Automatic Classification of Intrapartal Fetal Heart-Rate Recordings - Can It Compete with Experts?

Fetal heart rate (fHR) is used to evaluate the fetal well-being during the delivery. It provides information of fetal status and allows doctors to detect ongoing hypoxia. The routine clinical evaluation of intrapartal fHR is based on description of macroscopic morphological features of its baseline. In this paper we will show that using additional features for description of the fHR recordings we can improve the classification accuracy. Additionally since results of automatic signal evaluation are easily reproducible we can objectify the whole process thus enabling us to focus on the underlying reasons for high expert inter and intra observer variability.