Despite the improvements made in perinatal medicine during the 20th century, stillbirths still happen in 1 in 160 pregnancies in the developed world and this number is 10 times higher in developing countries. It represents a total of 26,000 fetal deaths each year in the US alone. Half of all stillbirths are caused by pregnancy disorders and conditions affecting the placenta.
In addition, between 1 and 7 in 1000 fetuses experience oxygen deprivation during labor which is severe enough to cause brain injury or death. It is estimated that half of these cases of birth-related injury are preventable. Incorrect cardiotocography (CTG) interpretation is leading the list of causes.
The CTG is used routinely to measure maternal uterine pressure and fetal heart rate (FHR). Antenatal CTG monitoring is used to identify fetuses at risk of intrauterine hypoxia and acidaemia. As early as 28 weeks of gestation, analysis of the FHR trace at gestational age is used as a nonstress test to assess the fetal well-being. In the perinatal period, timely, appropriate intervention can avoid fetal neurological damage or death. The CTG is visually assessed by a clinician or interpreted by computer analysis (computerized FHR) of the CTG trace. In the context of labor monitoring, the CTG is used for continuous fetal monitoring. An abnormal heart rate will lead the clinician to perform a cesarean.
With the recent advances in machine learning and statistical signal analysis new algorithms for assessing fetal antenatal or labor health status are being elaborated. These algorithms use signals recorded by usual care monitors (e.g. CTG, scalp electrocardiography) and novel alternative monitoring techniques such as non-invasive fetal electrocardiography or Magnetocardiography. This session aims to discuss the merits, prospects and limitations of novel algorithms intended to improve fetal monitoring.