Extreme Gradient Boosting and Soft Voting Ensemble Classifier for Diabetes Prediction

Diabetes is a chronic disease that has been impacting an increasing number of people throughout the years. Each year, it results in a huge number of deaths. Due to the fact that late diagnosis results in severe health complications and a significant number of deaths each year, it is critical to develop methods for early detection of this pathology. As a result, early detection is critical. Machine learning techniques aid in the early detection and prediction of diabetes. However, machine learning models do not perform well with missing values in the dataset. Imputation of missing values improves the outcome. In this work, we have used extreme gradient boosting (XGB) and another six traditional classifiers to train the model with a strong emphasis on missing value imputation. Results of various classifiers are combined using the soft voting ensemble (SVE) approach by assigning equal weights to the classifier. The experimentation uses the Pima Indian Diabetes Dataset, which contains information about people with and without diabetes. Missing value imputation for data pre-processing and ensemble classification has been shown to beat traditional classifiers.