Dataset Information

A Strategy for Classification of "Vaginal vs. Cesarean Section" Delivery: Bivariate Empirical Mode Decomposition of Cardiotocographic Recordings.

ABSTRACT: We propose objective and robust measures for the purpose of classification of "vaginal vs. cesarean section" delivery by investigating temporal dynamics and complex interactions between fetal heart rate (FHR) and maternal uterine contraction (UC) recordings from cardiotocographic (CTG) traces. Multivariate extension of empirical mode decomposition (EMD) yields intrinsic scales embedded in UC-FHR recordings while also retaining inter-channel (UC-FHR) coupling at multiple scales. The mode alignment property of EMD results in the matched signal decomposition, in terms of frequency content, which paves the way for the selection of robust and objective time-frequency features for the problem at hand. Specifically, instantaneous amplitude and instantaneous frequency of multivariate intrinsic mode functions are utilized to construct a class of features which capture nonlinear and nonstationary interactions from UC-FHR recordings. The proposed features are fed to a variety of modern machine learning classifiers (decision tree, support vector machine, AdaBoost) to delineate vaginal and cesarean dynamics. We evaluate the performance of different classifiers on a real world dataset by investigating the following classifying measures: sensitivity, specificity, area under the ROC curve (AUC) and mean squared error (MSE). It is observed that under the application of all proposed 40 features AdaBoost classifier provides the best accuracy of 91.8% sensitivity, 95.5% specificity, 98% AUC, and 5% MSE. To conclude, the utilization of all proposed time-frequency features as input to machine learning classifiers can benefit clinical obstetric practitioners through a robust and automatic approach for the classification of fetus dynamics.

SUBMITTER: Saleem S

PROVIDER: S-EPMC6433745 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Strategy for Classification of "Vaginal vs. Cesarean Section" Delivery: Bivariate Empirical Mode Decomposition of Cardiotocographic Recordings.

Saleem Saqib S Naqvi Syed Saud SS Manzoor Tareq T Saeed Ahmed A Ur Rehman Naveed N Mirza Jawad J

Frontiers in physiology 20190319

We propose objective and robust measures for the purpose of classification of "vaginal vs. cesarean section" delivery by investigating temporal dynamics and complex interactions between fetal heart rate (FHR) and maternal uterine contraction (UC) recordings from cardiotocographic (CTG) traces. Multivariate extension of empirical mode decomposition (EMD) yields intrinsic scales embedded in UC-FHR recordings while also retaining inter-channel (UC-FHR) coupling at multiple scales. The mode alignmen ...[more]

PMID: 30941054

Similar Datasets

Project description:BackgroundWith the development of China's two-child-policy, vaginal birth after cesarean section (VBAC) has aroused public concern. It is important to understand the labour characteristics and intrapartum management of women attempting VBAC to enhance the rates of successful VBAC. The purpose of our research was to investigate the differences in the characteristics of labor, intervention measures and perinatal outcomes between women who had a VBAC and primiparas or multiparas not undergoing VBAC, providing clinical references of intrapartum management for women who are planning a VBAC.Material and methodsThis observational retrospective study enrolled all women who laboured spontaneously and who had a VBAC (n = 139) at the Second Affiliated Hospital of Wenzhou Medical University in China between 2016 and 2019. They were allocated into VBAC group A (the previous cesarean section was performed before dilation of the cervix) and VBAC group B (the previous cesarean section was performed after dilation of the cervix). The primipara control group included 149 primiparae, and the multipara control group included 155 multiparae with second vaginal birth. Durations of labor, intervention measures and perinatal outcomes were compared among the groups.ResultsThe durations of labor, intrapartum interventions and maternal and neonatal outcomes in VBAC group A were similar to those of the VBAC group B. However, all women who had a VBAC and those in VBAC group A had shorter first, second and the total stages of labor than primiparae. All women with VBAC and those in VBAC group B had longer second stage of labor, but shorter third stage of labor than multiparae. Oxytocin, labor analgesia and artificial rupture of membranes were administered less often in women with VBAC than in primiparae, while phloroglucinol was administered more often in women with VBAC than in multiparae. Women who had a VBAC were more likely to receive episiotomy and had higher incidences of postpartum hemorrhage than primipara and multipara women.ConclusionsLabor characteristics, intrapartum interventions and perinatal outcomes in women who had a VBAC with cervical dilation were similar to those in women who had a VBAC without cervical dilation before the previous cesarean section, but differed significantly from those of multiparae and primiparae who did not undergo VBAC.

Dataset Information

A Strategy for Classification of "Vaginal vs. Cesarean Section" Delivery: Bivariate Empirical Mode Decomposition of Cardiotocographic Recordings.

Publications

A Strategy for Classification of "Vaginal vs. Cesarean Section" Delivery: Bivariate Empirical Mode Decomposition of Cardiotocographic Recordings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets