Machine Learning-Based Early Type 2 Diabetes Prediction

The escalating rise in diabetes cases has made the disease classified as a catastrophic chronic illness. Diabetes is a condition whereby the human body has excess blood glucose due to either insufficient insulin production or inefficient usage. Diabetes does not have visible symptoms at the onset of the disease and is usually detected late when the ailment is at an advanced stage. Since diabetes does not have a permanent cure, researchers have leveraged Machine Learning (ML) methods to diagnose prediabetes. Prediabetes is a preliminary stage before a patient has diabetes. Prediabetics can change their lifestyle to prevent the illness from advancing to the diabetic phase if they know they are prediabetics. This paper proposed an ensemble ML model to evaluate Pima Indians and Comprehensive (100k rows) datasets. The proposed Meta-Model (MM) achieved an accuracy and CV score of 97.13% for the comprehensive dataset.