Simulation model of a patient with type 1 diabetes using fuzzification

Abstract

Type 1 diabetes is one of the most common diseases. The disease is caused by a lack of insulin secretion from the beta cells of the pancreas, which leads to improper regulation of blood glucose levels. The article presents a simulation model for determining changes in glucose-insulin levels using fuzzy logic techniques. The work concerns a quite simple deterministic simulation model of a digital twin of a type 1 diabetes patient, and fuzzification can significantly improve the efficiency of this model. A series of numerical experiments showed that enriching a simple deterministic patient model with a fuzzy approach gives much more accurate results than the simple deterministic model. The use of fuzzy sets opens up a number of possibilities and is a completely natural approach, resulting from, among others, the specificity of the simulated phenomenon - vital parameters of people with type 1 diabetes.