A comparative study of classifiers for early diagnosis of gestational Diabetes Mellitus

Authors : Priya Shirley MULLER, M NİRMALA

Pages : 754-770

Doi:10.31801/cfsuasmas.704394

View : 31 | Download : 10

Publication Date : 2020-06-30

Article Type : Research Paper

Abstract :Gestational Diabetes Mellitus insert ignore into journalissuearticles values(GDM);, usually found deploying a medical test called the Oral Glucose Tolerance Test insert ignore into journalissuearticles values(OGTT);, is a prevalent complication during pregnancy. Early detection of GDM and identifying the most influential risk factors of GDM pose to be a challenging problem and is found to be crucial as GDM has dreadful health indications for both mother and the baby. The performances of computational techniques like Radial Basis Function insert ignore into journalissuearticles values(RBF); neural network and Multilayer Perceptron Network insert ignore into journalissuearticles values(MLP); were collated with that of the statistical technique Discriminant Analysis insert ignore into journalissuearticles values(DA); on real time GDM datasets for diagnosis of GDM in multigravida pregnant women, specifically women who have been pregnant more than once, without even a visit to the hospital. The most influential risk factors were identified using DA while the overall performance of MLP beyond doubt established itself to be the most effective technique for early diagnosis of GDM in women during pregnancy.
Keywords : Gestational diabetes mellitus, classifier, risk factors, multilayer perceptron network, back propagation algorithm, radial basis function algorithm, discriminant analysis

ORIGINAL ARTICLE URL