An Analysis of Predicting Diabetes using Machine Learning

Diabetes comes under chronic disease, in which cells are not able to use blood sugar (glucose) efficient enough for energy. This condition arrives when the cells become non-responsive to insulin and the blood sugar increases gradually. The known types of diabetes are, Type1, Type 2 and Type 3. Type 1 and type 2 diabetes are in hyperglycemia category (caused by increase in blood sugar), while Type 3 diabetes (Alzheimer's disease) which is caused by resistance to insulin in the brain. Prediction of preliminary stage diabetes is very important as it becomes worse in next stages. This Prediction can be done using machine learning classification models, which are more widely being used for other medical purposes. To predict, if a person is diabetic we need data about insulin, blood pressure, skin thickness and glucose. This data will be fitted in classification models of machine learning with a target vector of conclusion. This will prepare a model that can predict if a certain patient is a diabetic or not. We have implemented many classification models on the data. We have also used neural networks to serve the same purpose.