Diabetes prediction with Exploratory Data Analysis (EDA). Achieved the highest accuracy among literature
Diabetes Mellitus is a dangerous chronic disease that develops when blood sugar levels remain high for an extended period of time. Diabetics are at a higher risk of ailments such as heart and kidney disease, stroke, and vision issues, among others. Diabetes prediction was chosen for this article because it affects a large number of individuals. This prediction was made using a variety of machine learning methods, including decision trees, Naive Bayes, KNN, SVM, and Ensemble. The data was preprocessed with a range of EDA approaches before being used with these algorithms. The approaches described in this project can be utilized for pre-diagnosis, saving time and effort for doctors. The widely used PIMA Indian Dataset was used for this article’s dataset. The patients have eight different qualities in this dataset