Fetal Health Status Prediction During Labor and Delivery Based on Cardiotocogram Data Using Machine and Deep Learning

Abstract

A fetus is an unborn progeny which is in the embryo period until it comes to the world. The fetus grows and develops during every three month period in the pregnancy process. Obstetricians may identify prenatal defects and choose whether to intervene medically through cardiotocogram (CTG) data. However, the obstetrician’s visual assessment of the CTG data could be subjective or incorrect. Therefore, an automatic analysis of CTG data is very essential. In this chapter, the machine and deep learning models are experimented on CTG data. Before evaluating the models, data visualization of CTG data has played a huge role to make an understanding of the data and corresponding requirements of data pre-processing. The various classification models are used to the experiments show that compared with the traditional machine learning models and deep learning models, the data augmentation demonstrations clear benefits in terms of performance metrics.