Attention Networks for Personalized Mealtime Insulin Dosing in People with Type 1 Diabetes

TL;DR

This paper introduces a reinforcement learning approach with self-attention networks to personalize mealtime insulin dosing for Type 1 Diabetes, significantly reducing glycemic risk and potentially improving treatment simplicity and outcomes.

Contribution

It presents a novel reinforcement learning model with self-attention that outperforms existing architectures in insulin dosing prediction for T1D patients.

Findings

Significant reduction in glycemic risk scores.

Superior performance of self-attention networks over other architectures.

Effective generalization to unseen virtual subjects.

Abstract

Calculating mealtime insulin doses poses a significant challenge for individuals with Type 1 Diabetes (T1D). Doses should perfectly compensate for expected post-meal glucose excursions, requiring a profound understanding of the individual's insulin sensitivity and the meal macronutrients'. Usually, people rely on intuition and experience to develop this understanding. In this work, we demonstrate how a reinforcement learning agent, employing a self-attention encoder network, can effectively mimic and enhance this intuitive process. Trained on 80 virtual subjects from the FDA-approved UVA/Padova T1D adult cohort and tested on twenty, self-attention demonstrates superior performance compared to other network architectures. Results reveal a significant reduction in glycemic risk, from 16.5 to 9.6 in scenarios using sensor-augmented pump and from 9.1 to 6.7 in scenarios using automated insulin delivery. This new paradigm bypasses conventional therapy parameters, offering the potential to simplify treatment and promising improved quality of life and glycemic outcomes for people with T1D.