A Survey of Electronic Fetal Monitoring: A Computational Perspective

Electronic Fetal Monitoring (EFM) records fetal heart rate in order to assess fetal well being in labor. Since its suggestion in clinical practise by de Kergeradee in the nineteenth century, it has been adopted as standard medical practise in many delivery scenarios across the globe. The extent of its use has augmented from its original purpose and is now used to not only reduce prenatal mortality, but also neonatal encephalopathy and cerebral palsy. One of the difficulties with EFM is interpreting the data, which is especially difficult if it is acquired in a continuous fashion. A grading system has been developed (utilised for developing a guideline for Clinical Practise Algorithm) which consists of grading fetal heart rate (FHR) into fairly rough categories (three). These categories are defined by values associated with a set of four features. The values for this set of features are potentially influenced by the particular collection equipment and/or operating conditions. These factors, in conjunction with a stressful condition such as a complicated delivery scenario may render rapid and unequivocal reporting of the neonatal status sometimes difficult. This chapter examines the development of automated approaches to classifying FHR into one of three clinically defined categories. The ultimate goal is to produce a reliable automated system that can be deployed in real-time within a clinical setting and can therefore be considered as an adjunctive tool that will provide continuous on-line assistance to medical staff.