Basal-Bolus Advisor for Type 1 Diabetes (T1D) Patients Using Multi-Agent Reinforcement Learning (RL) Methodology

TL;DR

This paper introduces a multi-agent reinforcement learning system that acts as a personalized basal-bolus advisor for type 1 diabetes patients, significantly improving glucose regulation and reducing insulin dosages.

Contribution

The study presents a novel multi-agent RL methodology for personalized glucose control in T1D, outperforming conventional therapy in multiple clinical metrics.

Findings

Improved glucose control with increased time in target range

Reduced glycemic variability and hypoglycemia events

Significant reduction in daily basal insulin dosage

Abstract

This paper presents a novel multi-agent reinforcement learning (RL) approach for personalized glucose control in individuals with type 1 diabetes (T1D). The method employs a closed-loop system consisting of a blood glucose (BG) metabolic model and a multi-agent soft actor-critic RL model acting as the basal-bolus advisor. Performance evaluation is conducted in three scenarios, comparing the RL agents to conventional therapy. Evaluation metrics include glucose levels (minimum, maximum, and mean), time spent in different BG ranges, and average daily bolus and basal insulin dosages. Results demonstrate that the RL-based basal-bolus advisor significantly improves glucose control, reducing glycemic variability and increasing time spent within the target range (70-180 mg/dL). Hypoglycemia events are effectively prevented, and severe hyperglycemia events are reduced. The RL approach also leads to a statistically significant reduction in average daily basal insulin dosage compared to conventional therapy. These findings highlight the effectiveness of the multi-agent RL approach in achieving better glucose control and mitigating the risk of severe hyperglycemia in individuals with T1D.