Early Prediction of Obesity Related Pregnancy Complications Using Machine Learning Algorithms

Abstract

Artificial intelligence is widely used in medical field, machine learning and deep learning has been increasingly used in health care, prediction, and diagnosis many fields. Maternal obesity has emerged as a critical global health concern and is strongly associated with adverse pregnancy outcomes such as gestational diabetes mellitus, preeclampsia, gestational hypertension, preterm birth, and increased cesarean delivery rates. Early prediction of obesity related pregnancy complications remains challenging due to the complex, nonlinear, and heterogeneous interactions among maternal demographic, clinical, metabolic, and lifestyle factors. This paper proposes a machine learning based framework for the early prediction of obesity related pregnancy complications using routinely collected maternal health data. Electronic health records comprising demographic characteristics, pre pregnancy body mass index, obstetric history, vital signs, and biochemical indicators obtained during early gestation are utilized. A comprehensive data preprocessing pipeline is implemented, including missing value imputation, normalization, feature selection, and class imbalance handling to improve data quality and model reliability. Multiple machine learning algorithms are trained and evaluated using standard performance metrics. Experimental results demonstrate that ensemble learning models outperform traditional classifiers in terms of prediction accuracy, sensitivity, and robustness. The proposed framework enables effective early risk stratification of pregnant women, supporting timely preventive interventions and personalized clinical decision making. The findings have to improve maternal and fetal health outcomes and demonstrate their potential integration into intelligent clinical decision support systems for proactive and data driven pregnancy care across diverse populations and real world healthcare environments globally.