Bayesian outcome weighted learning for estimating sparse optimal individualized treatment rules

2011 

Contributed Abstract 

Paper 

Sophia Yazzourh (1), Nikki Freeman (2)

(1) Universite de Toulouse, N/A, (2) University of North Carolina at Chapel Hill, N/A

Nikki Freeman  
University of North Carolina at Chapel Hill

Sophia Yazzourh  
Universite de Toulouse

Nikki Freeman  
University of North Carolina at Chapel Hill

One of the primary goals of statistical precision medicine is to learn optimal individualized treatment rules (ITRs). The classification-based approach to estimating optimal ITRs was first introduced in outcome-weighted learning (OWL), which recasts the optimal ITR learning problem into a weighted classification problem. In this presentation, we introduce a Bayesian formulation of OWL. Starting from the OWL objective function, we generate an empirical likelihood that can be expressed as a scale mixture of normal distributions. We consider two types of prior distributions: a prior distribution that is equivalent to L-1 regularization of the ITR parameters and the spike-and-slab prior which enables ITR variable selection. A Gibbs sampling algorithm is developed for estimation. In addition to providing a strategy for learning an optimal ITR, Bayesian OWL provides (1) a principled approach for ITR variable selection and, thereby, the generation of parsimonious rules and (2) a natural, probabilistic approach to estimate uncertainty in ITR treatment recommendations themselves. We demonstrate our method through several simulation studies and a healthcare application.

Precision medicine|Individualized treatment rule|Bayesian machine learning| | |

Biometrics Section

Personalized/Precision Medicine