Early Analysis and Prediction of Fetal Abnormalities Using Machine Learning Classifiers
R. Chinnaiyan, D. Stalin Alex
Abstract
Cardiotocography is an important process in pregnancy such as monitoring the baby. It looks at whether a child's heartbeat is healthy or not. This can also determine whether a baby’s movement in the womb is normal or not. This research work investigates the machine learning classifiers Random Forest, Naïve Bayes and Support Vector Machine for the better analysis and early prediction of fetal abnormalities with the datasets of cardiotocographs. This research work uses 21 abdominal details from CTG datasets imported from Machine Learning Repository. The proposed models will be used as a guide for early analysis and prediction the condition of the fetus whether it is under normal, suspicious or pathological conditions.