Computer-Aided System with Machine Learning components for generating medical recommendations for type 1 diabetes patients

The paper presents an original method for processing medical data derived from a type 1 diabetes patient, aimed at generating therapeutic recommendations to improve the quality of the patient’s treatment. This problem is characterized by high complexity, the need to tailor the method to the available data, and the inability to conduct experiments other than computer simulations. The proposed approach introduces novel solutions, including the development of a computer model of a person with diabetes, the adaptation of a genetic algorithm to the specific problem, and the use of a time series similarity criterion for blood glucose concentration. The method was designed for patients using an insulin pump and a continuous glucose monitoring system. In the research section, data from five real patients were analyzed using the developed method, and the results indicated that it may be effective in supporting real-world therapy.