Evaluation of Risk Factors of Gestational Diabetes Mellitus (GDM) Using Data Mining
Prema N S1, Pushpalatha M P2

1Prema N S, Department of Information Science and Engineering , Vidyavardhaka College of Engineering, Mysuru, India.
2Pushpalatha M P, Department of Computer Science and Engineering ,Sri Jayachamarajendra College of Engineering, Mysuru, India.
Manuscript received on July 20, 2019. | Revised Manuscript received on August 10, 2019. | Manuscript published on August 30, 2019. | PP: 695-698 | Volume-8 Issue-6, August 2019. | Retrieval Number: F7967088619/2019©BEIESP | DOI: 10.35940/ijeat.F7967.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Diabetes is one of the major chronic diseases in all population which is a major health challenge. The diabetes developed during pregnancy is called Gestational diabetes mellitus (GDM). The identification of GDM at early stages of the pregnancy is very important otherwise it will lead to major health issues both in mother and the baby. We developed a Data mining (DM) model to analyze the risk factors of GDM using different DM techniques. Dataset used for analysis contains the details of the pregnant women collected from the local hospital of Mysuru, India. The clustering and classification techniques used are k-means clustering, J48 Decision Tree, Random-Forest and Naive-Bayes classifier. Classification accuracy is enhanced by using feature subset selection wrapper approach. A balanced dataset is developed by using Synthetic Minority Over-sampling Technique (SMOTE).Using accuracy the performances of classifiers are compared.
Keywords: Data mining, Gestational Diabetes Mellitus, SMOTE, K-means.