Intelligent fetal heart rate computer systems in intrapartum surveillance

The intrapartum cardiotocogram has had a disappointing impact on clinical practice. Misinterpretation of the cardiotocogram not only causes an increase in unnecessary intervention but is also implicated in a large proportion of patients with birth asphyxia and avoidable perinatal morbidity. Over the past 10-20 years, groups have attempted to develop computer systems capable of analysing the cardiotocogram but with limited success. The likely explanation is that these conventional systems analyse the cardiotocogram in isolation from clinical factors. More recently, research has focused on the use of artificial intelligence techniques which can assess the whole clinical picture to support clinical decision making during labour. The current literature is reviewed and a system that has been validated by comparison of its performance with 17 experts is described.