Classification of fetal heart rate tracings based on wavelet-transform & self-organizing-map neural networks

Vasios, G; Prentza, A; Blana, D; Salamalekis, E; Thomopoulos, P; Giannaris, D; Koutsouris, D

dc.contributor.author	Vasios, G	en
dc.contributor.author	Prentza, A	en
dc.contributor.author	Blana, D	en
dc.contributor.author	Salamalekis, E	en
dc.contributor.author	Thomopoulos, P	en
dc.contributor.author	Giannaris, D	en
dc.contributor.author	Koutsouris, D	en
dc.date.accessioned	2014-03-01T02:41:45Z
dc.date.available	2014-03-01T02:41:45Z
dc.date.issued	2001	en
dc.identifier.issn	05891019	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30616
dc.subject	Fetal heart rate monitoring	en
dc.subject	Fetal hypoxia	en
dc.subject	Fetal pulse oximetry	en
dc.subject	Neural network	en
dc.subject	Wavelet analysis	en
dc.title	Classification of fetal heart rate tracings based on wavelet-transform & self-organizing-map neural networks	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IEMBS.2001.1020527	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IEMBS.2001.1020527	en
heal.publicationDate	2001	en
heal.abstract	The objective of the present study is the development of an automated computerized system that will assist the early diagnosis of fetal hypoxia. We demonstrate that it is possible to distinguish between healthy subjects and acidemic fetuses by way of wavelet transform analysis of the fetal heart rate recordings and fetal pulse oximetry (FSpO2). We focus on the values of the standard deviation of the wavelet components (up to scale index 5) and we apply Self-Organizing-Map in order to investigate the relationship between the fetal heart rate variability in different scales and FSpO2 (taking as a threshold for the FSpO2, the 30% level and considering the minimum value of FSpO2 during a 10-minute segment) for normal and acidemic fetuses during the second stage of labor, which can be used to discriminate acidemic fetuses from normal ones. A total accuracy of 91% has been achieved, enabling us to correctly classify all the normal cases (but one) as belonging in the normal group and all pathologic cases (but two) as belonging in the acidemia group, therefore providing a clinically significant measure for the discrimination of the different groups. Fetal pulse oximetry seems to be an important additional source of information.	en
heal.journalName	Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings	en
dc.identifier.doi	10.1109/IEMBS.2001.1020527	en
dc.identifier.volume	2	en
dc.identifier.spage	1633	en
dc.identifier.epage	1636	en