly appreciate the Editor-in-Chief for his suggestion of investigating the sensitivity of the proposed method to the prior specification of the spatial precision parameter, which helped improve the manuscript.

Additional information

Funding

The first author’s work was supported by the National Institute of Health under Award Number SC2GM135078.