Automated Insulin Delivery for Type 1 Diabetes Mellitus Patients using Gaussian Process-based Model Predictive Control

TL;DR

This paper develops an advanced Gaussian Process-based Model Predictive Control system for automated insulin delivery in Type 1 Diabetes, accounting for circadian insulin sensitivity variations and measurement noise, aiming for clinical use.

Contribution

It introduces a new kernel function and noise handling in Gaussian Process modeling for insulin delivery, improving robustness and clinical applicability.

Findings

Effective control with variable meal schedules demonstrated in simulations

Enhanced Gaussian Process model handles noisy data reliably

Closer to clinical implementation through improved control accuracy

Abstract

The human insulin-glucose metabolism is a time-varying process, which is partly caused by the changing insulin sensitivity of the body. This insulin sensitivity follows a circadian rhythm and its effects should be anticipated by any automated insulin delivery system. This paper presents an extension of our previous work on automated insulin delivery by developing a controller suitable for humans with Type 1 Diabetes Mellitus. Furthermore, we enhance the controller with a new kernel function for the Gaussian Process and deal with noisy measurements, as well as, the noisy training data for the Gaussian Process, arising therefrom. This enables us to move the proposed control algorithm, a combination of Model Predictive Controller and a Gaussian Process, closer towards clinical application. Simulation results on the University of Virginia/Padova FDA-accepted metabolic simulator are presented for a meal schedule with random carbohydrate sizes and random times of carbohydrate uptake to show the performance of the proposed control scheme.