Pasar al contenido principal

ELECTROHISTEROGRAFIA PARA LA MEJORA EN LA TOMA DE DECISIONES EN SITUACIONES DE RIESGO EN OBSTETRICIA: PARTO PREMATURO E INDUCCION DEL PARTO

RTI2018-094449-A-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 21
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Comparative Study of Vaginal Labor and Caesarean Section Postpartum Uterine Myoelectrical Activity

  • Díaz-Martínez, María del Alba
  • Mas-Cabo, Javier
  • Cardona-Urrego, Karen
  • Monfort-Ortiz, Rogelio
  • Lopez-Corral, Angel
  • De Arriba-Garcia, Maria
  • Perales, Alfredo
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Ye Lin, Yiyao|||0000-0003-2929-181X
[EN] Postpartum hemorrhage (PPH) is one of the major causes of maternal mortality and morbidity worldwide, with uterine atony being the most common origin. Currently there are no obstetrical techniques available for monitoring postpartum uterine dynamics, as tocodynamometry is not able to detect weak uterine contractions. In this study, we explored the feasibility of monitoring postpartum uterine activity by non-invasive electrohysterography (EHG), which has been proven to outperform tocodynamometry in detecting uterine contractions during pregnancy. A comparison was made of the temporal, spectral, and non-linear parameters of postpartum EHG characteristics of vaginal deliveries and elective cesareans. In the vaginal delivery group, EHG obtained a significantly higher amplitude and lower kurtosis of the Hilbert envelope, and spectral content was shifted toward higher frequencies than in the cesarean group. In the non-linear parameters, higher values were found for the fractal dimension and lower values for Lempel-Ziv, sample entropy and spectral entropy in vaginal deliveries suggesting that the postpartum EHG signal is extremely non-linear but more regular and predictable than in a cesarean. The results obtained indicate that postpartum EHG recording could be a helpful tool for earlier detection of uterine atony and contribute to better management of prophylactic uterotonic treatment for PPH prevention., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR) and the Generalitat Valenciana (GV/2018/104 and AICO/2019/220).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Identification of atrial fibrillation drivers by means of concentric ring electrodes

  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Guillem Sánchez, María Salud|||0000-0001-5660-3693
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Rodrigo, Miguel
[EN] Background and objective: The prevalence of atrial fibrillation (AF) has tripled in the last 50 years due to population aging. High-frequency (DFdriver) activated atrial regions lead the activation of the rest of the atria, disrupting the propagation wavefront. Fourier based spectral analysis of body surface potential maps have been proposed for DFdriver identification, although these approaches present serious drawbacks due to their limited spectral resolution for short AF epochs and the blurring effect of the volume conductor. Laplacian signals (BCECG) from bipolar concentric ring electrodes (CRE) have been shown to outperform the spatial resolution achieved with conventional unipolar recordings. Our aimed was to determine the best DFdriver estimator in endocardial electrograms and to assess the BC-ECG capacity of CRE to quantify AF activity non-invasively. Methods: 31 AF episodes were simulated using realistic tridimensional models of the atria electrical activity and torso. Periodogram and autoregressive (AR) spectral estimators were computed and the percentile (P90th, P95th and P98th) to impose on the dominant frequencies (DFs) across whole atria to define the best DFdriver estimator evaluated. The identification of DFdriver on DFs from BC-ECG and unipolar surface signals with conventional disc electrodes was compared. Results: The best DFdriver estimator was P95th and AR order 100. BC-ECG signals allowed better detection of AF activity than unipolar signals, with a significantly greater percentage of electrode locations in which DFdriver was identified (p-value 0.0095). Conclusions: The use of BC-ECG signals for body surface Laplacian potential mapping with CRE could be helpful for better AF diagnosis, prognosis and ablation procedures than those with conventional disk electrodes., This work was supported by the Spanish Ministry of Economy and Competitiveness (PID2020-114291RB-I00) and the Instituto de Salud Carlos III, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR, PI17/01106) , EIT Health (Activity code 19600, EIT Health is supported by EIT, a body of the European Union) and the Generalitat Valenciana (AICO/2021/318, AICO/2021/126 and AICO/2019/220) .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Dispersion Entropy: A Measure of Electrohysterographic Complexity for Preterm Labor Discrimination

  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Díaz-Martínez, María del Alba
  • González Martínez, María
  • Monfort-Ortiz, R.
[EN] Although preterm labor is a major cause of neonatal death and often leaves health sequels in the survivors, there are no accurate and reliable clinical tools for preterm labor prediction. The Electrohysterogram (EHG) has arisen as a promising alternative that provides relevant information on uterine activity that could be useful in predicting preterm labor. In this work, we optimized and assessed the performance of the Dispersion Entropy (DispEn) metric and compared it to conventional Sample Entropy (SampEn) in EHG recordings to discriminate term from preterm deliveries. For this, we used the two public databases TPEHG and TPEHGT DS of EHG recordings collected from women during regular checkups. The 10th, 50th and 90th percentiles of entropy metrics were computed on whole (WBW) and fast wave high (FWH) EHG bandwidths, sweeping the DispEn and SampEn internal parameters to optimize term/preterm discrimination. The results revealed that for both the FWH and WBW bandwidths the best separability was reached when computing the 10th percentile, achieving a p-value (0.00007) for DispEn in FWH, c = 7 and m = 2, associated with lower complexity preterm deliveries, indicating that DispEn is a promising parameter for preterm labor prediction., This work was supported by the Spanish ministry of economy and competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR) and the Generalitat Valenciana (AICO/2019/220).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Concentric ring electrodes for non-invasive recording of gastric myoelectric activity

  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Martínez-de-Juan, José L.|||0000-0001-9133-3123
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Jareño-Silvestre, A.
[EN] Electrogastrography has emerged as a non-invasive technique for diagnosing an extensive variety of gastrointestinal disorders. The non-invasive electrogastrogram (EGG) remains a challenge due to the poor spatial resolution of conventional disk electrodes. In this work we attempted to determine the possibility of detecting gastric myoelectric activity using concentric ring electrodes (CRE) proposed to improve the spatial resolution of bioelectrical recordings. We simultaneously recorded 8 bipolar and bipolar concentric (BC) EGGs acquired by disk electrodes and CREs, respectively. The BC EGG showed lower signal amplitude than the bipolar recordings but were less influenced by cardiac interference and had a slow wave (SW) detectability above 80% when positioned over the stomach. We found a similar gastric SW frequency in both bipolar and BC EGG records in both fasting and postprandial states and a similar postprandial/fasting power ratio, suggesting the feasibility of using CRE to identify gastric myoelectric activity., Research supported by a grant from the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Directed Functional Coordination Analysis of Swallowing Muscles in Healthy and Dysphagic Subjects by Surface Electromyography

  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Galiano-Botella, Marina
  • Roldan-Vasco, Sebastian
  • Orozco-Duque, Andrés
[EN] Swallowing is a complex sequence of highly regulated and coordinated skeletal and smooth muscle activity. Previous studies have attempted to determine the temporal relationship between the muscles to establish the activation sequence pattern, assessing functional muscle coordination with cross-correlation or coherence, which is seriously impaired by volume conduction. In the present work, we used conditional Granger causality from surface electromyography signals to analyse the directed functional coordination between different swallowing muscles in both healthy and dysphagic subjects ingesting saliva, water, and yoghurt boluses. In healthy individuals, both bilateral and ipsilateral muscles showed higher coupling strength than contralateral muscles. We also found a dominant downward direction in ipsilateral supra and infrahyoid muscles. In dysphagic subjects, we found a significantly higher right-to-left infrahyoid, right ipsilateral infra-to-suprahyoid, and left ipsilateral supra-to-infrahyoid interactions, in addition to significant differences in the left ipsilateral muscles between bolus types. Our results suggest that the functional coordination analysis of swallowing muscles contains relevant information on the swallowing process and possible dysfunctions associated with dysphagia, indicating that it could potentially be used to assess the progress of the disease or the effectiveness of rehabilitation therapies., This work was partially supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR), and the Regional Joint Call for R+D+i projects (G8+1, Medellin, Colombia; Research Project PE2020-9 (G8 2020-39651)).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Evaluation of Swallowing Related Muscle Activity by Means of Concentric Ring Electrodes

  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Restrepo-Agudelo, Sebastián
  • Perez-Giraldo, Estefanía
  • Orozco-Duque, Andrés
[EN] Surface electromyography (sEMG) can be helpful for evaluating swallowing related muscle activity. Conventional recordings with disc electrodes suffer from significant crosstalk from adjacent muscles and electrode-to-muscle fiber orientation problems, while concentric ring electrodes (CREs) offer enhanced spatial selectivity and axial isotropy. The aim of this work was to evaluate CRE performance in sEMG recordings of the swallowing muscles. Bipolar recordings were taken from 21 healthy young volunteers when swallowing saliva, water and yogurt, first with a conventional disc and then with a CRE. The signals were characterized by the root-mean-square amplitude, signal-to-noise ratio, myopulse, zero-crossings, median frequency, bandwidth and bilateral muscle cross-correlations. The results showed that CREs have advantages in the sEMG analysis of swallowing muscles, including enhanced spatial selectivity and the associated reduction in crosstalk, the ability to pick up a wider range of EMG frequency components and easier electrode placement thanks to its radial symmetry. However, technical changes are recommended in the future to ensure that the lower CRE signal amplitude does not significantly affect its quality. CREs show great potential for improving the clinical monitoring and evaluation of swallowing muscle activity. Future work on pathological subjects will assess the possible advantages of CREs in dysphagia monitoring and diagnosis., This work was supported by the Spanish Ministry of the Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Electrohysterogram for ANN-Based Prediction of Imminent Labor in Women with Threatened Preterm Labor Undergoing Tocolytic Therapy

  • Mas-Cabo, Javier
  • Alberola Rubio, J.
  • Monfort-Ortiz, R.
  • Martinez-Saez, C.
  • Perales, A.
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Ye Lin, Yiyao|||0000-0003-2929-181X
[EN] Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy and entails high costs for health systems. Currently, no reliable labor proximity prediction techniques are available for clinical use. Regular checks by uterine electrohysterogram (EHG) for predicting preterm labor have been widely studied. The aim of the present study was to assess the feasibility of predicting labor with a 7- and 14-day time horizon in TPL women, who may be under tocolytic treatment, using EHG and/or obstetric data. Based on 140 EHG recordings, artificial neural networks were used to develop prediction models. Non-linear EHG parameters were found to be more reliable than linear for differentiating labor in under and over 7/14 days. Using EHG and obstetric data, the <7- and <14-day labor prediction models achieved an AUC in the test group of 87.1 +/- 4.3% and 76.2 +/- 5.8%, respectively. These results suggest that EHG can be reliable for predicting imminent labor in TPL women, regardless of the tocolytic therapy stage. This paves the way for the development of diagnostic tools to help obstetricians make better decisions on treatments, hospital stays and admitting TPL women, and can therefore reduce costs and improve maternal and fetal wellbeing., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR) and by the Generalitat Valenciana (AICO/2019/220).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Assessment of Dispersion and Bubble Entropy Measures for Enhancing Preterm Birth Prediction Based on Electrohysterographic Signals

  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Beskhani, Raja
  • Díaz-Martínez, María del Alba
  • Monfort-Ortiz, Rogelio
  • Diago-Almela, Vicente Jose
  • Hao, Dongmei
[EN] One of the remaining challenges for the scientific-technical community is predicting preterm births, for which electrohysterography (EHG) has emerged as a highly sensitive prediction technique. Sample and fuzzy entropy have been used to characterize EHG signals, although they require optimizing many internal parameters. Both bubble entropy, which only requires one internal parameter, and dispersion entropy, which can detect any changes in frequency and amplitude, have been proposed to characterize biomedical signals. In this work, we attempted to determine the clinical value of these entropy measures for predicting preterm birth by analyzing their discriminatory capacity as an individual feature and their complementarity to other EHG characteristics by developing six prediction models using obstetrical data, linear and non-linear EHG features, and linear discriminant analysis using a genetic algorithm to select the features. Both dispersion and bubble entropy better discriminated between the preterm and term groups than sample, spectral, and fuzzy entropy. Entropy metrics provided complementary information to linear features, and indeed, the improvement in model performance by including other non-linear features was negligible. The best model performance obtained an F1-score of 90.1 ± 2% for testing the dataset. This model can easily be adapted to real-time applications, thereby contributing to the transferability of the EHG technique to clinical practice., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR), and by the Generalitat Valenciana (AICO/2019/220)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Proyecto fin de carrera (BachelorThesis)

Análisis de las diferencias en parámetros de electrohisterograma, de tramos basales y contráctiles, entre partos inminentes y lejanos de mujeres con amenaza de parto prematuro

  • Martínez Pérez, Marta
[ES] Ante una amenaza de parto prematuro (APP) en la que los riesgos materno-fetales son mayores que en una gestación de más de 37 semanas, la discriminación de si éste realmente se dará de forma inminente (¿7 días) o más lejano (>7 días) es de gran relevancia para la mejor gestión de cada caso y de los recursos hospitalarios. Como valoración adicional del estado electrofisiológico del útero para distinguir entre ambas situaciones se propone la electrohisterografía. Partiendo de una base de datos de la UPV en colaboración con el Hospital La Fe de registros electrohisterográficos en mujeres con APP en condiciones clínicas habituales (bajo tratamientos tocolíticos), en este trabajo se analizan los cambios ante el parto inminente en parámetros de amplitud, espectrales y de complejidad valorados en tramos de actividad basal y contráctil de forma independiente y contrastados con el estudio `global¿ (promediado) usado en la bibliografía. Adicionalmente se valoran los ratios entre contracción y basal de los parámetros computados. Todo ello con énfasis en valorar su capacidad discriminatoria. Los resultados apuntan a que el número de parámetros obtenidos para discriminar entre grupos de pacientes es mayor con la valoración independiente en basal y contracción que en la global. Los parámetros de complejidad muestran que la señal se ordena a medida que se acerca el parto y los parámetros espectrales muestran un desplazamiento hacia bajas frecuencias. En todo caso, todas las familias de parámetros ofrecen capacidad discriminatoria entre parto inminente y no inminente. Por otro lado, el ratio entre tramos contráctiles y basales por parámetros muestra que los mayores cambios los sufren las pacientes de parto cercano. En futuros estudios se deberá valorar la complementariedad o redundancia de la información proporcionada por los distintos parámetros en los distintos tipos de tramos evaluados para el diagnóstico del parto inminente en APP., [EN] Faced with a threat of preterm labor (TPL) in which the maternal-fetal risks are greater than in a gestation of more than 37 weeks, the discrimination of whether it really will occur imminently (¿ 7 days) or more distant (>7 days) is relevant for the better management of each case and hospital resources. As an additional assessment of the electrophysiological state of the uterus to distinguish among both situations, it is proposed the use of electrohysterography. Based on a UPV database in collaboration with Hospital La Fe of electrohysterographic records in women with TPL in usual clinical conditions (under tocolytic treatments), this study analyses the changes in the face of imminent delivery in amplitude, spectral and complexity assessed in basal and contractile activity ranges independently and contrasted with the global study (averaged) used in the literature. Additionally, the ratios between contraction and baseline of the computed parameters are evaluated. All this with an emphasis on assessing their discriminatory capacity. The results suggest that the number of parameters obtained to discriminate between groups of patients is greater with the independent evaluation at baseline and contraction than in the global one. The complexity parameters show that the signal is ordered as parturition approaches and the spectral parameters shifts towards low frequences. In any case, all the families of parameters offer discriminatory capacity among imminent and non-imminent delivery. On the other hand, the ratio between contractile and basal sections by parameters shows that the greatest changes are suffered by patients with close labor. Future studies should assess the complementarity or redundancy of the information provided by the different parameters in the different types of sections evaluated for the diagnosis of imminent delivery in TPL.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Prediction of Labor Induction Success from the Uterine Electrohysterogram

  • Benalcazar-Parra, Carlos
  • Monfort-Ortiz, Rogelio
  • Alberola Rubio, José
  • PERALES MARIN, ALFREDO JOSE
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Prats-Boluda, Gema|||0000-0002-9362-5055
[EN] Pharmacological agents are often used to induce labor. Failed inductions are associated with unnecessarily long waits and greater maternal-fetal risks, as well as higher costs. No reliable models are currently able to predict the induction outcome from common obstetric data (area under the ROC curve (AUC) between 0.6 and 0.7). The aim of this study was to design an early success-predictor system by extracting temporal, spectral, and complexity parameters from the uterine electromyogram (electrohysterogram (EHG)). Different types of feature sets were used to design and train artificial neural networks: Set_1: obstetrical features, Set_2: EHG features, and Set_3: EHG+obstetrical features. Predictor systems were built to classify three scenarios: (1) induced women who reached active phase of labor (APL) vs. women who did not achieve APL (non-APL), (2) APL and vaginal delivery vs. APL and cesarean section delivery, and (3) vaginal vs. cesarean delivery. For Scenario 3, we also proposed 2-step predictor systems consisting of the cascading predictor systems from Scenarios 1 and 2. EHG features outperformed traditional obstetrical features in all the scenarios. Little improvement was obtained by combining them (Set_3). The results show that the EHG can potentially be used to predict successful labor induction and outperforms the traditional obstetric features. Clinical use of this prediction system would help to improve maternal-fetal well-being and optimize hospital resources., This work received financial support from the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (DPI2015-68397-R and RTI2018-094449-A-I00), Universitat Politècnica de València VLC/Campus (UPV-FE-2018-B02), Generalitat Valenciana (GV/2018/104), and Bial S.A.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Design and Assessment of a Robust and Generalizable ANN-Based Classifier for the Prediction of Premature Birth by means of Multichannel Electrohysterographic Records

  • Mas-Cabo, Javier
  • Alberola Rubio, José
  • Perales Marín, Alfredo José
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Ye Lin, Yiyao|||0000-0003-2929-181X
[EN] Preterm labor is one of the major causes of neonatal deaths and also the cause of significant health and development impairments in those who survive. However, there are still no reliable and accurate tools for preterm labor prediction in clinical settings. Electrohysterography (EHG) has been proven to provide relevant information on the labor time horizon. Many studies focused on predicting preterm labor by using temporal, spectral, and nonlinear parameters extracted from single EHG recordings. However, multichannel analysis, which includes information from the whole uterus and about coupling between the recording areas, may provide better results. The cross validation method is often used to design classifiers and evaluate their performance. However, when the validation dataset is used to tune the classifier hyperparameters, the performance metrics of this dataset may not properly assess its generalization capacity. In this work, we developed and compared different classifiers, based on artificial neural networks, for predicting preterm labor using EHG features from single and multichannel recordings. A set of temporal, spectral, nonlinear, and synchronization parameters computed from EHG recordings was used as the input features. All the classifiers were evaluated on independent test datasets, which were never ¿seen¿ by the models, to determine their generalization capacity. Classifiers¿ performance was also evaluated when obstetrical data were included. The experimental results show that the classifier performance metrics were significantly lower in the test dataset (AUC range 76-91%) than in the train and validation sets (AUC range 90-99%). The multichannel classifiers outperformed the single-channel classifiers, especially when information was combined into mean efficiency indexes and included coupling information between channels. Including obstetrical data slightly improved the classifier metrics and reached an AUC of for the test dataset. These results show promise for the transfer of the EHG technique to preterm labor prediction in clinical practice., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (DPI2015-68397-R, MINECO/FEDER, and RTI2018-094449-A-I00-AR); Generalitat Valenciana (AICO/2019/220); and the VLC/Campus (UPV-FE-2018-B03).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Inception 1D-convolutional neural network for accurate prediction of electrical insulator leakage current from environmental data during its normal operation using long-term recording

  • Bueno Barrachina, José Manuel
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Fuster Roig, Vicente Luis|||0000-0002-2428-9203
[EN] Contamination flashover remains one of the biggest challenges for power grid designers and maintenance engineers. Insulator leakage current contains relevant information about their state so that continuous monitoring is considered the most effective way to prevent contamination flashover. In this work, we attempted to accurately predict insulator leakage current in real time during normal operations based on environmental data using long-term recordings. We first confirmed that the history of environmental data also contained relevant information to predict leakage current by conditional Granger analysis and determined that 20 was the optimal previous samples number for this purpose. We then compared the performance of typical regression models and convolutional neural network (CNN), when using both current and the last 21 samples as input features. We confirmed that the model with the last 21 samples might perform significantly better. Input features pre-processing by cascaded inception architecture was fundamental to capture the complex dynamic interaction between environmental data and leakage current and significantly improved the model performance. CNN based on inception architecture performed much better, achieving an average R2 of 0.94 ±0.03. The proposed model could be used to predict leakage current in both porcelain insulators with or without coatings and silicone composite insulators. Our results pave the way for creating an on-line pre-warning system adapted to individual installations, can anticipate the negative consequences of weather and/or pollution deposits and is useful for designing a strategic high-voltage electrical insulator preventive maintenance plan for preventing contamination flashover and thus increase power grid reliability and resilience., This work was supported by the Spanish Ministry of Economy and Competitiveness, Spain, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR) .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Tesis doctoral (DoctoralThesis)

Biomarker Identification Based on Human Electrohysterography for the Early Detection of Risk in Different Obstetric Scenarios: Preterm Birth, Induction of Labour and Postpartum

  • Díaz Martínez, María del Alba
[ES] Durante la gestación, la mujer experimenta cambios fisiológicos, metabólicos y morfológicos que podrían conllevar importantes riesgos materno-fetales. En primer lugar, el parto prematuro es la principal causa de mortalidad infantil, con una prevalencia del 10% en gestaciones únicas (SG) y del 50% en gestaciones múltiples (MG). Por tanto, la caracterización de la actividad uterina, así como la comparación entre SG y MG, puede ayudar a comprender y manejar mejor esta patología. En segundo lugar, la inducción del parto (IOL) se asocia a un mayor riesgo de mortalidad y morbilidad materna cuando la fase latente del parto se prolonga excesivamente, especialmente en mujeres nulíparas. Sin embargo, la literatura es escasa y no se ha observado claramente la respuesta electrofisiológica uterina al fármaco de IOL. En este sentido, el estudio de biomarcadores basados en la electrohisterografía (EHG) podría ayudar a detectar precozmente el riesgo de fracaso de la IOL y orientar las decisiones clínicas en consecuencia. En tercer lugar, la hemorragia posparto (PPH) constituye una de las principales causas de mortalidad materna en el mundo. Su prevalencia es del 2-6%, y causa la muerte de 75.000 mujeres cada año. La principal causa es la atonía uterina, por lo que la EHG se convierte en la herramienta ideal para valorar el estado del útero e indicar el riesgo de PPH en función de la ausencia o no de actividad. Por ello, el objetivo de la presente tesis doctoral es la identificación de EHG-biomarcadores para la detección precoz de situaciones obstétricas de alto riesgo. Para ello, se generaron las bases de datos de señal EHG y de datos obstétricos para cada escenario en el Hospital Universitario y Politécnico La Fe. La mayor impulsividad y predictibilidad en MG respecto a SG durante el tercer trimestre, así como la correlación significativa entre los EHG-biomarcadores y el peso fetal, sugirió un acoplamiento electromecánico entre la sobredistensión y la actividad mioeléctrica registrada en superficie. En cuanto a la IOL, el grupo de éxito mostró un aumento significativo del número de contracciones y de la excitabilidad celular, junto con una menor complejidad, a partir de 2-3 horas tras la administración del fármaco de IOL. No se observaron cambios significativos con respecto a la actividad basal en el grupo de fracaso. La comparación basada en la paridad reportó una mayor ratio de progresión de la amplitud de la señal en el grupo de parosas. La actividad mioeléctrica en el postparto vaginal resultó ser más frecuente e intensa, además de exhibir una mayor excitabilidad celular que en los partos por cesárea. La capacidad discriminatoria de los biomarcadores de EHG para la detección precoz del riesgo en diversos contextos obstétricos ha hecho avanzar el conocimiento electrofisiológico actual del útero in vivo. La traslación del EHG a la práctica clínica requerirá la automatización del procesamiento de señales, para culminar en la creación de modelos predictivos generalizados y robustos que apoyen la toma de decisiones clínicas, mejoren la planificación y gestión del parto, prevengan complicaciones maternas y fetales y optimicen la asignación de recursos hospitalarios., [CA] Durant la gestació, la dona experimenta canvis fisiològics, metabòlics i morfològics que podrien comportar importants riscos matern-fetals. En primer lloc, el part prematur és la principal causa de mortalitat infantil, amb una prevalença del 10% en gestacions úniques (SG) i del 50% en gestacions múltiples (MG). Per tant, la caracterització de l'activitat uterina, així com la comparació entre SG i MG, ajuda a millorar la comprensió i gestió d'esta patologia. En segon lloc, la inducció del part (IOL) s'associa a un major risc de mortalitat i morbiditat materna quan la fase latent del part es prolonga excessivament, especialment en dones nul·lípares. No obstant això, la literatura és escassa i no s'ha observat clarament la resposta electrofisiològica uterina al fàrmac d'IOL. En este sentit, l'estudi de biomarcadors basats en la electrohisterografia (EHG) pot ajudar a detectar precoçment el risc de fracàs de la IOL i orientar les decisions clíniques en conseqüència. En tercer lloc, l'hemorràgia postpart (PPH) constituïx una de les principals causes de mortalitat materna en el món. La seua prevalença és del 2-6%, i causa la mort de 75.000 dones cada any. La principal causa és l'atonia uterina, per la qual cosa l'EHG es convertix en la ferramenta ideal per a valorar l'estat de l'úter i indicar el risc de PPH en funció de l'absència o no d'activitat. Per tant, l'objectiu de la present tesi doctoral és la identificació de biomarcadors d'EHG per a la detecció precoç de situacions d'alt risc obstètric. En este propòsit, s'han generat les bases de dades de senyals d'EHG i informació obstètrica de cada escenari en estudi a l'Hospital Universitari i Politècnic La Fe. La major impulsivitat i predictibilitat en MG respecte a SG durant el tercer trimestre, així com la correlació significativa entre els biomarcadors d'EHG i el pes fetal, va suggerir un acoblament electromecànic entre la sobredistensió i l'activitat mioelèctrica registrada en superfície. Pel que fa a l'IOL, el grup exitós va mostrar un augment significatiu del nombre de contraccions i de l'excitabilitat cel·lular, així com una menor complexitat, a partir de 2-3 hores tras l'administració del fàrmac de IOL. No es van observar canvis significatius respecte a l'activitat basal en el grup de fracàs. La comparació basada en la paritat va reportar una major ràtio de progressió de l'amplitud del senyal en el grup de paroses. L'activitat mioelèctrica en el postpart vaginal va ser més freqüent i intensa, a més d'exhibir una major excitabilitat cel·lular en els parts per cesària. La capacitat discriminatòria dels biomarcadors d'EHG per a la detecció precoç del risc en diversos contextos obstètrics ha fet avançar el coneixement electrofisiològic actual de l'úter in vivo. La translació de l'EHG a la pràctica clínica requerirá l'automatització del processament de senyals, per a culminar en la creació de models predictius generalitzats i robustos que donen suport a la presa de decisions clíniques, milloren la planificació i gestió del part, previnguen complicacions matern-fetals i optimitzen l'assignació de recursos hospitalaris., [EN] During pregnancy, women undergo physiological, metabolic, and morphological changes that could lead to significant maternal-foetal risks. Firstly, preterm birth is the leading cause of infant mortality, with a prevalence 10% in single (SG) and 50% in multiple gestations (MG). The characterisation of uterine activity, as well as the comparison between SG and MG, may thus help to better understand and manage this pathology. Secondly, induction of labour (IOL) is associated with an increased risk of maternal mortality and morbidity when the latent phase of labour is excessively prolonged, especially in nulliparous women. However, the literature is sparse and the uterine electrophysiological response to the IOL drug has not been clearly observed. In this sense, the study of biomarkers based on electrohysterography (EHG) could help to early detect the risk of IOL failure and guide clinical decisions accordingly. Thirdly, postpartum haemorrhage (PPH) constitutes one of the main causes of maternal mortality in the world. Its prevalence is 2-6%, causing the death of 75,000 women each year. The main cause is uterine atony, so EHG becomes the ideal tool to assess the state of the uterus and indicate the PPH risk based on the absence or not of activity. Therefore, the aim of the present doctoral thesis is the identification of EHG-biomarkers for the early detection of high-risk obstetrical situations. For this purpose, the EHG signal and obstetric databases were generated for each scenario at University and Polytechnic Hospital La Fe. The greater impulsivity and predictability in MG compared to SG during the third trimester, in addition to the significant correlation between EHGbiomarkers and foetal weight, suggested an electromechanical coupling between overdistension and surface recorded myoelectric activity. As for IOL, the successful group showed a significant increase in the number of contractions and cellular excitability, along with reduced complexity, from 2-3 hours after the IOL drug administration. No significant changes from baseline activity were observed in the failed group. Parity-based comparison reported a higher progression ratio of signal amplitude for the parous group. Myoelectric activity in vaginal postpartum was found to be more frequent and intense, in addition to exhibit a greater cellular excitability than in caesarean deliveries. Discriminatory capacity of EHGbiomarkers for early risk detection in various obstetric contexts has advanced current electrophysiological knowledge of the uterus in vivo. The translation of the EHG to clinical practice will entail the signal processing automation, culminating in the creation of generalised and robust predictive models that support clinical decision-making, improve birth planning and management, prevent maternal and foetal complications and optimise the allocation of hospital resources., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR and PID2021-124038OB-I00 and the Generalitat Valenciana (AICO/2019/220)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Contribución de congreso (ConferenceOutput)

Comparative Study of Uterine Myoelectrical Response to Labour Induction Drugs in Nulliparous and Parous Women with Different EHG Analysis Techniques

  • Díaz-Martínez, María del Alba
  • Monfort-Ortiz, Rogelio
  • Diago-Almela, Vicente José
  • Rey-Ferreira, Iria
  • Nieto-Tous, Mar
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Prats-Boluda, Gema|||0000-0002-9362-5055
[EN] Induction of labour (IOL) is one of the most widespread practices to promote the onset of labour when maternal-fetal well-being is compromised. Currently, the monitoring of this procedure in clinical practice is performed with subjective and poorly reproducible techniques such as tocography and cervical assessment, without taking into account other obstetric variables of special relevance as parity. Electrohysterography (EHG) has emerged as a promising alternative due to its usefulness and non-invasiveness. Traditionally, EHG has been characterized by analyzing the EHG-bursts (EBA) associated with uterine contractions and computing temporal, spectral and nonlinear parameters. Recent studies characterize the EHG by considering both EHG-burst and basal activity (WEWA). The first objective of this study was to discern which analysis technique presented the best performance for EHG characterization during IOL. Subsequently, differences in uterine myoelectric response to IOL drugs in nulliparous and parous women were analyzed and compared. EHG recordings were performed during the first 4 hours of IOL in 15 nulliparous and 10 parous women. EBA results showed a greater number of parameters with significant differences with their corresponding baseline ones than WEWA, as well as a greater slope in both parity groups. Parous women presented greater amplitude and more pronounced downward trends for nonlinear parameters than nulliparous, especially for Sample and Spectral Entropy, which is associated with a greater predisposition to achieve APL that is corroborated by obstetric variables. Moreover, future efforts seem necessary to study in depth the differences between parity groups in order to correctly characterize and interpret their evolution., The collaboration of the HUP La Fe has been fundamental for the development of this work. In addition, the Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, EU RTI2018- 094449-A-I00-AR) and the Generalitat Valenciana (AICO/2019/220) have supported it.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Combination of Feature Selection and Resampling Methods to Predict Preterm Birth Based on Electrohysterographic Signals from Imbalance Data

  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Diaz-Martinez, Alba
  • Diago-Almela, Vicente Jose
  • Monfort-Ortiz, Rogelio
  • Hao, Dongmei
[EN] Due to its high sensitivity, electrohysterography (EHG) has emerged as an alternative technique for predicting preterm labor. The main obstacle in designing preterm labor prediction models is the inherent preterm/term imbalance ratio, which can give rise to relatively low performance. Numerous studies obtained promising preterm labor prediction results using the synthetic minority oversampling technique. However, these studies generally overestimate mathematical models¿ real generalization capacity by generating synthetic data before splitting the dataset, leaking information between the training and testing partitions and thus reducing the complexity of the classification task. In this work, we analyzed the effect of combining feature selection and resampling methods to overcome the class imbalance problem for predicting preterm labor by EHG. We assessed undersampling, oversampling, and hybrid methods applied to the training and validation dataset during feature selection by genetic algorithm, and analyzed the resampling effect on training data after obtaining the optimized feature subset. The best strategy consisted of undersampling the majority class of the validation dataset to 1:1 during feature selection, without subsequent resampling of the training data, achieving an AUC of 94.5 ± 4.6%, average precision of 84.5 ± 11.7%, maximum F1-score of 79.6 ± 13.8%, and recall of 89.8 ± 12.1%. Our results outperformed the techniques currently used in clinical practice, suggesting the EHG could be used to predict preterm labor in clinics., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR), and by the Generalitat Valenciana (AICO/2019/220)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Uterine slow wave: directionality and changes with imminent delivery

  • Albaladejo-Belmonte, Mónica
  • Garfield, Robert E.
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
[EN] Objective. The slow wave (SW) of the electrohysterogram (EHG) may contain relevant information on the electrophysiological condition of the uterus throughout pregnancy and labor. Our aim was to assess differences in the SW as regards the imminence of labor and the directionality of uterine myoelectrical activity. Approach. The SW of the EHGwas extracted from the signals of the Icelandic 16-electrode EHG database in the bandwidth [5, 30] mHz and its power, spectral content, complexity and synchronization between the horizontal (X) and vertical (Y) directions were characterized by the root mean square (RMS), dominant frequency (domF), sample entropy (SampEn) and maximum cross-correlation (CCmax) of the signals, respectively. Significant differences between parameters at time-to-delivery (TTD) <= 7 versus>7 days and between the horizontal versus vertical directions were assessed. Main results. The SW power significantly increased in both directions as labor approached (TTD <= 7d versus>7d (mean +/- SD): RMSx = 0.12 +/- 0.10 versus 0.08 +/- 0.06 mV; RMSy = 0.12 +/- 0.09 versus 0.08 +/- 0.05mV), as well as the dominant frequency in the horizontal direction (domF(x) = 9.1 +/- 1.3 versus 8.5 +/- 1.2mHz) and the synchronization between both directions (CCmax = 0.44 +/- 0.16 versus 0.36 +/- 0.14). Furthermore, its complexity decreased in the vertical direction (SampEn(y) = 6.13 center dot 10(-2) +/- 8.7 center dot 10(-3) versus 6.50 center dot 10(-2) +/- 8.3 center dot 10(-3)), suggesting a higher cell-to-cell electrical coupling. Whereas there were no differences between the SW features in both directions in the general population, statistically significant differences were obtained between them in individuals in many cases. Significance. Our results suggest that the SW of the EHG is related to bioelectrical events in the uterus and could provide objective information to clinicians in challenging obstetric scenarios., This study was funded by Generalitat Valenciana in Programa para la promocion de I.+.D+i ACIF/2021/012, AICO/2021/126; the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Optimization of Imminent Labor Prediction Systems in Women with Threatened Preterm Labor Based on Electrohysterography

  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Pastor-Tronch, Julio
  • Monfort-Ortiz, Rogelio
  • Perales Marín, Alfredo
  • Diago, Vicente
  • Roca Prats, Alba
[EN] Preterm birth is the leading cause of death in newborns and the survivors are prone to health complications. Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy. The current methods used in clinical practice to diagnose preterm labor, the Bishop score or cervical length, have high negative predictive values but not positive ones. In this work we analyzed the performance of computationally efficient classification algorithms, based on electrohysterographic recordings (EHG), such as random forest (RF), extreme learning machine (ELM) and K-nearest neighbors (KNN) for imminent labor (<7 days) prediction in women with TPL, using the 50th or 10th-90th percentiles of temporal, spectral and nonlinear EHG parameters with and without obstetric data inputs. Two criteria were assessed for the classifier design: F1-score and sensitivity. RFF1_2 and ELMF1_2 provided the highest F1-score values in the validation dataset, (88.17 +/- 8.34% and 90.2 +/- 4.43%) with the 50th percentile of EHG and obstetric inputs. ELMF1_2 outperformed RFF1_2 in sensitivity, being similar to those of ELMSens (sensitivity optimization). The 10th-90th percentiles did not provide a significant improvement over the 50th percentile. KNN performance was highly sensitive to the input dataset, with a high generalization capability., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR); by the Generalitat Valenciana (AICO/2019/220).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Evaluation of Respiratory Muscle Activity by Means of Concentric Ring Electrodes

  • Estrada-Petrocelli, Luis
  • Torres, Abel
  • Sarlabous, Leonardo
  • Ràfols-de-Urquía, Magda
  • Jané, Raimon
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Garcia-Casado, Javier|||0000-0003-1410-2721
[EN] Surface electromyography (sEMG) can be used for the evaluation of respiratory muscle activity. Recording sEMG involves the use of surface electrodes in a bipolar configuration. However, electrocardiographic (ECG) interference and electrode orientation represent considerable drawbacks to bipolar acquisition. As an alternative, concentric ring electrodes (CREs) can be used for sEMG acquisition and offer great potential for the evaluation of respiratory muscle activity due to their enhanced spatial resolution and simple placement protocol, which does not depend on muscle fiber orientation. The aim of this work was to analyze the performance of CREs during respiratory sEMG acquisitions. Respiratory muscle sEMG was applied to the diaphragm and sternocleidomastoid muscles using a bipolar and a CRE configuration. Thirty-two subjects underwent four inspiratory load spontaneous breathing tests which was repeated after interchanging the electrode positions. We calculated parameters such as (1) spectral power and (2) median frequency during inspiration, and power ratios of inspiratory sEMG without ECG in relation to (3) basal sEMG without ECG (R-ins/noise), (4) basal sEMG with ECG (R-ins/cardio) and (5) expiratory sEMG without ECG (R-ins/exp). Spectral power, R-ins/noise and R-ins/cardio increased with the inspiratory load. Significantly higher values (p < 0.05) of R-ins/cardio and significantly higher median frequencies were obtained for CREs. R-ins/noise and R-ins/exp were higher for the bipolar configuration only in diaphragm sEMG recordings, whereas no significant differences were found in the sternocleidomastoid recordings. Our results suggest that the evaluation of respiratory muscle activity by means of sEMG can benefit from the remarkably reduced influence of cardiac activity, the enhanced detection of the shift in frequency content and the axial isotropy of CREs which facilitates its placement., This work was supported in part by the CERCA Program/Generalitat de Catalunya, in part by the Secretaria d'Universitats i Recerca de la Generalitat de Catalunya under Grant GRC 2017 SGR 01770, in part by the Spanish Grants RTI2018-098472-B-I00, RTI2018-094449-A-I00-AR (MCIU/AEI/FEDER, UE) and DPI2015-68397-R (MINECO/FEDER), and in part by the Biomedical Research Networking Centre in Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN, Instituto de Salud Carlos III/FEDER). The first author was supported by the IFARHU-SENACYT Scholarship Program from the Panama Government under Grant 270-2012-273.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Robust Characterization of the Uterine Myoelectrical Activity in Different Obstetric Scenarios

  • Mas-Cabo, Javier
  • Díaz-Martínez, María del Alba
  • Perales-Marin, Alfredo
  • Monfort-Ortiz, Rogelio
  • Roca-Prats, Alba
  • Lopez-Corral, Angel
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Prats-Boluda, Gema|||0000-0002-9362-5055
[EN] Electrohysterography (EHG) has been shown to provide relevant information on uterine activity and could be used for predicting preterm labor and identifying other maternal fetal risks. The extraction of high-quality robust features is a key factor in achieving satisfactory prediction systems from EHG. Temporal, spectral, and non-linear EHG parameters have been computed to characterize EHG signals, sometimes obtaining controversial results, especially for non-linear parameters. The goal of this work was to assess the performance of EHG parameters in identifying those robust enough for uterine electrophysiological characterization. EHG signals were picked up in different obstetric scenarios: antepartum, including women who delivered on term, labor, and post-partum. The results revealed that the 10th and 90th percentiles, for parameters with falling and rising trends as labor approaches, respectively, differentiate between these obstetric scenarios better than median analysis window values. Root-mean-square amplitude, spectral decile 3, and spectral moment ratio showed consistent tendencies for the different obstetric scenarios as well as non-linear parameters: Lempel-Ziv, sample entropy, spectral entropy, and SD1/SD2 when computed in the fast wave high bandwidth. These findings would make it possible to extract high quality and robust EHG features to improve computer-aided assessment tools for pregnancy, labor, and postpartum progress and identify maternal fetal risks., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR) and the Generalitat Valenciana (AICO/2019/220 & GV/2018/104)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Uterine myoelectrical activity as biomarker of successful induction with Dinoprostone: Influence of parity

  • Diaz-Martinez, Alba
  • Monfort-Ortiz, Rogelio
  • Nieto-Tous, Mar
  • Diago-Almela, Vicente Jose
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Garcia-Casado, Javier|||0000-0003-1410-2721
  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Prats-Boluda, Gema|||0000-0002-9362-5055
[EN] The prolonged latent phase of Induction of Labour (IOL) is associated with increased risks of maternal mortality and morbidity. Electrohysterography (EHG) has outperformed traditional clinical measures monitoring labour progress. Although parity is agreed to be of particular relevance to the success of IOL, no previous EHG¿related studies have been found in the literature. We thus aimed to identify EHG¿biomarkers to predict IOL success (active phase of labour in¿¿¿24¿h) and determine the influence of the myoelectrical response on the parity of this group. Statistically significant and sustained differences between the successful and failed groups were found from 150¿min in amplitude and non¿linear parameters, especially in Spectral Entropy and in their progression rates. In the nulliparous¿parous comparison, parous women showed statistically significantly higher amplitude progression rate. These biomarkers would therefore be useful for early detection of the risk of induction failure and would help to develop more robust and generalizable IOL success¿prediction systems., This work was supported by the Spanish Ministry of Economy and Competitiveness and the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR and PID2021-124038OB-I00). Funding for open access charge: CRUE-Universitat Politècnica de València
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Optimized Feature Subset Selection Using Genetic Algorithm for Preterm Labor Prediction Based on Electrohysterography

  • Nieto del-Amor, Félix|||0000-0003-0050-9360
  • Prats-Boluda, Gema|||0000-0002-9362-5055
  • Martínez-de-Juan, José L.|||0000-0001-9133-3123
  • Ye Lin, Yiyao|||0000-0003-2929-181X
  • Díaz-Martínez, María del Alba
  • Monfort-Ortiz, Rogelio
  • Diago-Almela, Vicente Jose
[EN] Electrohysterography (EHG) has emerged as an alternative technique to predict preterm labor, which still remains a challenge for the scientific-technical community. Based on EHG parameters, complex classification algorithms involving non-linear transformation of the input features, which clinicians found difficult to interpret, were generally used to predict preterm labor. We proposed to use genetic algorithm to identify the optimum feature subset to predict preterm labor using simple classification algorithms. A total of 203 parameters from 326 multichannel EHG recordings and obstetric data were used as input features. We designed and validated 3 base classifiers based on k-nearest neighbors, linear discriminant analysis and logistic regression, achieving F1-score of 84.63 ± 2.76%, 89.34 ± 3.5% and 86.87 ± 4.53%, respectively, for incoming new data. The results reveal that temporal, spectral and non-linear EHG parameters computed in different bandwidths from multichannel recordings provide complementary information on preterm labor prediction. We also developed an ensemble classifier that not only outperformed base classifiers but also reduced their variability, achieving an F1-score of 92.04 ± 2.97%, which is comparable with those obtained using complex classifiers. Our results suggest the feasibility of developing a preterm labor prediction system with high generalization capacity using simple easy-to-interpret classification algorithms to assist in transferring the EHG technique to clinical practice., This work was supported by the Spanish Ministry of Economy and Competitiveness, the European Regional Development Fund (MCIU/AEI/FEDER, UE RTI2018-094449-A-I00-AR) and by the Generalitat Valenciana (AICO/2019/220).