Search

• Uterine Electromyography (Electrohysterography) feature selection. • Statistical validation of Electrohysterogram features' dependency on pregnancy variables. • Mixed models analysis for Electrohysterogram features' characterization. The Uterine Electromyogram often referred as the Electrohysterogram (EHG) is a signal that has the potential to be used for pregnancy monitoring and preterm risk evaluation, amongst other applications. Classification algorithms success heavily rely on the adequacy of the selected features. In this study, Linear Mixed Models are used to evaluate a selected set of EHG features dependency on the gestational age, placental position, age, body mass index (BMI), gravidity and previous cesarean section. The obtained results point out, for example, to a dependency of some EHG features on the BMI and placental position, on the form of a low pass filtering effect. On the other hand, it was found that all the studied entropy features variation with gestational age was not statistically validated. Several conclusions can be drawn from the obtained results, which could be of interest for the increasing number of researchers using the EHG in machine learning computational algorithms, where the features are often selected without a disclosed criterion. [ABSTRACT FROM AUTHOR]

• Uterine Electromyography (Electrohysterography) database representation method. • Uterine contractions multichannel temporal representation for single or multiple subjects along the gestational age. • Uterine contractions' sequencing in the time and space domains. • Sequencing operation includes contraction type such as Alvarez and Braxton-Hicks waveforms. Uterine contractions' monitoring has been pointed out as an important tool that may be useful in the preterm risk assessment, term birth estimation and uterine physiology investigation. The multichannel EHG provides a mapping of the myometrium electrical activity projection on the selected channels, providing a wealth of information, including pacemaker regions, signal propagation and contraction amplitude and spectral characteristics. The EHG multichannel data representation, regarding contractile activity, presents an interpretation challenge, given the presence of the multiple contractions of, possibly, different types, in the respective acquisition channels, for different recording sessions and gestational ages of one or multiple pregnant subjects. Typically, an EHG dataset contains data from various subjects, for which multiple recording sessions could be performed, possibly leading to hundreds of recordings. The post-processing step of this data for contraction retrieval may result in multidimensional datasets, requiring interpretation in multiple research scenarios. In this work, a novel representation method is introduced, the Contractiongram, an intuitive graphical tool to facilitate the interpretation of the EHG contractile data for a subject or a whole dataset, throughout the pregnancy, including multisession acquisition scenarios. An application example is presented for a widely used open access EHG database. A contraction detection and classification were a result of a previous research work and used as a data pool for this study. The graphical representation obtained in the current study is a suitable tool for the identification of uterine contraction patterns in selected channels corresponding to different myometrial regions, in designated gestational ages. [ABSTRACT FROM AUTHOR]