Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning

TL;DR

This paper introduces a hybrid control policy combining model predictive control and ensemble deep reinforcement learning, enhanced with meta-learning, to improve personalized glucose regulation in artificial pancreas systems for type 1 diabetes.

Contribution

It proposes a novel hybrid control framework that integrates MPC and ensemble DRL with meta-learning for rapid adaptation, advancing personalized and safe glucose control in T1DM.

Findings

Achieved the highest time in euglycemic range in simulations

Reduced hypoglycemia incidents compared to existing methods

Demonstrated effective adaptation to new patients with limited data

Abstract

Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM). However, designing an effective control policy for the AP remains challenging due to the complex physiological processes, delayed insulin response, and inaccurate glucose measurements. While model predictive control (MPC) offers safety and stability through the dynamic model and safety constraints, it lacks individualization and is adversely affected by unannounced meals. Conversely, deep reinforcement learning (DRL) provides personalized and adaptive strategies but faces challenges with distribution shifts and substantial data requirements. Methods: We propose a hybrid control policy for the artificial pancreas (HyCPAP) to address the above challenges. HyCPAP combines an MPC policy with an ensemble DRL policy, leveraging the strengths of both policies while compensating for their respective limitations. To facilitate faster deployment of AP systems in real-world settings, we further incorporate meta-learning techniques into HyCPAP, leveraging previous experience and patient-shared knowledge to enable fast adaptation to new patients with limited available data. Results: We conduct extensive experiments using the FDA-accepted UVA/Padova T1DM simulator across three scenarios. Our approaches achieve the highest percentage of time spent in the desired euglycemic range and the lowest occurrences of hypoglycemia. Conclusion: The results clearly demonstrate the superiority of our methods for closed-loop glucose management in individuals with T1DM. Significance: The study presents novel control policies for AP systems, affirming the great potential of proposed methods for efficient closed-loop glucose control.