An Intelligent and Precise Method Used for Detecting Gestational Diabetes in the Early Stages

Abstract

This paper suggests a Naive Bayes classifier technique for identifying and categorizing gestational diabetes mellitus (GDM), GDM is a kind of diabetes mellitus that affects a small proportion of pregnant women but recovers to normal once the baby is born. The Pima Indians Diabetes Dataset was chosen for a comprehensive analysis of this critical and pervasive health disease because it contains 768 patient characteristics acquired from a machine learning source at the University of California, Irvine. The goal of the study is to apply smart technology to categorize diseases with high accuracy and precision, practically free of conceivable and potential faults, to provide satisfying findings. The approach is based on eight major characteristics that are present in the operations that are required to establish a precise and reliable categorization system. This approach involves training and testing on real data, as well as for deciding whether or not to construct a categorization model. The work was compared to earlier work and had a 96% accuracy rating.

Keywords

• classifier, feature selection, gestational diabetes, machine learning, naïve bayes