Using Reinforcement Learning to Simplify Mealtime Insulin Dosing for People with Type 1 Diabetes: In-Silico Experiments

TL;DR

This study develops a reinforcement learning agent that recommends insulin doses for people with type 1 diabetes, simplifying the process without precise carbohydrate counting and improving glycemic control in virtual simulations.

Contribution

The paper introduces a novel RL-based insulin dosing method using LSTM networks trained on virtual patient data, outperforming traditional carbohydrate counting approaches.

Findings

RL approach increased time-in-range to 73.1%

RL reduced hypoglycemia episodes to 2.0%

Outperformed baseline methods in virtual experiments

Abstract

People with type 1 diabetes (T1D) struggle to calculate the optimal insulin dose at mealtime, especially when under multiple daily injections (MDI) therapy. Effectively, they will not always perform rigorous and precise calculations, but occasionally, they might rely on intuition and previous experience. Reinforcement learning (RL) has shown outstanding results in outperforming humans on tasks requiring intuition and learning from experience. In this work, we propose an RL agent that recommends the optimal meal-accompanying insulin dose corresponding to a qualitative meal (QM) strategy that does not require precise carbohydrate counting (CC) (e.g., a usual meal at noon.). The agent is trained using the soft actor-critic approach and comprises long short-term memory (LSTM) neurons. For training, eighty virtual subjects (VS) of the FDA-accepted UVA/Padova T1D adult population were simulated using MDI therapy and QM strategy. For validation, the remaining twenty VS were examined in 26-week scenarios, including intra- and inter-day variabilities in glucose. \textit{In-silico} results showed that the proposed RL approach outperforms a baseline run-to-run approach and can replace the standard CC approach. Specifically, after 26 weeks, the time-in-range ($70-180$mg/dL) and time-in-hypoglycemia ($<70$mg/dL) were $73.1\pm11.6$% and $ 2.0\pm 1.8$% using the RL-optimized QM strategy compared to $70.6\pm14.8$% and $ 1.5\pm 1.5$% using CC. Such an approach can simplify diabetes treatment, resulting in improved quality of life and glycemic outcomes.