Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 378 - LiDS Student Paper Award Winners: Topic-Contributed Papers
Type: Topic Contributed
Date/Time: Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
Sponsor: Lifetime Data Science Section
Abstract #322232
Title: Kullback-Leibler-Based Discrete Failure Time Models for Integration of Published Prediction Models with New Time-to-Event Dataset
Author(s): Di Wang* and Wen Ye and Randall Sung and Hui Jiang and Jeremy Taylor and Kevin He
Companies: University of Michigan and University of Michigan and University of Michigan and University of Michigan and University of Michigan and University of Michigan
Keywords: Calibration; Data integration; Kullback-Leibler discrimination; Survival prediction
Abstract:

Existing literature for prediction of time-to-event data has primarily focused on risk factors from a single individual-level dataset. However, these analyses may suffer from small sample sizes, high dimensionality, and low signal-to-noise ratios. To improve prediction performance and better understand risk factors associated with time-to-event outcomes, we consider the problem of integrating published survival models with an internal individual-level dataset. To incorporate information from published models while allowing differences in the underlying distributions, we propose a discrete failure time modeling procedure based on time-dependent Kullback-Leibler discriminatory information that measures the discrepancy between the published models and the internal dataset. Simulations were conducted to show the advantage of the proposed method compared with those solely based on data from the internal study or external information. We applied the proposed method to improve prediction performance on a kidney transplant dataset from a local hospital by integrating published survival models obtained from the Scientific Registry of Transplant Recipients (SRTR).


Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program