Enhanced Optimal Feature Selection Techniques for Fetal Risk Prediction using Machine Learning Algorithms

Abstract

Cardiotocography (CTG) records fetal heart rate (FHR) and uterine contractions (UC) simultaneously. The CTG,*which is one of the*most common*diagnostic techniques used during pregnancy and before delivery to evaluate maternal and fetal well-being. Doctors can understand the state of the fetus by observing the*Cardiotocography trace patterns. There are several techniques for interpreting a typical cardiotocography data based on signal processing and computer programming. Only a few decades after cardiotocography has been implemented into clinical*practice, the predictive potential of these approaches remains controversial and still unreliable This paper presents MRMR feature selection algorithms with four classification for Fetal risk prediction using python.