Assessing the Predictive Performance of Survival Models with Longitudinal Data

Abstract

In many follow-up studies, different types of outcomes are collected including longitudinal measurements and time-to-event outcomes. Commonly, it is of interest to study the association between them. Different regression modelling techniques have been proposed in the literature to study such association. In this paper, we will focus on two of them: two-stage models and joint modelling framework and compare them in terms of the predictive capacity of the time-to-event model. Our interest is twofold: discussing the occurrence of bias estimations and predictive capacity of the models in short-term and long-term mortality in our particular case study, Cardiac Resynchronization Therapy (CRT).