An Efficient Method of Classification the Gestational Diabetes Using ID3 Classifier

Abstract

Artificial intelligence algorithms have an important and effective role in the medical field, especially in the field of diagnosing diseases. This research focuses on predicting the diagnosis of gestational diabetes by using the Iterative Dichotomiser3 (ID3) classifier algorithm, which is utilized to identify gestational diabetes; it was one of the most significant algorithms employed in this study. Training and testing are two critical phases of the research study. This study employed the Pima Indians Diabetes dataset, which comprised 768 women aged 21 and above with the eight reported traits. A feature selection stage, a discretization step, and using the classifier model for producing decision rules are all part of the Pima Indians diabetes data gathering process (Diabetes Dataset). In this study, the decision tree is employed to develop the classifier model, which is based on Diabetes training. The Iterative Dichotomiser3 (ID3) technique may be used to run the decision tree classification process. Diabetes is tested using decision rules, and the classifier implementation confusion matrix was retrieved from the testing portion. The system delivered high-quality results with a 94 percent accuracy rate.