Smart Diabetes Assistent

Diabetes is a disease that occurs when glucose, which is blood sugar, levels are too high. According to the Centers for Disease Control (CDC), as of 2022 diabetes affects 11.3% of the US population. This disease is caused when not enough insulin is produced by the body (Type 1) or when insulin is not being used effectively (Type 2). This is critical because insulin is a hormone that regulates glucose, therefore improper insulin levels affect glucose levels- varying levels of glucose are referred to as a hypoglycemic event (low blood sugar) or a hyperglycemic event (high blood sugar) and can lead to further health issues if not treated properly. This project focuses on developing a personalized, data-driven diabetes application. The general aim of the algorithms is to predict blood glucose levels and give insights in the relation between blood glucose variation and physical activity (PA) incorporating (the variability of) the effect of PA on the blood glucose level. A focus will be on the personalization of those algorithms. In a second phase, the algorithms can be integrated in tools and applications to increase time-within-range and decrease hypo- and hyperglycemic events in outpatient clinical settings for moments before, during and after physical activity. Personalized algorithms will give insight into the correlation between physical activity and glucose levels and may provide more accurate blood glucose levels for patients with diabetes, leading to a reduction in hypo or hyperglycemic events for patients.