Machine Learning Techniques for Diabetes Prognosis

Abstract

Diabetes is a long-term illness that has the potential to devastate the global health-care system. Diabetes will affect 522 million people worldwide by 2033. Diabetes develops in eagerness, hunger, and the process of excreting due to high blood sugar levels.. Among other problems, diabetes is a primary cause of blindness, renal failure, amputations, heart failure, and stroke. Our bodies convert food into sugars, or glucose, when we consume it. At that point, our pancreas is supposed to release insulin. Insulin is the key molecule that allows glucose to enter and be used for energy in our cells. This system, however, does not operate in the case Diabetes Type 1 and Type 2 diabetes are the most common, but there are many others, including gestational diabetes, which develops during pregnancy, and the other forms of Diabetes. Machine learning is a new discipline of data science that studies how machines learn from their past experiences. The goal of the research is to develop a module that can accurately identify diabetes in a patient early, by combining the outcomes of various machine learning approaches. Among the approaches used are K-Nearest Neighbor, Logistic Regression, Random Forest, and Support Vector Machine. The model’s accuracy when utilizing each of the algorithms is pre-determined. The model accompanying the capital accuracy for forecasting diabetes is therefore preferred.