Diabetes prediction using feature engineering and machine learning algorithms with security

Abstract

The prevalence of diabetes has been steadily increasing, necessitating accurate prediction models to assist in early diagnosis and proactive management. In this paper, a hybrid machine learning-based diabetes prediction model has been proposed. To evaluate the model, the dataset was subsequently divided into training and testing subsets. We used the Random Forest Classifier, Light Gradient Boosting Mechanism Classifier, Gradient Boosting Classifier, Logistic Regression, K-Nearest Neighbours (KNN) Classifier, Naive Bayes Gaussian, Decision Tree Classifier, XGBoost Classifier, and Support Vector Classifier as nine different classifiers. Several metrics were used to evaluate the models, including testing accuracy, recall score, F1 score, and precision score. We have evaluated our model on the “Pima Indian Diabetes Database”[1], which served as the main dataset, for diabetes prediction. The proposed model serves as a practical framework for researchers and practitioners interested in leveraging machine learning techniques for diabetes prediction.