Authors:
R. Sivakani, Sureshkumar Somayajula, Sayyed Khawar Abbas, C. Sathish Kumar, A. Thenmozhi, J. Anciline Jenifer
Addresses:
Department of Artificial Intelligence and Data Science, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Computer Science and Technology, Sunlife Canada Financials, Toronto, Ontario, Canada. Department of Information Systems, Corvinus University of Budapest, Budapest, Hungary. Department of Computer Science, Faculty of Science and Humanities, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Master of Computer Application, Francis Xavier Engineering College, Tirunelveli, Tamil Nadu, India.
Abstract:
Diabetes is a grave global health emergency, and the incidence has been growing in recent years. Among others, gestational diabetes is particularly dangerous as it is a type of disease not only afflicted by a mother, but a child in the womb as well. The proposed research will propose an excellent machine learning model that is specifically designed to diagnose gestational diabetes at its initial stages to avoid such complications as kidney failure or heart disease in future. In the research, a hybrid method is employed that combines several algorithms to improve prediction precision. In this study, two different datasets were obtained from the Kaggle repository, with emphasis on various physiological parameters. It was implemented using advanced computational tools, such as Python libraries and integrated development environments, to analyse large-scale data. The model was strictly tested using ten-fold cross-validation on a subset of 216 instances. The findings indicate a high level of diagnostic capability, with 90% accuracy. This paper highlights the significance of automated screening in maternal healthcare, offering a faster, more efficient alternative to conventional diagnostic methods and the most effective approach for testing in a clinical setting.
Keywords: Gestational Diabetes; Machine Learning; Hybrid Approach; Early Prediction; Healthcare Analytics; Medical Diagnosis; Computational Efficiency; Multi-Line Performance.
Received on: 05/03/2025, Revised on: 28/06/2025, Accepted on: 05/10/2025, Published on: 07/06/2026
DOI: 10.64091/ATIHL.2026.000301
AVE Trends in Intelligent Health Letters, 2026 Vol. 3 No. 2 , Pages: 68-77