Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks

Automated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jakub Ficek, Kacper Radzikowski, Jan Krzysztof Nowak, Osamu Yoshie, Jaroslaw Walkowiak, Robert Nowak
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	sound analysis bowel sounds gastroenterology machine learning neural network deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/81992e7d88854053ab89b148fe3c6054
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:81992e7d88854053ab89b148fe3c6054
record_format	dspace
spelling	oai:doaj.org-article:81992e7d88854053ab89b148fe3c60542021-11-25T18:57:52ZAnalysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks10.3390/s212276021424-8220https://doaj.org/article/81992e7d88854053ab89b148fe3c60542021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7602https://doaj.org/toc/1424-8220Automated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome to study gastrointestinal motility and in a surgical setting. This article proposes a novel methodology for the analysis of BS using hybrid convolutional and recursive neural networks. It is one of the first methods of using deep learning to be widely explored. We have developed an experimental pipeline and evaluated our results with a new dataset collected using a device with a dedicated contact microphone. Data have been collected at night-time, which is the most interesting period from a neurogastroenterological point of view. Previous works had ignored this period and instead kept brief records only during the day. Our algorithm can detect bowel sounds with an accuracy >93%. Moreover, we have achieved a very high specificity (>97%), crucial in diagnosis. The results have been checked with a medical professional, and they successfully support clinical diagnosis. We have developed a client-server system allowing medical practitioners to upload the recordings from their patients and have them analyzed online. This system is available online. Although BS research is technologically mature, it still lacks a uniform methodology, an international forum for discussion, and an open platform for data exchange, and therefore it is not commonly used. Our server could provide a starting point for establishing a common framework in BS research.Jakub FicekKacper RadzikowskiJan Krzysztof NowakOsamu YoshieJaroslaw WalkowiakRobert NowakMDPI AGarticlesound analysisbowel soundsgastroenterologymachine learningneural networkdeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7602, p 7602 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	sound analysis bowel sounds gastroenterology machine learning neural network deep learning Chemical technology TP1-1185
spellingShingle	sound analysis bowel sounds gastroenterology machine learning neural network deep learning Chemical technology TP1-1185 Jakub Ficek Kacper Radzikowski Jan Krzysztof Nowak Osamu Yoshie Jaroslaw Walkowiak Robert Nowak Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
description	Automated bowel sound (BS) analysis methods were already well developed by the early 2000s. Accuracy of ~90% had been achieved by several teams using various analytical approaches. Clinical research on BS had revealed their high potential in the non-invasive investigation of irritable bowel syndrome to study gastrointestinal motility and in a surgical setting. This article proposes a novel methodology for the analysis of BS using hybrid convolutional and recursive neural networks. It is one of the first methods of using deep learning to be widely explored. We have developed an experimental pipeline and evaluated our results with a new dataset collected using a device with a dedicated contact microphone. Data have been collected at night-time, which is the most interesting period from a neurogastroenterological point of view. Previous works had ignored this period and instead kept brief records only during the day. Our algorithm can detect bowel sounds with an accuracy >93%. Moreover, we have achieved a very high specificity (>97%), crucial in diagnosis. The results have been checked with a medical professional, and they successfully support clinical diagnosis. We have developed a client-server system allowing medical practitioners to upload the recordings from their patients and have them analyzed online. This system is available online. Although BS research is technologically mature, it still lacks a uniform methodology, an international forum for discussion, and an open platform for data exchange, and therefore it is not commonly used. Our server could provide a starting point for establishing a common framework in BS research.
format	article
author	Jakub Ficek Kacper Radzikowski Jan Krzysztof Nowak Osamu Yoshie Jaroslaw Walkowiak Robert Nowak
author_facet	Jakub Ficek Kacper Radzikowski Jan Krzysztof Nowak Osamu Yoshie Jaroslaw Walkowiak Robert Nowak
author_sort	Jakub Ficek
title	Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
title_short	Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
title_full	Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
title_fullStr	Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
title_full_unstemmed	Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks
title_sort	analysis of gastrointestinal acoustic activity using deep neural networks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/81992e7d88854053ab89b148fe3c6054
work_keys_str_mv	AT jakubficek analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT kacperradzikowski analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT jankrzysztofnowak analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT osamuyoshie analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT jaroslawwalkowiak analysisofgastrointestinalacousticactivityusingdeepneuralnetworks AT robertnowak analysisofgastrointestinalacousticactivityusingdeepneuralnetworks
_version_	1718410472760279040

Analysis of Gastrointestinal Acoustic Activity Using Deep Neural Networks

Ejemplares similares