A Bayesian proportional hazards mixture cure model for partly interval-censored data
Principal Investigator
Name
Chun Pan
Degrees
PhD
Institution
Hunter College
Position Title
Assistant Professor
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1437
Initial CDAS Request Approval
Jan 4, 2024
Title
A Bayesian proportional hazards mixture cure model for partly interval-censored data
Summary
Partly interval-censored data arise when some failure times are exactly observed while others are only known to be within certain time intervals. Cure fraction arises when a subgroup of subjects will never experience the event of interest in a study. Proportional hazards mixture cure (PHMC) model is a popular analysis method for survival data where a subgroup of subjects do not experience the event of interest. In the PLCO cancer screening trial, each participant is screened periodically for several types of cancer: prostate, lung, colorectal and ovarian. If cancer is detected at one visit, its exact occurrence is between the previous and the current visits. Thus the event time is interval-censored. Furthermore, at the end of the follow up, a substantial portion of the study subjects will still be cancer free. So it has a cure fraction. It is challenging to fit a PHMC model to partly interval-censored data due to its complex data structure. Our goal is to develop such an algorithm and apply it to the PLCO data.
Aims
Develop an efficient and easy to implement Bayesian semiparametric approach for fitting a proportional hazards mixture cure model to partly interval-censored data with a cure fraction.
Provide statistical inference in the latency part: among subjects who will eventually experience the event of interest, how potential risk factors affect hazard function/survival function.
Provide statistical inference in the incidence part: among all subjects, how potential risk factors affect whether or not one subject will eventually experience the event of interest.
Collaborators
NA