Bayesian negative-binomial-family-based multistate Markov model for the evaluation of periodic population-based cancer screening considering incomplete information and measurement errors

Chen-Yang Hsu, Ming-Fang Yen, Anssi Auvinen, Sherry Chiu, Hsiu-Hsi Chen

研究成果: 雜誌貢獻文章同行評審

2 引文 斯高帕斯(Scopus)

摘要

Population-based cancer screening is often asked but hardly addressed by a question: “How many rounds of screening are required before identifying a cancer of interest staying in the pre-clinical detectable phase (PCDP)?” and also a similar one related to the number of screens required for stopping screening for the low risk group. It can be answered by using longitudinal follow-up data on repeated rounds of screen, namely periodic screen, but such kind of data are rather complicated and fraught with intractable statistical properties including correlated multistate outcomes, unobserved and incomplete (censoring or truncation) information, and imperfect measurements. We therefore developed a negative-binomial-family-based discrete-time stochastic process, taking sensitivity and specificity into account, to accommodate these thorny issues. The estimation of parameters was implemented with Bayesian Markov Chain Monte Carlo method. We demonstrated how to apply this proposed negative-binomial-family-based model to the empirical data similar to the Finnish breast cancer screening program.
原文英語
頁(從 - 到)1-21
期刊Statistical Methods in Medical Research
DOIs
出版狀態已發佈 - 十二月 15 2016

指紋

深入研究「Bayesian negative-binomial-family-based multistate Markov model for the evaluation of periodic population-based cancer screening considering incomplete information and measurement errors」主題。共同形成了獨特的指紋。

引用此