Classification of the Cardiotocogram Data for Anticipation of Fetal Risks using Bagging Ensemble Classifier

Abstract

Abstract Cardiotocography (CTG) is utilized for monitoring fetal status during antepartum and intrapartum periods to predict the condition of the fetal wellbeing, broadly in pregnant women having potential difficulties to designate the risk of a fetal acidosis. These predictions are assessed in a real-time clinical decision support system and gives valuable information which can be utilized for additional information about the fetal state. The improvements in modern obstetric practice permitted numerous reliable and robust machine learning approaches to be employed in classifying fetal heart rate signals. The role of machine learning algorithms in identifying illnesses is becoming crucial. The purpose of this study is to evaluate the classification performances of ensemble machine learning algorithms on the antepartum CTG data. Hence, this paper is focused on the Bagging ensemble machine learning algorithm to classify fetal heart rate signals as normal or abnormal. The accuracy, F-measure and ROC area is utilized as performance metrics to assess the success of the classifiers. Experimental results have revealed that the Bagging ensemble classifier produced satisfactory results, and Bagging with Random Forest achieved better results with an accuracy of 99.02%.