Extensive-Comparison-of-Machine-Learning-Algorithms-forCardiotocography-Signal-Classification
Cardiotocography (CTG) has been a widely used process to record fetal heart rate (FHR) and uterine contractions (UC) during pregnancy. The results from the CTG is analyzed and used to classify the fetus into one of several morphological patterns or fetal states. This classification has traditionally been done by obstetricians based on standard and approved guidelines but that does not eliminate the tedious nature of the task nor the high probability of classification errors. Recently, machine learning techniques have been used to make these classifications with high accuracy but no extensive comparisons to determine the best model has been done. We carry out predictions for both fetal state and morphological patterns using 7 different models and an ensemble of the best models. We also explore the correlation between the two sets of labels to see how knowledge of one of them could affect the prediction of the other. We then show that our models performed better than those of other researchers who used the UCI data set, the ensemble worked better than the individual models and the correlation between the labels (fetal state and morphological pattern) improved the accuracy predicting one label when the other one is known.
