Joint modelling of longitudinal and time-to-event data applied to group sequential trials

  • Abigail Burdon

Student thesis: Doctoral ThesisPhD


Consider a Phase 3 clinical trial where the primary endpoint is overall survival. The investigators wish to define a group sequential stopping rule which allows for early stopping for efficacy and early stopping for futility. Suppose that longitudinal data are observed on a biomarker which is assumed to be predictive of survival, and we wish to use this biomarker information to inform early stopping decisions.

We shall first present a joint model for survival and longitudinal data and a method which establishes the distribution of successive estimates of parameters in the joint model across interim analyses. Then, we are equipped to use the estimates to define both efficacy and futility stopping rules. With the methodology in place, by simulation we can assess the potential benefits of including biomarker information, how this affects interim decisions and ultimately alters the trial.

A second joint model is then considered where treatment is assumed to have a direct effect on survival and an indirect effect acting through the biomarker. The challenge here is to summarise the overall effect of treatment and we shall use the restricted mean survival time (RMST) methodology to do so. We show that it is possible to create a group sequential trial based on this complex joint model and discuss the design considerations for a trial using RMST as an analysis approach.
Date of Award14 Feb 2022
Original languageEnglish
Awarding Institution
  • University of Bath
SupervisorChristopher Jennison (Supervisor) & Vangelis Evangelou (Supervisor)

Cite this