Activity Number:
|
493
- Section on Risk Analysis CPapers 1
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Section on Risk Analysis
|
Abstract #309764
|
|
Title:
|
Using Benefit-Risk Process to Evaluate Treatment Effect in the Presence of a Primary Endpoint and Secondary Measurements
|
Author(s):
|
Yuchen Yang* and Chen Hu and Mei-Cheng Wang
|
Companies:
|
Johns Hopkins University and Johns Hopkins University and Johns Hopkins University
|
Keywords:
|
Composite endpoint;
Benefit-risk assessment;
Semi-competing risks
|
Abstract:
|
Decision making in the presence of a primary endpoint and secondary measurements is challenging in clinical trials. In this paper, we consider the benefit-risk process, which is a time-dependent composite measure that accumulates evidence from both the primary endpoint and secondary measurements. The benefit-risk process can be employed to increase power and provide benefit-risk assessment in clinical trials. We show that the two sample testing procedure of the benefit-risk process for a fixed time limit is closely related with the weighted Kaplan-Meier statistics. A semiparametric regression model for the benefit-risk process is developed to evaluate the potentially time-varying treatment effect that allows for change of directions when the effects of the treatment on the primary endpoint and secondary measurements are opposite. Large sample properties of the proposed estimator are derived in the absence of censoring and in the presence of completely independent censoring. Simulation and data analysis results are presented. The proposed regression methodology provides an alternative way to analyze semi-competing risks data and composite endpoints.
|
Authors who are presenting talks have a * after their name.