Prediction of the Development of Gestational Diabetes Mellitus in Pregnant Women Using Machine Learning Methods

The paper is devoted to the application of machine learning methods prediction development gestational diabetes mellitus in early pregnancy. Based on two publicly available databases, study assesses influence such features as body mass index, thickness triceps skin folds, ultrasound measurements maternal visceral fat, first measured fasting glucose, and others a predictors mellitus. supervised based decision trees, support vector machines, logistic regression, k-nearest neighbors classifier, ensemble learning, Naive Bayes neural networks were implemented determine best classification models for computerized disease prediction. accuracy different classifiers was determined compared. Support classifier demonstrated highest (83.0% total correctly prognosed cases, 87.9% healthy class, 78.1% mellitus) predicting from Pima Indians Diabetes Database. Extreme gradient boosting performed best, comparing other methods, Visceral Adipose Tissue Measurements during Pregnancy It showed 82.2% 93.6% mellitus).