Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 277 - SPEED: Biometrics and Environmental Statistics Part 1
Type: Contributed
Date/Time: Tuesday, August 9, 2022 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract #322827
Title: Model Selection for Survival Individualized Treatment Rules Using the Jackknife Estimator
Author(s): Gilson D Honvoh* and Hunyong Cho and Michael Kosorok
Companies: University of North Carolina at Chapel Hill and University of North Carolina at Chapel Hill and University of North Carolina at Chapel Hill
Keywords: Precision medicine; Individualized treatment rules; Censoring; Cross-validation; Jackknife; Inverse probability of censoring weighted

Precision medicine is formalized through the identification of individualized treatment rules (ITRs) that maximize a clinical outcome. When the type of outcome is time-to-event, the correct handling of censoring is crucial for estimating reliable optimal ITRs. In this paper, we extend the jackknife estimator of the value function to allow for right-censored data for a binary treatment. The jackknife estimator or leave-one-out-cross-validation (Jiang et al., 2020) approach was proposed to estimate the value function and select optimal ITRs using existing machine learning methods. We address the issue of censoring by introducing an inverse probability of censoring weighted (IPCW) adjustment in the expression of the jackknife estimator of the value function. We prove the consistency of the newly proposed estimator under minimal assumptions. Furthermore, using a Z-test, we compare the optimal ITR learned with a precision medicine model with the zero-order model. Through simulation studies, we show the asymptotic properties and the performance of our proposed estimator under different censoring rates.

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

Back to the full JSM 2022 program