Different Machine Learning Algorithms Involved in Glucose Monitoring to Prevent Diabetes Complications and Enhanced Diabetes Mellitus Management

Diabetes mellitus (DM) is a group of metabolic disorders resulting from dysregulation of blood glucose (BG). Hence, it may lead to various vascular and neural complications involving multiple organ systems, either short- or long-term. During the past two decades, various computer-assisted systems based on machine learning algorithms haves based on machine learning algorithms have become available and have achieved satisfactory performance in glucose monitoring and predicting the prognosis of diabetic patients. The increased availability of multidimensional health data has shed light on machine learning for a novel BG prediction and diabetes management method. So far, various machine learning algorithms have been productive in predicting BG and diabetes progression and prognosis. Hence, machine learning algorithms have been regarded as accurate, with less operation cost and higher efficacy in predicting potential diabetes in the undiagnosed population, profiling personalized BG dynamics, establishing personalized decision support systems, and building BG alarm events in DM patients. However, real-world data concerning the efficacy of various machine learning algorithms in diabetes prediction and management is still limited, and internationally acceptable guidelines have not been established to estimate and quantify the potential lifestyle-relevant variables related to the BG level. This chapter has been written to address the current progress in the application of machine learning in glucose monitoring and DM management. Different machine learning algorithms have also been discussed on the validity and feasibility of the algorithms fit for purpose.