|
Activity Number:
|
355
- Contributed Poster Presentations: Biopharmaceutical Section
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #304668
|
|
|
Title:
|
A Personalized Medicine Approach for Comparative Evidence in Non-Randomized Studies
|
|
Author(s):
|
Carl De Moor* and Lu Tian and Fabio Pellegrini
|
|
Companies:
|
Biogen and Stanford University School of Medicine and Biogen International GmbH
|
|
Keywords:
|
Personalized medicine;
observational data;
doubly robust estimator;
comparative effectiveness research
|
|
Abstract:
|
Numerous advances have been made to estimate individualized treatment effects in randomized clinical trials to identify subgroups of patients who may benefit more from a given treatment. Achieving the same objective in non-randomized studies conducted in real world settings presents unique challenges. In particular, imbalance in covariate distributions between treatment groups may introduce spurious treatment covariate interactions, especially when the prognostic effects of the covariates are not disentangled from their role as effect modifiers. In this work, we will present a set of new methods for estimating a continuous score measuring the individualized treatment benefit and validating the quality of such a scoring system based on observational data. The double robustness technique has been employed to overcome the difficulties caused by covariate imbalance. The method addressing individualized treatment effects will be illustrated here with two treated observational cohorts of multiple sclerosis patients.
|
Authors who are presenting talks have a * after their name.
