Gestational Diabetes Prediction using Machine Learning for Consumer Electronics Healthcare

Gestational Diabetes Mellitus (GDM) is a significant health issue t hat affects m any non-diabetic women during pregnancy, with its prevalence steadily increasing. Early and accurate detection of GDM is crucial due to the severe complications it poses for both mothers and their children, including perinatal complications, future diabetes risk, metabolic syndrome, cardiovascular issues, pre-eclampsia, and polyhydram-nios. This paper explores the use of machine learning (ML) algorithms for consumer electronics healthcare system to predict GDM, evaluating six models: Random Forest, K-Nearest Neighbour, Support Vector Machine, Logistic Regression, Decision Tree, and X G Boost. The dataset includes parameters such as pregnancies, glucose levels, blood pressure, skin thickness, insulin levels, BMI, diabetes pedigree function, age, and outcome, aimed at optimizing prediction accuracy. Through detailed exper-imentation, these models are assessed based on accuracy, mean squared error, R-squared, and root mean square error, presenting the results visually for improved under-standing. By integrating ML into consumer electronics healthcare devices, this approach aims to enhance GDM prediction and management, offering more informed clinical decisions and accessible health monitoring tools, ultimately improving healthcare outcomes for pregnant women and their children.