An Ensemble Model for the Prediction of Gestational Diabetes Mellitus (GDM) Prema N S1,*, Pushpalatha M P2 1Associate Professor, Department of Information Science and Engineering, Vidyavardhaka College of Engineering, Mysuru-02, India 2Professor, Department of Computer Science and Engineering, Sri Jayachamarajendra College of Engineering, Mysuru-06, India *Corresponding author: Prema N S, Email: prema.gowda@gmail.com
Online published on 13 November, 2019. Abstract Diabetes is the common chronic disease and a major health challenge in all population. Gestational Diabetes Mellitus (GDM) is a type of diabetes developed in women at the time of pregnancy. Our study is about predicting GDM by considering various risk factors using ensemble classification techniques. In this paper different ensemble learning models are used for prediction of GDM. A new ensemble model is proposed where ensemble stacking is done for the results of k-means clustering. Where clustering is done by excluding the class attribute of the data set. The data samples used for testing the model is collected from the local hospitals of Mysuru, Karnataka state, India. The performance of the classifiers have been measured and compared in terms of accuracy. Top Keywords Gestational Diabetes Mellitus, SMOTE, Ensemble, Stacking, k-means. KNN, Random Forest, Logistic Regression. Top |