Diabetes Prediction Using Binary Grey Wolf Optimization and Decision Tree

Abstract

Type 2 diabetes is a well-known lifelong condition disease that reduces the human body’s ability to produce insulin. This causes high blood sugar levels, which leads to different complications, including stroke, eye, cardiovascular, kidney, and nerve damage. Although diabetes has attained the attention of huge research, the classification performance of such medical problems utilizing techniques of machine learning is quite low, primarily due to the class imbalance and the presence of missing values in data. In this work, we proposed a model using binary Grey wolf optimization (GWO) and a Decision tree. The proposed model is composed of preprocessing, feature selection, and classification. In preprocessing, that is responsible for minority class oversampling and handling missing values. In the second step, binary GWO are used to select the most significant features. In the third step, the proposed model is trained using the Decision tree algorithm. The model achieved an accuracy of 83.11% when it was applied on the Pima Indian's dataset.