Effective Prognosis of Diabetes Using Machine Learning Techniques

Abstract

Diabetes has emerged as a primary disease in most of the nations like China, India and United States. unchecked Diabetes leads to serious health issues which can cause damage to human tissues and organs. The presence of high sugar quantity in the blood stream is the specific cause of diabetes. However, this disease isn’t curable and can solely be controlled. If it is not medicated, it will cause many difficulties. This difficulty might end up in death. Severe difficulties lead to foot sores, cardiovascular disease and eye blurriness. The aim of this project is to build a system which could predict the patient’s diabetic also called sugar risk level with a higher accuracy. Model development is based on categorization algorithm like random forest, logistic regression and k-nearest neighbour algorithms. The performance of each algorithm is analysed and the model with highest accuracy is chosen for prediction of diabetes.