Leveraging synthetic data to develop a machine learning model for voiding Flow rate prediction from audio signals

Vista sencilla de ítem
dc.contributor.authorÁlvarez Arteaga, Marcos Lázaro
dc.contributor.authorBahillo, Alfonso
dc.contributor.authorArjona Aguilera, Laura
dc.contributor.authorNogueira, Diogo Marcelo
dc.contributor.authorGomes, Elsa Ferreira
dc.contributor.authorJorge, Alípio
dc.date.accessioned2026-01-09T09:43:47Z
dc.date.available2026-01-09T09:43:47Z
dc.date.issued2025-07-18
dc.date.updated2026-01-09T09:43:47Z
dc.description.abstractSound-based uroflowmetry (SU) is a non-invasive technique emerging as an alternative to traditional uroflowmetry (UF) to calculate the voiding flow rate based on the sound generated by the urine impacting the water in a toilet, enabling remote monitoring and reducing the patient burden and clinical costs. This study trains four different machine learning (ML) models (random forest, gradient boosting, support vector machine and convolutional neural network) using both regression and classification approaches to predict and categorize the voiding flow rate from sound events. The models were trained with a dataset that contains sounds from synthetic void events generated with a high precision peristaltic pump and a traditional toilet. Sound was simultaneously recorded with three devices: Ultramic384k, Mi A1 smartphone and Oppo Smartwatch. To extract the audio features, our analysis showed that segmenting the audio signals into 1000 ms segments with frequencies up to 16 kHz provided the best results. Results show that random forest achieved the best performance in both regression and classification tasks, with a mean absolute error (MAE) of 0.9, 0.7 and 0.9 ml/s and quadratic weighted kappa (QWK) of 0.99, 1.0 and 1.0 for the three devices. To evaluate the models in a real environment and assess the effectiveness of training with synthetic data, the best-performing models were retrained and validated using a real voiding sounds dataset. The results reported an MAE below 2.5 ml/s and a QWK above 0.86 for regression and classification tasks, respectively.en
dc.description.sponsorshipThis work was supported in part by the Spanish Ministry of Science, Innovation and Universities (MICIU) through the SWALU Project under Grant CPP2022-010045; in part by the 2020 ‘‘Ayuda para contratos predoctorales,’’ funded by MICIU and the State Research Agency Agencia Estatal de Investigación (AEI), 10.13039/501100011033, and co-financed by the European Social Fund Fondo Social Europeo (FSE) under the slogan ‘‘FSE invierte en tu futuro,’’ under Grant PRE2020-095612; in part by the Basque Government through the Hazitek Program under the BATHMIC Project, Grant ZL-2024/00481; and in part by the Ministry through the Aginplace Project, funded by MICIU, AEI (10.13039/501100011033), and the European Union (UE) through the European Regional Development Fund Fondo Europeo de Desarrollo Regional (FEDER), under Grants PID2023-146254OB-C41 and PID2023-146254OA-C44en
dc.identifier.citationAlvarez, M. L., Bahillo, A., Arjona, L., Marcelo Nogueira, D., Ferreira Gomes, E., & Jorge, A. M. (2025). Leveraging synthetic data to develop a machine learning model for voiding Flow rate prediction from audio signals. IEEE Access, 13, 127240-127251. https://doi.org/10.1109/ACCESS.2025.3590626
dc.identifier.doi10.1109/ACCESS.2025.3590626
dc.identifier.eissn2169-3536
dc.identifier.urihttps://hdl.handle.net/20.500.14454/4654
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.rights© 2025 The Authors
dc.subject.otherMachine learning
dc.subject.otherNon-invasive voiding monitoring
dc.subject.otherSound voiding signals
dc.subject.otherSound-based uroflowmetry
dc.subject.otherVoiding flow estimation
dc.titleLeveraging synthetic data to develop a machine learning model for voiding Flow rate prediction from audio signalsen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.endPage127251
oaire.citation.startPage127240
oaire.citation.titleIEEE Access
oaire.citation.volume13
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
alvarez_leveraging_2025.pdf
Tamaño:
1.64 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos