Personalized Dose Guidance using Safe Bayesian Optimization

Abstract

This work considers the problem of personalized dose guidance using Bayesian optimization that learns the optimum drug dose tailored to each individual, thus improving therapeutic outcomes. Safe learning using interior point method ensures patient safety with high probability. This is demonstrated using the problem of learning the optimum bolus insulin dose in patients with type 1 diabetes to counteract the effect of meal consumption. Starting from no a priori information about the patients, our dose guidance algorithm is able to improve the therapeutic outcome (measured in terms of % timein-range) without jeopardizing patient safety. Other potential healthcare applications are also discussed.

Bayesian Optimization for the Inverse Problem in Electrocardiography

“…Due to the characteristics of the problem, where each single evaluation of the cost function is computationally expensive, we use a specialized CMA-ESbased Bayesian optimization technique, that can deliver good results even with a reduced number of function evaluations. Bayesian optimization already has a considerable number of success stories, when applied to medical issues such as assigning personalized dose to patients [14], individualized treatment rules [15], regenerative medicine [16], and deep brain stimulation [17], [18], among many others. The results obtained using Bayesian optimization were the motivation to use it as an alternative solution in the inverse problem of electrocardiography.…”