Classification of cardiotocographic records by neural networks

Antepartum fetal monitoring based on the classical cardiotocography (CTG) is a noninvasive and low-price tool for checking fetal status. Its introduction in the clinical routine limited the occurrence of fetal problems leading to a reduction of the precocious child mortality. Nevertheless very poor indications on fetal pathologies can be inferred from the actual CTG analysis methods, either they consist of the clinician eye inspection or of automatic algorithms. A relevant amount of this unsatisfactory performance resides on the weakness of methods used for classifying fetal conditions and generate a risk alarm during pregnancy. In the paper three neural classifiers are proposed to discriminate among fetal behavioral states and among normal and pathological fetal conditions, on the basis of CTG recordings. All classifiers are fed by indexes extracted from fetal heart rate signal. Results show very promising performance towards the prediction of fetal outcomes on the set of collected FHR signals.