Intrapartum Fetal Heart Rate Classification: Cross-Database Evaluation

Fetal Heart Rate (FHR) provides obstetricians with essential information about fetal reactions to stress events during delivery. Early detection of fetal acidosis, enabling timely interventions and prevention of adverse consequences of acidosis for fetuses, remains a challenging task. In particular, the use of different, proprietary and small databases in various published works hinders meaningful comparisons of achieved results. This work relies on the the use of two independent databases in order to asses relevantly acidosis detection performance and to address important issues of knowledge transfer (features, classification model) from one database to the other. Using a large set of features, supervised classification is performed with state-of-the-art sparse support vector machines. It shows that selected features and classification performance are consistent for both databases. Further it quantifies the level of generalization of the achieved results, by making use of one database for learning and the other one for testing.