Accelerated Recurrent Time Analysis of Doubly Censored Data: An Application to Pseudomona Aeruginosa Infection in Young Children with Cystic Fibrosis

• Activity Number: 74
• Type: Contributed
• Date/Time: Sunday, July 29, 2012 : 4:00 PM to 5:50 PM
• Sponsor: Biometrics Section
• Author(s): Xiaoyan Sun*+ and Limin Peng and Yijian Huang and Amita Manatunga and HuiChuan J. Lai
• Companies: Emory University and Emory University and Emory University and Emory University and University of Wisconsin-Madison
• Keywords: recurrent event ; doubly censoring ; accelerated recurrent time model ; estimating equation ; varying-coefficient model

Abstract

Left censoring often occurs in registry-based studies. For example, recurrent pseudomonas aeruginosa (PA) infections accelerate the lung disease and shorten the survival of Cystic Fibrosis (CF) patients. While PA onset and remissions are usually well monitored during CF registry follow-up, the information on PA infections prior to the registry entry is often unavailable. In this work, we propose a new regression method for analyzing recurrent event data subject to such left censoring in addition to right censoring (ie. double censoring). We adopt the accelerated recurrent time model (Huang and Peng, 2009), and develop estimation and inference procedures that appropriate account for the presence of double censoring . We illustrate our method via an analysis of the time to expected frequency of PA infection in CF children through the use of the US CF Foundation Patient Registry (CFFPR).