Abstract

SARMIENTO, Luis O et al. Non-invasive fetal heart rate estimate by use of blind signal separation techniques. Rev. Colom. Cardiol. [online]. 2010, vol.17, n.4, pp.187-190. ISSN 0120-5633.

Early fetal diagnosis of heart disease during pregnancy is one of the current medical challenges. Therefore, the evaluation of the fetal electrocardiogram is crucial in the diagnosis of various cardiac abnormalities. However, the performance of the fetal electrocardiogram for its further assessment is a complicated task due to many factors ranging from EEG acquisition techniques and conditions of physiological factors, to the possible comorbidity between different pathologies. From years ago, the scientific investigation is focused in the study of the fetal electrocardiogram and both invasive and non-invasive techniques have been used. The non-invasive most used technique is the doppler ultrasound, but this does not provide information about the morphological and temporal parameters of the fetal electrocardiogram; the latter can be obtained by placing electrodes on the abdomen and thorax of the mother. This technique opens the possibility to characterize the fetal electrocardiographic signal but there is the problem that this signal may be mixed with other bio-medical signals such as maternal ECG,respiration, stomach activity, contraction of the uterus, and by external interference with AC power or thermal noise. As of today, the fetal electrocardiographic signal is still in a characterization stage, which is why it is necessary to investigate new methodologies for its study. The aim of this work is to use signal processing techniques to perform a non-invasive fetal electrocardiogram starting from the superficial electrocardiogram of the mother in order to obtain an estimate of the fetal heart rate.

Keywords : fetal heart rate; FECG (fetal electrocardiogram); BSS (blind source separation; ICA (independent component analysis).

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )