Abstract: One of the primary information technologies for antenatal management is the utilization of a machine learning system for healthcare interventions. A machine learning tool is a vital resource for antenatal care and the monitoring of pregnant women, offering services that support healthcare providers, pregnant women, and their family members in predicting and providing adequate healthcare. One of the major challenges faced by pregnant women is the issue of gestational diabetes during pregnancy. It comes with complications such as spontaneous abortion, secondary infections, fetal malformation, hypertensive disorder, cholestasis, obstructed vaginal delivery, and kidney disease. This study aims to develop a machine learning model for predicting gestational diabetes mellitus (GDM) using medical history and socioeconomic features of pregnant women, employing three machine learning models: Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM). The results of the implementation show that XGBoost achieved an F-score of 0.6234 and an accuracy of 83.11%, RF achieved an F-score of 0.6053 and an accuracy of 82.79%, while SVM obtained a performance accuracy of 83.44% with an F-score of 0.5731. The developed machine learning approach will guide healthcare practitioners on the deployment of machine learning models for gestational diabetes mellitus prediction.
Keywords: machine learning, disease prediction, gestational diabetes mellitus, Extreme Gradient Boosting, Artificial Intelligence.
Title: Machine Learning-Based Extreme Gradient Boost Algorithm for the Prediction of Gestational Diabetes Mellitus among Pregnant Women
Author: Ogechukwu Emmanuella Ndukwe, Laeticia Nneka Onyejegbu, Friday E. Onuodu
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Vol. 13, Issue 4, October 2025 - December 2025
Page No: 1-11
Research Publish Journals
Website: www.researchpublish.com
Published Date: 04-October-2025
