Clinically relevant graphical predictions from Bayesian joint longitudinal-survival models

  • Laura A. Hatfield
  • Bradley P. Carlin


Recent interest in understanding the effect of interventions on patient-reported outcomes as well as traditional clinical endpoints has led to an expansion of methods for simultaneous modeling of longitudinal and survival data in clinical trials. Such joint models link the multiple outcome measures using an underlying latent structure, typically a collection of individual-level random effects. They can estimate treatment effects separately on different aspects of a disease process, as well as illuminate associations among outcomes and individual variability. In communicating model output to clinicians and patients, it is challenging to convey a meaningful interpretation of multiple treatment effects, complex outcome associations, and important underlying assumptions. This paper presents graphical displays designed to make the output of Bayesian joint models accessible to non-technical audiences, while preserving important methodological features. We emphasize individual-level posterior predictions of longitudinal and survival outcomes, illustrating our methods using patient-reported symptom severity and survival in a clinical trial example.


Patient-reported outcomes Joint longitudinal-survival models Parameter interpretation Statistical graphics Hierarchical Bayesian methods Markov chain Monte Carlo 

Supplementary material

10742_2012_87_MOESM1_ESM.pdf (32 kb)
(PDF 33 KB)


  1. Carlin, B., Louis, T.: Bayesian Methods for Data Analysis, 3rd edn. Chapman & Hall/CRC, Boca Raton (2009)Google Scholar
  2. Fairclough, D.: Patient reported outcomes as endpoints in medical research. Stat. Methods Med. Res. 13, 115–138 (2004)PubMedCrossRefGoogle Scholar
  3. Gelman, A.: Prior distributions for variance parameters in hierarchical models. Bayesian Anal. 3, 515–533 (2006)Google Scholar
  4. Gray, S., Brookmeyer, R.: Multidimensional longitudinal data: estimating a treatment effect from continuous, discrete, or time-to-event response variables. J. Am. Stat. Assoc. 95, 396–406 (2000)Google Scholar
  5. Hatfield, L., Boye, M., Carlin, B.: Joint modeling of multiple longitudinal patient-reported outcomes and survival. J. Biopharm. Stat. 21, 971–991 (2011)PubMedCrossRefGoogle Scholar
  6. Hatfield, L., Boye, M., Hackshaw, M., Carlin, B.: Multilevel Bayesian models for survival times and longitudinal patient-reported outcomes with many zeros. J. Am. Stat. Assoc. (to appear) (2012a)Google Scholar
  7. Hatfield, L., Hodges, J., Carlin, B.: Combining longitudinal and survival information in Bayesian joint models: when are treatment estimates improved? Technical report, Division of Biostatistics, University of Minnesota, Research Report # 2012-002 (2012b)Google Scholar
  8. Kurland, B., Johnson, L., Egleston, B., Diehr, P.: Longitudinal data with follow-up truncated by death: match the analysis method to research aims. Stat. Sci. 24, 211–222 (2009)PubMedCrossRefGoogle Scholar
  9. Rizopoulos, D.: Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data. Biometrics 67, 819–829 (2011)PubMedCrossRefGoogle Scholar
  10. Rubin, D.: Inference and missing data (with discussion). Biometrika 63, 581–592 (1976)CrossRefGoogle Scholar
  11. Soto, G., Spertus, J.: EPOCH® and ePRISM®: a web-based translational framework for bridging outcomes research and clinical practice. Comput. Cardiol. 34, 205–208 (2007)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Department of Health Care PolicyHarvard Medical SchoolBostonUSA
  2. 2.Division of Biostatistics, School of Public HealthUniversity of MinnesotaMinneapolisUSA

Personalised recommendations