Closed Loop Control of Blood Glucose Levels in Diabetes Using an Artificial Neural Network Controller

Abstract

Regulating blood glucose levels (BGL) is of paramount significance for those with Type 1 Diabetes (T1D), as it can lead to severe health issues, including cardiovascular complications. Our research is centred around the development of an automated closed-loop system, rooted in the minimal Bergman model and driven by a carefully trained artificial neural network (ANN) controller. This approach, evaluated on three T1D patients, effectively keeps blood glucose within the desirable range of 70 to 140 mg/dl, holding the promise of enhancing the overall health and well-being of individuals living with T1D. The potential impact of this research extends to an improved quality of life and a reduction in healthcare burdens.