DeepAI AI Chat
Log In Sign Up

Bayesian Estimation of Two-Part Joint Models for a Longitudinal Semicontinuous Biomarker and a Terminal Event with R-INLA: Interests for Cancer Clinical Trial Evaluation

by   Denis Rustand, et al.

Two-part joint model for a longitudinal semicontinuous biomarker and a terminal event has been recently introduced based on frequentist computation. The biomarker distribution is decomposed into a probability of positive value and the expected value among positive values. Shared random effects can represent the association structure between the biomarker and the terminal event. The computational burden increases compared to standard joint models with a single regression model for the biomarker. In this context, the frequentist estimation implemented in the R package frailtypack can be challenging for complex models (i.e., large number of parameters and dimension of the random effects). As an alternative, we propose a Bayesian estimation of two-part joint models based on the Integrated Nested Laplace Approximation (INLA) algorithm to alleviate the computational burden and be able to fit more complex models. Our simulation studies show that R-INLA reduces the computation time substantially as well as the variability of the estimates and improves the model convergence compared to frailtypack. We contrast the Bayesian and frequentist approaches in two randomized cancer clinical trials (GERCOR and PRIME studies), where R-INLA suggests a stronger association between the biomarker and the risk of event. Moreover, the Bayesian approach was able to characterize subgroups of patients associated with different responses to treatment in the PRIME study where frailtypack had convergence issues. Our study suggests that the Bayesian approach using R-INLA algorithm enables broader applications of the two-part joint model to clinical applications.


page 1

page 2

page 3

page 4


Joint longitudinal and time-to-event models for multilevel hierarchical data

Joint modelling of longitudinal and time-to-event data has received much...

merlin: An R package for Mixed Effects Regression for Linear, Nonlinear and User-defined models

The R package merlin performs flexible joint modelling of hierarchical m...

Adaptive enrichment trial designs using joint modeling of longitudinal and time-to-event data

Adaptive enrichment allows for pre-defined patient subgroups of interest...

BAGEL: A Bayesian Graphical Model for Inferring Drug Effect Longitudinally on Depression in People with HIV

Access and adherence to antiretroviral therapy (ART) has transformed the...

Bayesian shared-parameter models for analysing sardine fishing in the Mediterranean Sea

European sardine is experiencing an overfishing around the world. The dy...