|
Activity Number:
|
166
- Non-Clinical Statistics, Personalized Medicine, and Other Topics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 10, 2021 : 10:00 AM to 11:50 AM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #318832
|
|
|
Title:
|
A Comparison of Precision Medicine Methods for Count Outcomes: A Simulation Study and a Case Study in Multiple Sclerosis
|
|
Author(s):
|
Xiaotong Jiang* and Gabrielle Simoneau and Bora Youn and Changyu Shen and Fabio Pellegrini and Carl de Moor
|
|
Companies:
|
Biogen and Biogen and Biogen and Biogen and Biogen and Biogen
|
|
Keywords:
|
precision medicine;
doubly robust estimator;
individualized treatment rules;
treatment effect heterogeneity;
sample size;
count outcomes
|
|
Abstract:
|
Precision medicine (PM) methods aim to discover an optimal individualized treatment rule (ITR), which recommends a treatment based on patient characteristics at the time of treatment decision that leads to the best patient outcome. The goal of this study is to understand the ability of PM methods to correctly identify optimal ITR in various situations for count outcomes. In the context of both randomized trials and observational studies, we compare existing PM methods using the analysis of number of relapses in multiple sclerosis (MS) as a motivating example. We compare methods in terms of the estimated value function, which is the average treatment effect in the population if patients follow the estimated optimal ITR. In simulations, we study the impact of sample size and varying levels of treatment effect heterogeneity. In the case study, we compare optimal ITRs choosing between dimethyl fumarate and teriflunomide as the treatment of MS using US claims. Results show that a subset of methods outperforms the “one-size-fits-all" rule regardless of heterogeneity levels and model performance gradually converges as sample size increases.
|
Authors who are presenting talks have a * after their name.
