Flexible joint model for time-to-event and non-Gaussian longitudinal outcomes.

Bayesian P-splines; Joint models; generalized linear mixed models; longitudinal outcome; survival outcome; Humans; Longitudinal Studies; Proportional Hazards Models; Models, Statistical; Linear Models; Survival Analysis; Glioblastoma/mortality; Computer Simulation; Disease Progression; Bayes Theorem; Glioblastoma; Epidemiology; Statistics and Probability; Health Information Management

Abstract :

[en] In medical studies, repeated measurements of biomarkers and time-to-event data are often collected during the follow-up period. To assess the association between these two outcomes, joint models are frequently considered. The most common approach uses a linear mixed model for the longitudinal part and a proportional hazard model for the survival part. The latter assumes a linear relationship between the survival covariates and the log hazard. In this work, we propose an extension allowing the inclusion of nonlinear covariate effects in the survival model using Bayesian penalized B-splines. Our model is valid for non-Gaussian longitudinal responses since we use a generalized linear mixed model for the longitudinal process. A simulation study shows that our method gives good statistical performance and highlights the importance of taking into account the possible nonlinear effects of certain survival covariates. Data from patients with a first progression of glioblastoma are analysed to illustrate the method.

Research Center/Unit :

Mathematics - ULiège
ISBA-LIDAM - UCLouvain

Disciplines :

Mathematics

Author, co-author :

Doms, Hortense ; Institut de Statistique, Biostatistique et Sciences Actuarielles, Université catholique de Louvain, Louvain-la-Neuve, Belgium

Lambert, Philippe ; Université de Liège - ULiège > Département des sciences sociales > Méthodes quantitatives en sciences sociales ; Institut de Statistique, Biostatistique et Sciences Actuarielles, Université catholique de Louvain, Louvain-la-Neuve, Belgium

Legrand, Catherine; Institut de Statistique, Biostatistique et Sciences Actuarielles, Université catholique de Louvain, Louvain-la-Neuve, Belgium

Language :

English

Title :

Flexible joint model for time-to-event and non-Gaussian longitudinal outcomes.

Publication date :

October 2024

Journal title :

Statistical Methods in Medical Research

ISSN :

0962-2802

eISSN :

1477-0334

Publisher :

SAGE, England

Volume :

Issue :

Pages :

1783 - 1799

Peer reviewed :

Peer Reviewed verified by ORBi

Additional URL :

https://journals.sagepub.com/doi/pdf/10.1177/09622802241269010

Funders :

FWB - Fédération Wallonie-Bruxelles

Funding text :

The authors acknowledge the support of the ARC project IMAL (grant 20/25-107) financed by the Wallonia-Brussels Federation and granted by the Acad\u00E9mie universitaire Louvain. The authors thank the European Organization for Research and Treatment of Cancer for permission to use the data from EORTC-26101. The contents of this publication and methods used are solely the responsibility of the authors and do not necessarily represent the official views of the EORTC. The author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article.The authors acknowledge the support of the ARC project IMAL (grant 20/25-107) financed by the Wallonia-Brussels Federation and granted by the Acad\u00E9mie universitaire Louvain. The authors thank the European Organization for Research and Treatment of Cancer for permission to use the data from EORTC-26101. The contents of this publication and methods used are solely the responsibility of the authors and do not necessarily represent the official views of the EORTC.

Available on ORBi :

since 10 March 2025

Statistics

Number of views

34 (2 by ULiège)

Number of downloads

1 (1 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

Rizopoulos D. Joint Models for Longitudinal and Time-to-Event Data, With Applications in R. Boca Raton: Chapman & Hall, 2012.
Faucett C Thomas D. Simultaneously modelling censored survival data and repeatedly measured covariates: a Gibbs sampling approach. Stat Med 1996; 15: 1663–1685.
Wulfsohn M Tsiatis A. A joint model for survival and longitudinal data measured with error. Biometrics 1997; 53: 330–339.
Faucett CL Schenker N Elashoff RM. Analysis of censored survival data with intermittently observed time-dependent binary covariates. J Am Stat Assoc 1998; 93: 427–437.
Viviani S Alfo M Rizopoulos D. Generalized linear mixed joint model for longitudinal and survival outcomes. Stat Comput 2014; 24: 417–427.
Rizopoulos D. The R package JMbayes for fitting joint models for longitudinal and time-to-event data using MCMC. J Stat Softw 2016; 72: 1–45.
Brown ER Ibrahim JG DeGruttola V. A flexible B-spline model for multiple longitudinal biomarkers and survival. Biometrics 2005; 61: 64–73.
Chi Y Ibrahim JG. Joint models for multivariate longitudinal and multivariate survival data. Biometrics 2006; 62: 432–445.
Rizopoulos D Ghosh P. A Bayesian semiparametric multivariate joint model for multiple longitudinal outcomes and a time-to-event. Stat Med 2011; 30: 1366–1380.
Elashoff RM Li G Lin N. A joint model for longitudinal measurements and survival data in the presence of multiple failure types. Biometrics 2008; 64: 762–771.
Williamson P Kolamunnage-Dona R Philipson P, et al. Joint modelling of longitudinal and competing risks data. Stat Med 2008; 27: 6426–6438.
Andrinopoulou ER Rizopoulos D Takkenberg JJM, et al. Joint modeling of two longitudinal outcomes and competing risk data. Stat Med 2014; 33: 3167–3178.
Tsiatis AA Davidian M. Joint modeling of longitudinal and time-to-event data: an overview. Stat Sin 2004; 14: 809–834.
Papageorgiou G Mauff K Tomer A, et al. An overview of joint modeling of time-to-event and longitudinal outcomes. Annu Rev Stat Appl 2019; 6: 223–240.
Wu L Liu W Yi GY, et al. Analysis of longitudinal and survival data: joint modeling, inference methods, and issues. J Probab Stat 2012; 2012: 1–17.
Andrinopoulou ER Rizopoulos D Takkenberg JJM, et al. Combined dynamic predictions using joint models of two longitudinal outcomes and competing risk data. Stat Methods Med Res 2017; 26: 1787–1801.
Eilers PHC Marx BD. Flexible smoothing with B-splines and penalties. Stat Sci 1996; 11: 89–121.
Köhler M Umlauf N Beyerlein A, et al. Flexible Bayesian additive joint models with an application to type 1 diabetes research. Biometrical J 2017; 59: 1144–1165.
Lang S Brezger A. Bayesian P-splines. J Comput Graph Stat 2004; 13: 183–212.
Wick W Gorlia T Bendszus M et al. Lomustine and bevacizumab in progressive glioblastoma. New England J Med 2017; 377: 1954–1963.
Taal W Oosterkamp HM Walenkamp AM et al. Combination of bevacizumab and lomustine in patients with first recurrence of glioblastoma: prolongs progression-free survival but not overall survival: a randomized, phase III trial of the EORTC brain tumor and radiotherapy groups. J Clin Oncol 2014; 32: 1239–1247.
Tan AC Ashley DM L’opez GY, et al. Management of glioblastoma: state of the art and future directions. CA: A Cancer J Clinici 2020; 70: 299–312.
Brown H Prescott R. Applied Mixed Models in Medicine. 2nd ed. New York: John Wiley and Sons, 2006.
Marx BD Eilers PHC. Direct generalized additive modeling with penalized likelihood. Comput Stat Data Anal 1998; 28: 193–209.
Lambert P Eilers PHC. Bayesian proportional hazards model with time varying regression coefficients: a penalized Poisson regression approach. Stat Med 2005; 24: 3977–3989.
Jullion A Lambert P. Robust specification of the roughness penalty prior distribution in spatially adaptive Bayesian P-splines models. Comput Stat Data Anal 2007; 51: 2542–2558.
Rue H Held L. Gaussian Markov Random Fields: Theory and Applications. Boca Raton: CRC Press, 2005.
Alsefri M Sudell M Garcia-Finana M, et al. Bayesian joint modelling of longitudinal and time to event data: a methodological review. BMC Med Res Methodol 2020; 20: 1–17.
Rizopoulos D Papageorgiou G Afonso P. JMbayes2: Extended Joint Models for Longitudinal and Time-to-Event Data, 2023. URL http://CRAN.R-project.org/package=JMbayes2, R package version 0.4-5.
Wood S. Generalized Additive Models: An Introduction With R. Boca Raton, London, New York: Chapman and Hall/CRC Press, 2017.
Crowther MJ Lambert PC. Simulating biologically plausible complex survival data. Stat Med 2013; 32: 4118–4134.
Brent RP. Some efficient algorithms for solving systems of nonlinear equations. SIAM J Numer Anal 1973; 10: 327–344.
Geweke J. Evaluating the accuracy of sampling-based approaches to calculating posterior moments. Bayesian Stat 1992; 4: 641–649.
Gorlia T Stupp R Brandes AA et al. New prognostic factors and calculators for outcome prediction in patients with recurrent glioblastoma: a pooled analysis of EORTC brain tumour group phase I and II clinical trials. Eur J Cancer 2012; 48: 1176–1184.
ClinicalTrials.gov: National Library of Medicine (US). Identifier NCT01290939, Bevacizumab and Lomustine for Recurrent GBM, https://clinicaltrials.gov/ct2/show/NCT01290939 (2021, accessed 27 April 2023).
ECOG-ACRIN Cancer Research Group. ECOG Performance Status, https://ecog-acrin.org/resources/ecog-performance-status/ (2022, accessed 27 April 2023).
Chahal M Thiessen B Mariano C. Treatment of older adult patients with glioblastoma: moving towards the inclusion of a comprehensive geriatric assessment for guiding management. Curr Oncol 2022; 29: 360–376.
Wood SN. On P-values for smooth components of an extended generalized additive model. Biometrika 2013; 100: 221–228.
Singer M Webb AR. Oxford Handbook of Critical Care. Oxford: Oxford University Press, 2005.
Ibrahim JG Chu H Chen LM. Basic concepts and methods for joint models of longitudinal and survival data. J Clini Oncol: Off J Am Soc Clini Oncol 2010; 28: 2796–2801.