Automatic detection of fetal health status from cardiotocography data using machine learning algorithms

A method for the automatic determination of the fetus health status using Cardiotocography (CTG) and computer-based machine learning algorithms was developed. Five computation friendly machine learning algorithms were used to create multiclass classification models to predict the fetus health status from secondary CTG dataset containing normal, suspected and pathologic data available at University California Irvine Machine Learning Repository. Furthermore, a comparative analysis among the built models was executed. According to the comparative analysis, the best model to automatically detect fetal health was the extreme gradient boosting algorithm-based model with an accuracy of 96.7% and an F1-Score of 0.963 in the pathologic class. This finding thus has the potential to diagnose fetal heart conditions unsupervised, and more efficiently and effectively.