Early Prediction of Gestational Diabetes Using Machine Learning Models with Non Invasive Clinical Features

Gestational diabetes mellitus is linked to adverse maternal and neonatal outcomes, which can be improved through early prediction.This current study evaluates the predictive performance of several machine learning algorithms including Logistic Regression, Decision Tree, Random Forest, Light Gradient Boosting Machine, Extreme Gradient Boosting Tree, and Extreme Gradient Boosting by using a publicly available dataset consisting of 1013 records.The dataset included six predictive features: age, pregnancy number, weight, height, body mass index, heredity, and the outcome variable indicate the presence or absence of gestational diabetes.Data pre-processing steps included outlier detection, standardization, and Synthetic Minority Oversampling Technique for class balancing.Model performance was evaluated using accuracy, precision, recall, specificity, and F1 score.LightGBM achieved the highest overall accuracy (89.62%), followed by XGBTree (88.46%) and RF (87.69%).Our findings align with prior research showing the superiority of ensemble models in capturing complex feature interactions.