Session 35: Machine Learning and Precision Medicine

Session title: Machine Learning and Precision Medicine
Organizer: Haoda Fu (Eli Lilly)
Chair: Genevera Allen(Rice)
Time: June 6th, 8:30am – 10:00am
Location: VEC 404 /405

Speech 1:  Support vector machines for learning optimal individualized treatment rules with multiple treatments
Speaker: Donglin Zeng (UNC)
Abstract: Support vector machine (SVM) methods have been proposed to estimate optimal individualized treatment rules when treatment is binary. Extending SVM to more than two treatment options remains an open and challenging problem. In this work, we propose a novel and efficient algorithm to generalize SVM-based outcome weighted learning to a multi-treatment setting.  The proposed method sequentially solves binary SVM problems. Theoretically, we show that the resulting treatment rule is Fisher consistent and derive the convergence rate for the estimated value function. We conduct extensive simulation studies to demonstrate that the proposed method has superior performance to competing methods.

Speech 2: Individualized Treatment Recommendation (ITR) for SurvivalOutcomes
Speaker: Haoda Fu (Eli Lilly)
Abstract: ITR is a method to recommend treatment based on individual patient characteristics to maximize clinical benefit. During the past a few years, we have developed and published methods on this topic with various applications including comprehensive search algorithms, tree methods , benefit risk algorithm, multiple treatment & multiple ordinal treatment algorithms. In this talk, we propose a new ITR method to handle survival outcomes for multiple treatments. This new model enjoy the following practical and theoretical features

  1. Instead of fitting the data, our method directly search the optimal treatment policy which improvesthe efficiency
  2. To adjust censoring, we propose a doubly robust estimator. Our method only requires either censoring model or survival model is correct, but not both.  When both are correct, our method enjoys better efficiency
  3. Our method handles multiple treatments with intuitive geometry explanations
  4. Our method is Fisher’s consistent even under either censoring model or survival model misspecification (but not both).


This method has potential applications in multiple therapeutic areas. One direct impact for Diabetes business unit is that how we can leverage Lilly Diabetes’ broad treatment options to reduce or delay diabetes comorbidities such as CV event, diabetes related retinopathy, nephropathy, or neuropathy.

Speech 3: Estimation and Evaluation of Linear Individualized Treatment Rules to Guarantee Performance
Speaker: Yuanjia Wang (Columbia)
Abstract:  In clinical practice, an informative and practically useful treatment rule should be simple and transparent. However, because simple rules are likely to be far from optimal, effective methods to construct such rules must guarantee performance, in terms of yielding the best clinical outcome (highest reward) among the class of simple rules under consideration. Furthermore, it is important to evaluate the benefit of the derived rules on the whole sample and in pre-specified subgroups (e.g., vulnerable patients). To achieve both goals, we propose a robust machine learning method to estimate a linear treatment rule that is guaranteed to achieve optimal reward among the class of all linear rules. We then develop a diagnostic measure and inference procedure to evaluate the benefit of the obtained rule and compare it with the rules estimated by other methods. We provide theoretical justification for the proposed method and its inference procedure, and we demonstrate via simulations its superior performance when compared to existing methods. Lastly, we apply the method to the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) trial on major depressive disorder and show that the estimated optimal linear rule provides a large benefit for mildly depressed and severely depressed patients but manifests a lack-of-fit for moderately depressed patients.