Intelligent Control with Artificial Neural Networks for Automated Insulin Delivery Systems

Abstract

Type 1 diabetes mellitus is a disease that affects millions of people around the world. Recent progress in embedded devices has allowed the development of artificial pancreas that can pump insulin subcutaneously to automatically regulate blood glucose levels in diabetic patients. In this work, a Lyapunov-based intelligent controller using artificial neural networks is proposed for application in automated insulin delivery systems. The adoption of an adaptive radial basis function network within the control scheme allows regulation of blood glucose levels without the need for a dynamic model of the system. The proposed model-free approach does not require the patient to inform when they are going to have a meal and is able to deal with inter- and intrapatient variability. To ensure safe operating conditions, the stability of the control law is rigorously addressed through a Lyapunov-like analysis. In silico analysis using virtual patients are provided to demonstrate the effectiveness of the proposed control scheme, showing its ability to maintain normoglycemia in patients with type 1 diabetes mellitus. Three different scenarios were considered: one long- and two short-term simulation studies. In the short-term analyses, 20 virtual patients were simulated for a period of 7 days, with and without prior basal therapy, while in the long-term simulation, 1 virtual patient was assessed over 63 days. The results show that the proposed approach was able to guarantee a time in the range above 95% for the target glycemia in all scenarios studied, which is in fact well above the desirable 70%. Even in the long-term analysis, the intelligent control scheme was able to keep blood glucose metrics within clinical care standards: mean blood glucose of 119.59 mg/dL with standard deviation of 32.02 mg/dL and coefficient of variation of 26.78%, all below the respective reference values.

Type 1 and type 2 diabetes mortality burden: Predictions for 2030 based on Bayesian age‐period‐cohort analysis of China and global mortality burden from 1990 to 2019

“…It was previously believed that type 1 diabetes generally occurs in childhood or adolescence 53 , but current research has found that type 1 diabetes can occur and develop throughout the entire life cycle, even in individuals over 80 years old 54 , 55 . The discovery of insulin in 1922 transformed type 1 diabetes into a treatable disease 56 , and with the intensive research of individualized treatment, clinical treatment has made great progress, including the design of insulin analogs 57 , smart insulin pumps 58 , continuous glucose sensors, and closed‐loop insulin delivery systems 59 . These advancements greatly improved blood sugar control in type 1 diabetes, reducing the frequency of diabetes‐related complications and greatly improving the long‐term outcomes of people with type 1 diabetes 60 , 61 .…”

Precision Insulin Delivery: Predictive Modelling for Bolus Insulin Injection in Real-Time

“…2) Sample size: In this work, sample size is chosen based on the patients whose blood glucose levels were improved. Many studies have chosen sample sizes of 13,20,25,56 [6,10,[16][17][18] to predict insulin dosage. Therefore, glucose values at the time of bolus infusion, meal time, and amount of insulin dosage given are focused on a total sample size of 60 patients.…”

Enhancement of the Blood Glucose Level for Diabetic Patients Based on an Adaptive Auto-Tuned PID Controller via Meta-Heuristic Methods

“…In addition, the authors in [10,11] exploited the type-2 fuzzy controller for tracking and stabilizing the blood glucose level in T1D patients. On the other hand, a radial basis function neural network was utilized in [12] as an intelligent controller for an automated insulin delivery system for a virtual patient model to monitor and control the blood glucose level within days. In another work, the authors in [13] illustrated the estimation of the T1D patient model based on a UVA/Padova metabolic simulator and designed control algorithms using an intelligent predictive control model with linear and nonlinear controllers to regulate the blood glucose level for the linear thirdorder patient model.…”