Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks
IntroductionCardiotocography (CTG) is used to monitor and evaluate fetal health by recording the fetal heart rate (FHR) and uterine contractions (UC) over time. Among these, the detection of late deceleration (LD), the early marker of fetal mild hypoxemia, is important, and the temporal relationship...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2025.1525266/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590831327903744 |
|---|---|
| author | Ikumi Sato Ikumi Sato Yuta Hirono Yuta Hirono Eiri Shima Hiroto Yamamoto Kousuke Yoshihara Chiharu Kai Chiharu Kai Akifumi Yoshida Fumikage Uchida Naoki Kodama Satoshi Kasai |
| author_facet | Ikumi Sato Ikumi Sato Yuta Hirono Yuta Hirono Eiri Shima Hiroto Yamamoto Kousuke Yoshihara Chiharu Kai Chiharu Kai Akifumi Yoshida Fumikage Uchida Naoki Kodama Satoshi Kasai |
| author_sort | Ikumi Sato |
| collection | DOAJ |
| description | IntroductionCardiotocography (CTG) is used to monitor and evaluate fetal health by recording the fetal heart rate (FHR) and uterine contractions (UC) over time. Among these, the detection of late deceleration (LD), the early marker of fetal mild hypoxemia, is important, and the temporal relationship between FHR and UC is an essential factor in deciphering it. However, there is a problem with UC signals generally tending to have poor signal quality due to defects in installation or obesity in pregnant women. Since obstetricians evaluate potential LD signals only from the FHR signal when the UC signal quality is poor, we hypothesized that LD could be detected by capturing the morphological features of the FHR signal using Artificial Intelligence (AI). Therefore, this study compares models using FHR only (FHR-only model) and FHR with UC (FHR + UC model) constructed using a Convolutional Neural Network (CNN) to examine whether LD could be detected using only the FHR signal.MethodsThe data used to construct the CNN model were obtained from the publicly available CTU-UHB database. We used 86 cases with LDs and 440 cases without LDs from the database, confirmed by expert obstetricians.ResultsThe results showed high accuracy with an area under the curve (AUC) of 0.896 for the FHR-only model and 0.928 for the FHR + UC model. Furthermore, in a validation using 23 cases in which obstetricians judged that the UC signals were poor and the FHR signal had an LD-like morphology, the FHR-only model achieved an AUC of 0.867.ConclusionThis indicates that using only the FHR signal as input to the CNN could detect LDs and potential LDs with high accuracy. These results are expected to improve fetal outcomes by promptly alerting obstetric healthcare providers to signs of nonreassuring fetal status, even when the UC signal quality is poor, and encouraging them to monitor closely and prepare for emergency delivery. |
| format | Article |
| id | doaj-art-9ac6c0335eb04fe7ae8e8786bb187d1e |
| institution | Kabale University |
| issn | 1664-042X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj-art-9ac6c0335eb04fe7ae8e8786bb187d1e2025-01-23T06:56:18ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2025-01-011610.3389/fphys.2025.15252661525266Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networksIkumi Sato0Ikumi Sato1Yuta Hirono2Yuta Hirono3Eiri Shima4Hiroto Yamamoto5Kousuke Yoshihara6Chiharu Kai7Chiharu Kai8Akifumi Yoshida9Fumikage Uchida10Naoki Kodama11Satoshi Kasai12Department of Nursing, Faculty of Nursing, Niigata University of Health and Welfare, Niigata, JapanMajor in Health and Welfare, Graduate School of Niigata University of Health and Welfare, Niigata, JapanMajor in Health and Welfare, Graduate School of Niigata University of Health and Welfare, Niigata, JapanTOITU Co., Ltd., Tokyo, JapanDepartment of Obstetrics and Gynecology, Niigata University Graduate School of Medical and Dental Sciences, Niigata, JapanDepartment of Obstetrics and Gynecology, Niigata University Graduate School of Medical and Dental Sciences, Niigata, JapanDepartment of Obstetrics and Gynecology, Niigata University Graduate School of Medical and Dental Sciences, Niigata, JapanMajor in Health and Welfare, Graduate School of Niigata University of Health and Welfare, Niigata, JapanDepartment of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata, JapanDepartment of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata, JapanTOITU Co., Ltd., Tokyo, JapanDepartment of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata, JapanDepartment of Radiological Technology, Faculty of Medical Technology, Niigata University of Health and Welfare, Niigata, JapanIntroductionCardiotocography (CTG) is used to monitor and evaluate fetal health by recording the fetal heart rate (FHR) and uterine contractions (UC) over time. Among these, the detection of late deceleration (LD), the early marker of fetal mild hypoxemia, is important, and the temporal relationship between FHR and UC is an essential factor in deciphering it. However, there is a problem with UC signals generally tending to have poor signal quality due to defects in installation or obesity in pregnant women. Since obstetricians evaluate potential LD signals only from the FHR signal when the UC signal quality is poor, we hypothesized that LD could be detected by capturing the morphological features of the FHR signal using Artificial Intelligence (AI). Therefore, this study compares models using FHR only (FHR-only model) and FHR with UC (FHR + UC model) constructed using a Convolutional Neural Network (CNN) to examine whether LD could be detected using only the FHR signal.MethodsThe data used to construct the CNN model were obtained from the publicly available CTU-UHB database. We used 86 cases with LDs and 440 cases without LDs from the database, confirmed by expert obstetricians.ResultsThe results showed high accuracy with an area under the curve (AUC) of 0.896 for the FHR-only model and 0.928 for the FHR + UC model. Furthermore, in a validation using 23 cases in which obstetricians judged that the UC signals were poor and the FHR signal had an LD-like morphology, the FHR-only model achieved an AUC of 0.867.ConclusionThis indicates that using only the FHR signal as input to the CNN could detect LDs and potential LDs with high accuracy. These results are expected to improve fetal outcomes by promptly alerting obstetric healthcare providers to signs of nonreassuring fetal status, even when the UC signal quality is poor, and encouraging them to monitor closely and prepare for emergency delivery.https://www.frontiersin.org/articles/10.3389/fphys.2025.1525266/fullcardiotocographyfetal heart ratelate decelerationnonreassuring fetal statusconvolutional neural network |
| spellingShingle | Ikumi Sato Ikumi Sato Yuta Hirono Yuta Hirono Eiri Shima Hiroto Yamamoto Kousuke Yoshihara Chiharu Kai Chiharu Kai Akifumi Yoshida Fumikage Uchida Naoki Kodama Satoshi Kasai Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks Frontiers in Physiology cardiotocography fetal heart rate late deceleration nonreassuring fetal status convolutional neural network |
| title | Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks |
| title_full | Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks |
| title_fullStr | Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks |
| title_full_unstemmed | Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks |
| title_short | Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks |
| title_sort | comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks |
| topic | cardiotocography fetal heart rate late deceleration nonreassuring fetal status convolutional neural network |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2025.1525266/full |
| work_keys_str_mv | AT ikumisato comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT ikumisato comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT yutahirono comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT yutahirono comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT eirishima comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT hirotoyamamoto comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT kousukeyoshihara comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT chiharukai comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT chiharukai comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT akifumiyoshida comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT fumikageuchida comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT naokikodama comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks AT satoshikasai comparisonandverificationofdetectionaccuracyforlatedecelerationwithandwithoututerinecontractionssignalsusingconvolutionalneuralnetworks |