On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor
Preterm pregnancies are one of the leading causes of morbidity and mortality amongst children under the age of five. This is a global issue and has been identified as an area requiring active research. The emphasis now is to identify and develop methods of predicting the likelihood of preterm birth....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Engineering Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4591/27/1/20 |
| _version_ | 1797612001349861376 |
|---|---|
| author | Ejay Nsugbe José Javier Reyes-Lagos Dawn Adams Oluwarotimi Williams Samuel Mojisola Grace Asogbon Michael Provost |
| author_facet | Ejay Nsugbe José Javier Reyes-Lagos Dawn Adams Oluwarotimi Williams Samuel Mojisola Grace Asogbon Michael Provost |
| author_sort | Ejay Nsugbe |
| collection | DOAJ |
| description | Preterm pregnancies are one of the leading causes of morbidity and mortality amongst children under the age of five. This is a global issue and has been identified as an area requiring active research. The emphasis now is to identify and develop methods of predicting the likelihood of preterm birth. This paper uses physiological data from a group of patients in active labor. The dataset contains information about fetal heart rate (FHR) and maternal heart rate (MHR) for all patients and electrohysterogram (EHG) recordings for the measurement of uterine contractions. For the physiological data analysis and associated signal processing, we utilize deep wavelet scattering (DWS). This is an unsupervised decomposition and feature extraction method combining characteristics from deep learning convolutions, as well as the classical wavelet transform, to observe and investigate the extent to which active preterm labor can be accurately identified from an acquired physiological signal, the results of which were compared with the metaheuristic linear series decomposition learner (LSDL). Additional machine learning algorithms are tested on the acquired physiological data to allow for the identification of optimal model architecture for this specific physiological data. |
| first_indexed | 2024-03-11T06:36:16Z |
| format | Article |
| id | doaj.art-c8170b0507554cb5880a86f9c9fcdaf3 |
| institution | Directory Open Access Journal |
| issn | 2673-4591 |
| language | English |
| last_indexed | 2024-03-11T06:36:16Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Engineering Proceedings |
| spelling | doaj.art-c8170b0507554cb5880a86f9c9fcdaf32023-11-17T10:54:39ZengMDPI AGEngineering Proceedings2673-45912022-11-012712010.3390/ecsa-9-13192On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active LaborEjay Nsugbe0José Javier Reyes-Lagos1Dawn Adams2Oluwarotimi Williams Samuel3Mojisola Grace Asogbon4Michael Provost5Nsugbe Research Labs, Swindon SN1 31G, UKSchool of Medicine, Autonomous University of Mexico State (UAEMéx), Toluca de Lerdo 50180, MexicoSchool of Computing, Ulster University, Newtownabbey BT37 0QB, UKKey Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CAS), Shenzhen 518055, ChinaKey Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (CAS), Shenzhen 518055, ChinaIndependent Researcher, Nottingham NG9 3FT, UKPreterm pregnancies are one of the leading causes of morbidity and mortality amongst children under the age of five. This is a global issue and has been identified as an area requiring active research. The emphasis now is to identify and develop methods of predicting the likelihood of preterm birth. This paper uses physiological data from a group of patients in active labor. The dataset contains information about fetal heart rate (FHR) and maternal heart rate (MHR) for all patients and electrohysterogram (EHG) recordings for the measurement of uterine contractions. For the physiological data analysis and associated signal processing, we utilize deep wavelet scattering (DWS). This is an unsupervised decomposition and feature extraction method combining characteristics from deep learning convolutions, as well as the classical wavelet transform, to observe and investigate the extent to which active preterm labor can be accurately identified from an acquired physiological signal, the results of which were compared with the metaheuristic linear series decomposition learner (LSDL). Additional machine learning algorithms are tested on the acquired physiological data to allow for the identification of optimal model architecture for this specific physiological data.https://www.mdpi.com/2673-4591/27/1/20pregnancypretermsignal processingLSDLsignal decompositionobstetric medicine |
| spellingShingle | Ejay Nsugbe José Javier Reyes-Lagos Dawn Adams Oluwarotimi Williams Samuel Mojisola Grace Asogbon Michael Provost On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor Engineering Proceedings pregnancy preterm signal processing LSDL signal decomposition obstetric medicine |
| title | On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor |
| title_full | On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor |
| title_fullStr | On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor |
| title_full_unstemmed | On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor |
| title_short | On the Use of Deep Learning Decompositions and Physiological Measurements for the Prediction of Preterm Pregnancies in a Cohort of Patients in Active Labor |
| title_sort | on the use of deep learning decompositions and physiological measurements for the prediction of preterm pregnancies in a cohort of patients in active labor |
| topic | pregnancy preterm signal processing LSDL signal decomposition obstetric medicine |
| url | https://www.mdpi.com/2673-4591/27/1/20 |
| work_keys_str_mv | AT ejaynsugbe ontheuseofdeeplearningdecompositionsandphysiologicalmeasurementsforthepredictionofpretermpregnanciesinacohortofpatientsinactivelabor AT josejavierreyeslagos ontheuseofdeeplearningdecompositionsandphysiologicalmeasurementsforthepredictionofpretermpregnanciesinacohortofpatientsinactivelabor AT dawnadams ontheuseofdeeplearningdecompositionsandphysiologicalmeasurementsforthepredictionofpretermpregnanciesinacohortofpatientsinactivelabor AT oluwarotimiwilliamssamuel ontheuseofdeeplearningdecompositionsandphysiologicalmeasurementsforthepredictionofpretermpregnanciesinacohortofpatientsinactivelabor AT mojisolagraceasogbon ontheuseofdeeplearningdecompositionsandphysiologicalmeasurementsforthepredictionofpretermpregnanciesinacohortofpatientsinactivelabor AT michaelprovost ontheuseofdeeplearningdecompositionsandphysiologicalmeasurementsforthepredictionofpretermpregnanciesinacohortofpatientsinactivelabor |