Bayesian semi-parametric inference for clustered recurrent events with zero-inflation and a terminal event/4163305

Abstract

Recurrent event data are common in clinical studies when participants are followed longitudinally, and are often subject to a terminal event. With the increasing popularity of large pragmatic trials and a heterogeneous source population, participants are often nested in clinics and can be either susceptible or structurally unsusceptible to the recurrent process. These complications require new modeling strategies to accommodate potential zero-event inflation as well as hierarchical data structures in both the terminal and non-terminal event processes. In this paper, we develop a Bayesian semiparametric model to jointly characterize the zero-inflated recurrent event process and the terminal event process. We use a point mass mixture of non-homogeneous Poisson processes to describe the recurrent intensity and introduce shared random effects from different sources to bridge the non-terminal and terminal event processes. To achieve robustness, we consider nonparametric Dirichlet processes to model the residual of the accelerated failure time model for the survival process as well as the cluster-specific frailty distribution, and develop a Markov Chain Monte Carlo algorithm for posterior inference. We demonstrate the superiority of our proposed model compared with competing models via simulations and apply our method to a pragmatic cluster-randomized trial for fall injury prevention among the elderly.

A comparison of analytical strategies for cluster randomized trials with survival outcomes in the presence of competing risks

“…A third limitation is that we have not considered the possible recurrence of our target event (fall-related injury) in the simulations, and have not addressed the death event as a semi-competing risk. 52 This may be one of the reasons why the multi-state models performs similarly to the Cox models, as we are merely interested in the time to first event. In more general settings, the multi-state model can be more suitable to complex survival data with transitions to more than two states.…”