ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine

TL;DR

This paper introduces ESCADA, a novel safe and personalized dose allocation algorithm for precision medicine, specifically targeting the leveling of physiological variables, with proven theoretical guarantees and successful in silico testing in diabetes management.

Contribution

We develop ESCADA, a new multi-armed bandit algorithm designed for safe, personalized dose recommendations in leveling tasks, with theoretical regret and safety bounds, and demonstrate its effectiveness in diabetes simulation.

Findings

ESCADA outperforms GP-UCB and rule-based methods in simulations.

The algorithm provides strong safety guarantees during dose optimization.

In silico tests show improved patient safety and treatment efficacy.

Abstract

Finding an optimal individualized treatment regimen is considered one of the most challenging precision medicine problems. Various patient characteristics influence the response to the treatment, and hence, there is no one-size-fits-all regimen. Moreover, the administration of an unsafe dose during the treatment can have adverse effects on health. Therefore, a treatment model must ensure patient \emph{safety} while \emph{efficiently} optimizing the course of therapy. We study a prevalent medical problem where the treatment aims to keep a physiological variable in a safe range and preferably close to a target level, which we refer to as \emph{leveling}. Such a task may be relevant in numerous other domains as well. We propose ESCADA, a novel and generic multi-armed bandit (MAB) algorithm tailored for the leveling task, to make safe, personalized, and context-aware dose recommendations. We derive high probability upper bounds on its cumulative regret and safety guarantees. Following ESCADA's design, we also describe its Thompson sampling-based counterpart. We discuss why the straightforward adaptations of the classical MAB algorithms such as GP-UCB may not be a good fit for the leveling task. Finally, we make \emph{in silico} experiments on the bolus-insulin dose allocation problem in type-1 diabetes mellitus disease and compare our algorithms against the famous GP-UCB algorithm, the rule-based dose calculators, and a clinician.