Keywords: Machine Learning, Personalized Medicine
Individualized medical decision making is often complex due to patient treatment response heterogeneity. Pharmacotherapy may exhibit distinct efficacy and safety profiles for different patient populations. An “optimal” treatment that maximizes clinical benefit for a patient may also lead to concern of safety due to a high risk of adverse events. Thus, to guide individualized clinical decision making and deliver optimal tailored treatments, maximizing clinical benefit should be considered in the context of controlling for potential risk. In this work, we propose two approaches to identify personalized optimal treatment strategy that maximizes clinical benefit under a constraint on the average risk. We derive the theoretical optimal treatment rule under the risk constraint and draw an analogy to the Neyman-Pearson lemma to prove the theorem. We present algorithms that can be easily implemented by any off-the-shelf quadratic programming package. We conduct extensive simulation studies to show satisfactory risk control when maximizing the clinical benefit. Lastly, we apply our method to a randomized trial of type 2 diabetes patients to guide optimal utilization of the first line insulin treatments based on individual patient characteristics while controlling for the rate of hypoglycemia events. We identify baseline glycated hemoglobin level, body mass index, and fasting blood glucose as three key factors among 18 biomarkers to differentiate treatment assignments, and demonstrate a successful control of the risk of hypoglycemia in both the training and testing data set.