Time prediction of Diabetes Mellitus using Machine Learning

Diabetes mellitus, commonly known as Diabetes, is a chronic disease that is characterized by high blood sugar. Failure of the pancreas to produce enough insulin and body’s inefficient use of insulin are both pathologic causes of Diabetes . With rapid development of Machine Learning, ML has been applied to many aspects of medical health and has proven helpful in predicting health conditions more accurately and quickly.

The proposed system is a web application which is specifically designed to be used by doctors. K- Nearest Neighbor is a machine learning algorithm used for identification and time prediction of Diabetes mellitus in this project. The result is either Yes or No for diabetes prediction and if Yes, the time of getting diabetes is predicted as after 6 months or 1 year or 2 year or 3 year. It makes use of old patients data that includes BMI, age, insulin level, BP and so on to predict possibility of occurrence of diabetes in a new patient.

Technologies: