Supporting information may be found in the online version of this article.
A Bayesian model for misclassified binary outcomes and correlated survival data with applications to breast cancer†‡
Article first published online: 21 SEP 2012
Copyright © 2012 John Wiley & Sons, Ltd.
Statistics in Medicine
Volume 32, Issue 13, pages 2320–2334, 15 June 2013
How to Cite
Luo, S., Yi, M., Huang, X. and Hunt, Kelly K. (2013), A Bayesian model for misclassified binary outcomes and correlated survival data with applications to breast cancer. Statist. Med., 32: 2320–2334. doi: 10.1002/sim.5629
Sheng Luo and Min Yi contributed equally to this work.
- Issue published online: 8 MAY 2013
- Article first published online: 21 SEP 2012
- Manuscript Accepted: 27 AUG 2012
- Manuscript Received: 27 SEP 2011
- NIH. Grant Number: U01 NS043127
- NINDS. Grant Number: U01NS43128
- binomial regression;
- Cox model;
- frailty model;
- latent class model;
- Markov chain Monte Carlo;
- tumor relapse
Breast cancer patients may experience ipsilateral breast tumor relapse (IBTR) after breast conservation therapy. IBTR is classified as either true local recurrence or new ipsilateral primary tumor. The correct classification of IBTR status has significant implications in therapeutic decision-making and patient management. However, the diagnostic tests to classify IBTR are imperfect and prone to misclassification. In addition, some observed survival data (e.g., time to relapse, time from relapse to death) are strongly correlated with IBTR status. We present a Bayesian approach to model the potentially misclassified IBTR status and the correlated survival information. We conduct the inference using a Bayesian framework via Markov chain Monte Carlo simulation implemented in WinBUGS. Extensive simulation shows that the proposed method corrects biases and provides more efficient estimates for the covariate effects on the probability of IBTR and the diagnostic test accuracy. Moreover, our method provides useful subject-specific patient prognostic information. Our method is motivated by, and applied to, a dataset of 397 breast cancer patients. Copyright © 2012 John Wiley & Sons, Ltd.