Abstract
To achieve personalized medicine, an individualized treatment strategy assigning treatment based on an individual's characteristics that leads to the largest benefit can be considered. Recently, a machine learning approach, O-learning, has been proposed to estimate an optimal individualized treatment rule (ITR), but it is developed to make binary decisions and thus limited to compare two treatments. When many treatment options are available, existing methods need to be adapted by transforming a multiple treatment selection problem into multiple binary treatment selections, for example, via one-vs-one or one-vs-all comparisons. However, combining multiple binary treatment selection rules into a single decision rule requires careful consideration, because it is known in the multicategory learning literature that some approaches may lead to ambiguous decision rules. In this work, we propose a novel and efficient method to generalize outcome-weighted learning for binary treatment to multi-treatment settings. We solve a multiple treatment selection problem via sequential weighted support vector machines. We prove that the resulting ITR is Fisher consistent and obtain the convergence rate of the estimated value function to the true optimal value, i.e., the estimated treatment rule leads to the maximal benefit when the data size goes to infinity. We conduct simulations to demonstrate that the proposed method has superior performance in terms of lower mis-allocation rates and improved expected values. An application to a three-arm randomized trial of major depressive disorder shows that an ITR tailored to individual patient's expectancy of treatment efficacy, their baseline depression severity and other characteristics reduces depressive symptoms more than non-personalized treatment strategies (e.g., treating all patients with combined pharmacotherapy and psychotherapy).