|
Activity Number:
|
8
- Machine Learning Methods and Applications: Making an Impact in Biomedical Research
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
|
Abstract #300273
|
Presentation
|
|
Title:
|
RELIEF-Based Feature Selection for Heterogeneous Treatment Effects with Massive Data
|
|
Author(s):
|
Xiaogang Su*
|
|
Companies:
|
University of Texas, El Paso
|
|
Keywords:
|
Feature Selection;
Heterogeneous Treatment Effects;
Precision medicine;
RELIEF
|
|
Abstract:
|
We extend the RELIEF machine learning techniques for feature selection in estimating heterogeneous treatment effects with big data. The proposed method facilitates a variable importance ranking for covariates in terms of their predictive (vs. prognostic) values in modifying the treatment effects. The method can also be oriented towards the assessment of qualitative treatment-by-covariate interactions. Properties of the proposed method are explored, including a statistical interpretation in association with the K nearest neighbors (KNN). We demonstrate the usefulness and efficiency of the proposed method and make comparison with other competitive approaches via both simulation and real data applications.
|
Authors who are presenting talks have a * after their name.
