Extracting Interpretable Features for Fetal Heart Rate Recordings with Gaussian Processes

During labor, fetal heart rate (FHR) and uterine activity (UA) are continuously monitored with Cardiotocography (CTG). The FHR and UA signals are visually inspected by obstetricians to assess the fetal well-being. However, due to the subjectivity of the visual inspection, the evaluations of CTG recordings performed by obstetricians have high inter- and intra-variability. The computerized analysis of FHR relies on features either hand-crafted by experts or automatically learned by machine learning methods. However, the popular interpretable FHR features, in general, have low correlation with the pH value of the umbilical cord blood at birth, which is the current gold standard for labeling FHRs in the computerized analysis of FHRs. The features found by machine learning methods, by contrast, usually have limited interpretability. In this paper, in a follow up of our previous work on FHR analysis using Gaussian processes (GPs), we explore the possibility of using the hyperparameters of GPs as interpretable features. Our results indicate that some GP features achieve high correlation with the pH values, while at the same time they are not highly correlated with other popular features.