Early Diabetes Prediction Based on Stacking Ensemble Learning Model

As one of the chronic diseases threatening human health, early detection and early treatment of diabetes plays an important role in the control and development the disease. With the increasing development of artificial intelligence technology, machine learning models are widely used in disease prediction. The generalization ability of a single machine learning model is not strong, and it often has limitations in diagnostic applications. Accordingly, this paper proposes an early diabetes prediction model based on stacking ensemble earning. In this model, Gradient Boosting Decision Tree, Adaboost and Random Forest were used as primary learners and logistic regression was used as secondary learners. As the results show that the ensemble model proposed in this paper can predict early diabetes more effectively than a single model. Although the proposed model is more accurate in predicting early onset diabetes, the timeliness of the model needs to be improved