A deep learning framework for noninvasive fetal ECG signal extraction
Introduction: The availability of proactive techniques for health monitoring is essential to reducing fetal mortality and avoiding complications in fetal wellbeing. In harsh circumstances such as pandemics, earthquakes, and low-resource settings, the incompetence of many healthcare systems worldwide...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2024.1329313/full |
| _version_ | 1797197577934864384 |
|---|---|
| author | Maisam Wahbah Maisam Wahbah M. Sami Zitouni Raghad Al Sakaji Kiyoe Funamoto Namareq Widatalla Anita Krishnan Yoshitaka Kimura Ahsan H. Khandoker |
| author_facet | Maisam Wahbah Maisam Wahbah M. Sami Zitouni Raghad Al Sakaji Kiyoe Funamoto Namareq Widatalla Anita Krishnan Yoshitaka Kimura Ahsan H. Khandoker |
| author_sort | Maisam Wahbah |
| collection | DOAJ |
| description | Introduction: The availability of proactive techniques for health monitoring is essential to reducing fetal mortality and avoiding complications in fetal wellbeing. 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 fetus in hospitals and homes in a direct and fast manner is very important in such conditions.Methods: Monitoring the health of the baby can potentially be accomplished through the computation of vital bio-signal measures 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 a 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.Results: To test the proposed framework, we performed both subject-dependent (5-fold cross-validation) and independent (leave-one-subject-out) tests. The proposed framework achieved 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. Furthermore, we computed the fetal heart rate from the detected R-peaks, and the demonstrated results highlight the robustness of the proposed framework.Discussion: This work has the potential to cater to the critical industry of maternal and fetal healthcare as well as advance related applications. |
| first_indexed | 2024-04-24T06:46:11Z |
| format | Article |
| id | doaj.art-1e587a771bc64433aa75454dbcd80e73 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-24T06:46:11Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-1e587a771bc64433aa75454dbcd80e732024-04-22T18:21:15ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2024-04-011510.3389/fphys.2024.13293131329313A deep learning framework for noninvasive fetal ECG signal extractionMaisam Wahbah0Maisam Wahbah1M. Sami Zitouni2Raghad Al Sakaji3Kiyoe Funamoto4Namareq Widatalla5Anita Krishnan6Yoshitaka Kimura7Ahsan H. Khandoker8College of Engineering and Information Technology, University of Dubai, Dubai, United Arab EmiratesDepartment of Biomedical Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesCollege of Engineering and Information Technology, University of Dubai, Dubai, United Arab EmiratesDepartment of Industrial and Systems Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesTohoku University School of Medicine, Sendai, JapanHealth Engineering Innovation Center (HEIC), Department of Biomedical Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesChildren’s National Hospital, Washington, DC, United StatesTohoku University School of Medicine, Sendai, JapanHealth Engineering Innovation Center (HEIC), Department of Biomedical Engineering, Khalifa University, Abu Dhabi, United Arab EmiratesIntroduction: The availability of proactive techniques for health monitoring is essential to reducing fetal mortality and avoiding complications in fetal wellbeing. 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 fetus in hospitals and homes in a direct and fast manner is very important in such conditions.Methods: Monitoring the health of the baby can potentially be accomplished through the computation of vital bio-signal measures 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 a 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.Results: To test the proposed framework, we performed both subject-dependent (5-fold cross-validation) and independent (leave-one-subject-out) tests. The proposed framework achieved 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. Furthermore, we computed the fetal heart rate from the detected R-peaks, and the demonstrated results highlight the robustness of the proposed framework.Discussion: This work has the potential to cater to the critical industry of maternal and fetal healthcare as well as advance related applications.https://www.frontiersin.org/articles/10.3389/fphys.2024.1329313/fullbiomedical signal processing algorithmsdeep learningfetal heart ratelong short-term memorynoninvasive fetal electrocardiogram |
| spellingShingle | Maisam Wahbah Maisam Wahbah M. Sami Zitouni Raghad Al Sakaji Kiyoe Funamoto Namareq Widatalla Anita Krishnan Yoshitaka Kimura Ahsan H. Khandoker A deep learning framework for noninvasive fetal ECG signal extraction Frontiers in Physiology biomedical signal processing algorithms deep learning fetal heart rate long short-term memory noninvasive fetal electrocardiogram |
| title | A deep learning framework for noninvasive fetal ECG signal extraction |
| title_full | A deep learning framework for noninvasive fetal ECG signal extraction |
| title_fullStr | A deep learning framework for noninvasive fetal ECG signal extraction |
| title_full_unstemmed | A deep learning framework for noninvasive fetal ECG signal extraction |
| title_short | A deep learning framework for noninvasive fetal ECG signal extraction |
| title_sort | deep learning framework for noninvasive fetal ecg signal extraction |
| topic | biomedical signal processing algorithms deep learning fetal heart rate long short-term memory noninvasive fetal electrocardiogram |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2024.1329313/full |
| work_keys_str_mv | AT maisamwahbah adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT maisamwahbah adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT msamizitouni adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT raghadalsakaji adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT kiyoefunamoto adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT namareqwidatalla adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT anitakrishnan adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT yoshitakakimura adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT ahsanhkhandoker adeeplearningframeworkfornoninvasivefetalecgsignalextraction AT maisamwahbah deeplearningframeworkfornoninvasivefetalecgsignalextraction AT maisamwahbah deeplearningframeworkfornoninvasivefetalecgsignalextraction AT msamizitouni deeplearningframeworkfornoninvasivefetalecgsignalextraction AT raghadalsakaji deeplearningframeworkfornoninvasivefetalecgsignalextraction AT kiyoefunamoto deeplearningframeworkfornoninvasivefetalecgsignalextraction AT namareqwidatalla deeplearningframeworkfornoninvasivefetalecgsignalextraction AT anitakrishnan deeplearningframeworkfornoninvasivefetalecgsignalextraction AT yoshitakakimura deeplearningframeworkfornoninvasivefetalecgsignalextraction AT ahsanhkhandoker deeplearningframeworkfornoninvasivefetalecgsignalextraction |