Diabetes Feature Extraction Through Machine Learning Approach

Abstract

There are a number of individuals who suffer from diabetes mellitus, definitely among the most popular severe diseases. Diabetic mellitus can be caused by a variety of factors, including age, obesity, inactivity, genetics, dietary habits, blood pressure, and others. An individual's risk of developing diabetes increases chance from growing several illnesses, affect the heart, renal disease, kidneys, nerves harm, eyesight damage and so on. The various tests that are widely utilized in hospitals to diagnose diabetes are used to determine appropriate treatment, according to that diagnosis. So, in this paper, we will discover what the essential components of diabetes causes are in this essay. In areas of application where datasets containing tens or thousands of elements are available, variable and feature choice have become the focus of significant study. Our determination of whether someone is likely to develop diabetes in the future will also focus on the most crucial characteristics. We used two ML algorithms on the dataset to predict diabetes. One is KNN where the other one is K-means algorithm. We found that the model KNN works well on diabetes prediction with the accuracy of 81%.