Diabetes Prediction Using Machine Learning

Abstract

Chronic diseases like diabetes have the potential to wreck the world's health care system. According to the International Diabetes Federation, there are 382 million diabetics worldwide. By 2035, this will increase to 592 million. Diabetes is a disease characterised by high blood glucose levels. The signs of this raised blood sugar level include increased thirst, appetite, and frequency of urinating. Diabetes is a significant contributing factor to heart failure, stroke, kidney failure, amputations, blindness, and kidney failure. When we eat, our bodies turn the food we consume into sugars like glucose. Then, we anticipate insulin to be released from our pancreas. Insulin functions as a key to unlock our cells, allowing glucose to enter and be used as fuel by us. However, in diabetes, this mechanism does not work. The most common types of diabetes are type 1 and type 2, but there are others, including gestational diabetes, which develops during pregnancy. Machine learning is a new area in data science that investigates how machines learn from experience. The purpose of this work is to develop a system that, by combining the findings of different machine learning algorithms, can more correctly identify early diabetes in a patient. Some of the approaches used include Logistic Regression, Random Forest, Support Vector Machine, and the Nave Bayes Algorithm. The accuracy of each algorithm is computed alongside.