Classification and prediction of hypoglycemia in diabetic patients using machine learning techniques

Abstract

Type 1 diabetics can lower their risk of microvascular and macrovascular problems by carefully regulating their blood glucose levels. The downside is that these measures are incredibly challenging because of the wide diversity across individuals, as well as other factors that affect glycemic management. Keeping glucose levels under control is difficult due to the possibility of severe hypoglycemia in patients receiving intensive insulin therapy. In people with diabetes, hypoglycemia is a common complication, which has a negative impact on overall health and well-being. Improving patient safety by anticipating unfavourable glycemic events has become a practical approach to enhanced patient safety using machine learning decision assistance. This paper suggests the use of three machine learning techniques to solve the problem of diabetic safety: (1) Random Forest for continuous glucose predictions, (2) support vector machines for postprandial period predictions, and (3)artificial neural networks for overnight hypoglycemic predictions. It has the two different categorization and prediction capabilities already established. A major system feature is the overall reduction in bouts of hypoglycemia, which results in an increase in patient safety and provides better confidence in treatment decisions.