Data-guided Treatment Recommendation with Feature Scores
In this paper, we consider the use of large-scale genomics data for treatment recommendation. This is related to the individualized treatment rule [Qian and Murphy 2011] but we specially aim at overcoming its limitations when there is a large number of covariates and/or an issue of model misspecification. We tackle the problem using a dimension reduction method, namely Sliced Inverse Regression (SIR, [Li 1991]), with a rich class of models for the treatment response. More interestingly, SIR defines a feature space for high-dimensional data, offering an advantage similar to the popular neural network models. With the features obtained from SIR, simple visualization is used to compare different treatment options and display the recommended treatment. We further derive the consistency and the convergence rate of the proposed recommendation approach through a value function. The effectiveness of the proposed approach is demonstrated by simulation studies and a real-data example of the treatment of multiple myeloma with favorable performance.
READ FULL TEXT