Combining Dynamic Predictions From Joint Models for Longitudinal and Time-to-Event Data Using Bayesian Model Averaging

• Published in: Journal of the American Statistical Association Vol. 109; no. 508; pp. 1385 - 1397
• Main Authors: Rizopoulos, Dimitris, Hatfield, Laura A., Carlin, Bradley P., Takkenberg, Johanna J. M.
• Format: Journal Article
• Language: English
• Published: Alexandria Taylor & Francis 02.10.2014; Taylor & Francis Group, LLC; Taylor & Francis Ltd
• Subjects: Applications and Case Studies; Averaging; Bayesian analysis; Bayesian networks; Biomarkers; Datasets; Heart valves; Induced substructures; Mathematical models; Multilevel models; prediction; Predictive modeling; Probability; Prognostic modeling; Random effects; Real time; Reoperation; Risk assessment; Risk prediction; Simulations; Statistical models; Statistics; Time-dependent covariates
• DOI: 10.1080/01621459.2014.931236
• ISSN: 1537-274X; 0162-1459

The joint modeling of longitudinal and time-to-event data is an active area of statistics research that has received a lot of attention in recent years. More recently, a new and attractive application of this type of model has been to obtain individualized predictions of survival probabilities and/or of future longitudinal responses. The advantageous feature of these predictions is that they are dynamically updated as extra longitudinal responses are collected for the subjects of interest, providing real time risk assessment using all recorded information. The aim of this article is two-fold. First, to highlight the importance of modeling the association structure between the longitudinal and event time responses that can greatly influence the derived predictions, and second, to illustrate how we can improve the accuracy of the derived predictions by suitably combining joint models with different association structures. The second goal is achieved using Bayesian model averaging, which, in this setting, has the very intriguing feature that the model weights are not fixed but they are rather subject- and time-dependent, implying that at different follow-up times predictions for the same subject may be based on different models. Supplementary materials for this article are available online.