AUTHOR=Wahbah Maisam , Zitouni M. Sami , Al Sakaji Raghad , Funamoto Kiyoe , Widatalla Namareq , Krishnan Anita , Kimura Yoshitaka , Khandoker Ahsan H. 

TITLE=A deep learning framework for noninvasive fetal ECG signal extraction

JOURNAL=Frontiers in Physiology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2024.1329313

DOI=10.3389/fphys.2024.1329313

ISSN=1664-042X

ABSTRACT=The availability of proactive techniques for health monitoring is essential to reduce fetal mortality and avoid complications in fetal well-being. In harsh circumstances such as pandemics, earthquakes, and low-resource settings, the incompetence of many healthcare systems worldwide in providing essential services, especially for pregnant women, is critical. Being able to continuously monitor the fetal in hospitals and homes in a direct and fast manner is very important in such conditions. This can potentially be accomplished through the computation of vital bio-signal measures for monitoring the health of the baby using a clear fetal Electrocardiogram (ECG) signal. The aim of this study is to develop a framework to detect and identify the R-peaks of the fetal ECG directly from 12 channel abdominal composite signal. Thus, signals were recorded noninvasively from 70 pregnant (healthy and with health conditions) women with no records of fetal abnormalities. The proposed model employs a recurrent neural network architecture to robustly detect the fetal ECG R-peaks. To test the proposed framework, we performed both of subject-dependent (5 folds cross-validation) and -independent (leave-one-subject-out) tests. The proposed framework achieved an average accuracy values of 94.2% and 88.8%, respectively. More specifically, the leave-one-subject-out test accuracy was 86.7% during the challenging period of vernix caseosa layer formation. Further, we computed the fetal heart rate from the detected R-peaks and the demonstrated results highlight the robustness of the proposed framework. This work has the potential of catering the critical industry of maternal and fetal healthcare, as well as advancing related applications.