Detecting Intrapartum Fetal Hypoxia from Cardiotocography Using Machine Learning

Intrapartum cardiotocography (CTG) can identify babies at risk of fetal hypoxia by detecting changes in fetal heart rate and uterine contractions during labour. However, variability in CTG interpretations affects intervention timings. Machine learning (ML) has been applied to this problem and has succeeded. We proposed to use a 5-minute Apgar score as the benchmark for hypoxia in our ML algorithms as it has shown a high correlation with abnormal CTG and better clinical support decision-making than pH umbilical cord blood. We used the CTU-UHB database containing 552 CTGs. We trained and compared five algorithms of decision tree (DT), random forest (RF), support vector machine (SVM), k-Nearest Neighbour (kNN) and artificial neural network (ANN). Performances were evaluated using precision, recall, F1 score and AUROC. The ANN with four deep layers had the highest recall (100%), while the RF classifier had the highest F1 (97%), AUROC (99.73%) and precision (97%) (Table 1). The longest deceleration length is the most important feature among the 21 features. Apgar scores can be used as a surrogate hypoxia marker for classifying CTG, making the model results more informative for clinical decision-making.