Early Detection of Type-2 Diabetes Mellitus using Machine Learning based Prediction Models

Diabetes, a condition that lasts for a long time, or we say, is a lifetime problem where the body cannot produce enough or no insulin, does not use the body’s insulin effectively, or can exhibit both. As a result of which body cells cannot take the blood sugar, eventually, the body’s sugar level is elevated. Diabetes today is an almost door-to-door problem, causes slow but significant changes in the body. So, we must address it more vigorously. As we know it, ML, a part of AI, is widely being used in predicting many diseases like cancers, tumors, etc. Here we are involved in detecting the chances of type-2 Diabetes in people using ML at an early stage and comparative analysis of the model’s results in detecting type-2 Diabetes. The models used are KNN, LR, SVM, RF, and DT. The dataset used is the local dataset from SKIMS Soura, Kashmir.