Find in Library

Preterm births are one of the key causes of death in children under the age of five: they have financial implications associated with care and cause great psychological distress for the families involved. In this work, we applied a novel signal decomposition approach termed Linear Series Decomposition Learner (LSDL) from electrohysterogram (EHG) and tocodynamometer (Toco) signals to the prediction of a preterm delivery, alongside an associated delivery imminency timeline, using the logistic regression and support vector machine classifiers. The results from the classification exercise showed an equivalent performance for the EHG and Toco signals for the preterm prediction, while in the case of the imminency prediction, the Toco signals provided better results in predicting the delivery imminency period. These results have made apparent that a LSDL decomposed Toco/mechanical signal carries useful information which can be used to predict delivery imminency and supersedes that of an electrophysiological/EHG signal.