Online Program Home
  My Program

Abstract Details

Activity Number: 131 - Predictive Modeling in Data Science
Type: Contributed
Date/Time: Monday, July 31, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Learning and Data Science
Abstract #322975 View Presentation
Title: SVM-CART for Disease Classification
Author(s): Evan Reynolds* and Mousumi Banerjee and Brian Callaghan
Companies: University of Michigan and University of Michigan and University of Michigan
Keywords: Statistical Learning ; Complex Interactions ; Classification and Regression Trees ; Support Vector Machines ; Ensemble Classifiers
Abstract:

Classification and regression trees (CART) and support vector machines (SVM) have become very popular statistical learning tools for analyzing complex data that often arises in biomedical research. While both CART and SVM serve as powerful classifiers in many clinical settings, there are some common scenarios in which each fails to meet the performance and simplicity needed for use as a clinical decision-making tool. In this paper, we propose a new classification method, SVM-CART, that combines features of SVM and CART to produce a more flexible classifier that has the potential to outperform either method in terms of simplicity or prediction accuracy. Furthermore, to enhance prediction accuracy we provide extensions of a single SVM-CART to an ensemble. Finally, we develop methods to select the single most representative classifier from the SVM-CART ensemble. The goal is to produce a decision-making tool that can be used in the clinical setting, while still harnessing the stability and predictive improvements gained through the SVM-CART ensemble. The methods are illustrated using a clinical neuropathy dataset.


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

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association