Cardiotocography Analysis for Fetal State Classification Using Machine Learning Algorithms

Fetus problems are the major reasons in gynecology for pregnant women's. If the conditions for the fetus inside womb are not appropriate, then there are major chances of health deterioration of the fetus. Cardiotocography (CTG) technique is used to record the fetal heart rate (FHR) and uterine contractions (UC) simultaneously. This paper uses commonly used algorithms for machine learning, such as Decision Tree (DT), Support Vector Machine (SVM) and R - Studio algorithms for Naïve Bayes (NB). The data set is extracted from the UCI Machine Learning Repository and classified into a fetal state by means of a normal, suspicious and pathological class that is trained and tested using algorithms and compared on the basis of different performance measures.