Section: New Results

Joint modeling of longitudinal and repeated time-to-event data

Participants : Cyprien Mbogning, Kevin Bleakley, Marc Lavielle.

We have proposed a nonlinear mixed-effects framework to jointly model longitudinal and repeated time-to-event data. The article Joint modeling of longitudinal and repeated time-to-event data with maximum likelihood estimation via the SAEM algorithm was submitted in 2012. A parametric nonlinear mixed-effects model is used for the longitudinal observations and a parametric mixed-effects hazard model for repeated event times. We have shown the importance for parameter estimation of properly calculating the conditional density of the observations (given the individual parameters) in the presence of interval and/or right censoring. Parameters are estimated by maximizing the exact joint likelihood with the Stochastic Approximation Expectation-Maximization algorithm.

We have illustrated the use of these modeling methods in two real data examples: patient survival in primary biliary cirrhosis, and repeated epileptic seizure count data from a clinical trial.

This workflow for joint models is now implemented in the MONOLIX software