- -

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

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

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

Mostrar el registro sencillo del ítem

Ficheros en el ítem

dc.contributor.author Nieto del-Amor, Félix es_ES
dc.contributor.author Prats-Boluda, Gema es_ES
dc.contributor.author Garcia-Casado, Javier es_ES
dc.contributor.author Diaz-Martinez, Alba es_ES
dc.contributor.author Diago-Almela, Vicente Jose es_ES
dc.contributor.author Monfort-Ortiz, Rogelio es_ES
dc.contributor.author Hao, Dongmei es_ES
dc.contributor.author Ye Lin, Yiyao es_ES
dc.date.accessioned 2023-01-19T19:01:05Z
dc.date.available 2023-01-19T19:01:05Z
dc.date.issued 2022-07-07 es_ES
dc.identifier.uri http://hdl.handle.net/10251/191405
dc.description.abstract [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. es_ES
dc.description.sponsorship 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) es_ES
dc.language Inglés es_ES
dc.publisher MDPI AG es_ES
dc.relation.ispartof Sensors es_ES
dc.rights Reconocimiento (by) es_ES
dc.subject Genetic algorithm es_ES
dc.subject Imbalance data learning es_ES
dc.subject Electrohysterography es_ES
dc.subject Preterm labor prediction es_ES
dc.subject Resampling methods es_ES
dc.subject Uterine electromyography es_ES
dc.subject Machine learning es_ES
dc.subject.classification TECNOLOGIA ELECTRONICA es_ES
dc.title Combination of Feature Selection and Resampling Methods to Predict Preterm Birth Based on Electrohysterographic Signals from Imbalance Data es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.3390/s22145098 es_ES
dc.relation.projectID info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-094449-A-I00/ES/ELECTROHISTEROGRAFIA PARA LA MEJORA EN LA TOMA DE DECISIONES EN SITUACIONES DE RIESGO EN OBSTETRICIA: PARTO PREMATURO E INDUCCION DEL PARTO/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GENERALITAT VALENCIANA//AICO%2F2019%2F220//DESARROLLO DE HERRAMIENTAS DE USO CLINICO PARA LA PREDICCION DEL PARTO PREMATURO EN BASE A LA ELECTROHISTEROGRAFIA/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escuela Técnica Superior de Ingenieros Industriales - Escola Tècnica Superior d'Enginyers Industrials es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escuela Técnica Superior de Ingeniería del Diseño - Escola Tècnica Superior d'Enginyeria del Disseny es_ES
dc.description.bibliographicCitation Nieto Del-Amor, F.; Prats-Boluda, G.; Garcia-Casado, J.; Diaz-Martinez, A.; Diago-Almela, VJ.; Monfort-Ortiz, R.; Hao, D.... (2022). Combination of Feature Selection and Resampling Methods to Predict Preterm Birth Based on Electrohysterographic Signals from Imbalance Data. Sensors. 22(14):1-18. https://doi.org/10.3390/s22145098 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion https://doi.org/10.3390/s22145098 es_ES
dc.description.upvformatpinicio 1 es_ES
dc.description.upvformatpfin 18 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 22 es_ES
dc.description.issue 14 es_ES
dc.identifier.eissn 1424-8220 es_ES
dc.identifier.pmid 35890778 es_ES
dc.identifier.pmcid PMC9319575 es_ES
dc.relation.pasarela S\469903 es_ES
dc.contributor.funder GENERALITAT VALENCIANA es_ES
dc.contributor.funder AGENCIA ESTATAL DE INVESTIGACION es_ES
dc.subject.ods 03.- Garantizar una vida saludable y promover el bienestar para todos y todas en todas las edades es_ES
dc.subject.ods 10.- Reducir las desigualdades entre países y dentro de ellos es_ES
upv.costeAPC 2100 es_ES


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem