Prediction of Diabetes using Machine Learning

Abstract

Abstract: Diabetes is a chronic condition that could lead to a catastrophe in the world's healthcare system. 537 million people worldwide have diabetes, according to the International Diabetes Federation. By 2045, this number is anticipated to reach 783 million. A rise in blood glucose levels can result in diabetes. Numerous symptoms, which includes frequent urination, increased thirst, and increased appetite, are brought on by this raised blood glucose level. It is a significant contributor to heart failure, stroke, kidney failure, blindness, and amputations. The objective of the given study mainly is to develop the single collective system that combines result of many different types machine learning techniques, including Logistic Regression, Linear Regression, Support Vector Machine, and Random Forest, to more accurately predict diabetes in a patient. It collects the patient's records based on their pregnancy, blood sugar levels, blood pressure, insulin levels, body mass index, and many other factors. Each of the strategies will be used to determine the model's correctness, however, we found that the Support vector machine method had the highest accuracy (77%). The diabetes forecast is then made using the model with the highest accuracy.