Clinically Relevant Sound-based Features in COVID-19 Identification

Detalhes bibliográficos
Autor(a) principal: Matias, Pedro
Data de Publicação: 2022
Outros Autores: Costa, Joao, Carreiro, Andre V., Gamboa, Hugo, Sousa, Ines, Gomez, Pedro, Sousa, Joana, Neuparth, N, Carreiro-Martins, Pedro, Soares, Filipe
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/144963
Resumo: Publisher Copyright: Author
id RCAP_0e1982391d0d874f83012e3c71f5a8b1
oai_identifier_str oai:run.unl.pt:10362/144963
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Clinically Relevant Sound-based Features in COVID-19 IdentificationRobustness Assessment with a Data-Centric Machine Learning PipelineCOVID-19data-centricDatabasesFeature extractionfeature extractionLarynxLungsmachine learningMachine learningPandemicsRespiratory systemsignal processingSignal processingspeechSpeech recognitionvocal tractComputer Science(all)Materials Science(all)Engineering(all)Electrical and Electronic EngineeringPublisher Copyright: AuthorAs long as the COVID-19 pandemic is still active in most countries worldwide, rapid diagnostic continues to be crucial to mitigate the impact of seasonal infection waves. Commercialized rapid antigen self-tests proved they cannot handle the most demanding periods, lacking availability and leading to cost rises. Thus, developing a non-invasive, costless, and more decentralized technology capable of giving people feedback about the COVID-19 infection probability would fill these gaps. This paper explores a sound-based analysis of vocal and respiratory audio data to achieve that objective. This work presents a modular data-centric Machine Learning pipeline for COVID-19 identification from voice and respiratory audio samples. Signals are processed to extract and classify relevant segments that contain informative events, such as coughing or breathing. Temporal, amplitude, spectral, cepstral, and phonetic features are extracted from audio along with available metadata for COVID-19 identification. Audio augmentation and data balancing techniques are used to mitigate class disproportionality. The open-access Coswara and COVID-19 Sounds datasets were used to test the performance of the proposed architecture. Obtained sensitivity scores ranged from 60.00% to 80.00% in Coswara and from 51.43% to 77.14% in COVID-19 Sounds. Although previous works report higher accuracy on COVID-19 detection, this research focused on a data-centric approach by validating the quality of the samples, segmenting the speech events, and exploring interpretable features with physiological meaning. As the pandemic evolves, its lessons must endure, and pipelines such as the proposed one will help prepare new stages where quick and easy disease identification is essential.LIBPhys-UNLFaculdade de Ciências e Tecnologia (FCT)NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)Comprehensive Health Research Centre (CHRC) - pólo NMSRUNMatias, PedroCosta, JoaoCarreiro, Andre V.Gamboa, HugoSousa, InesGomez, PedroSousa, JoanaNeuparth, NCarreiro-Martins, PedroSoares, Filipe2022-10-24T22:13:42Z2022-10-032022-10-03T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10362/144963eng2169-3536PURE: 47286236https://doi.org/10.1109/ACCESS.2022.3211295info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:24:58Zoai:run.unl.pt:10362/144963Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:51:50.268115Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Clinically Relevant Sound-based Features in COVID-19 Identification
Robustness Assessment with a Data-Centric Machine Learning Pipeline
title Clinically Relevant Sound-based Features in COVID-19 Identification
spellingShingle Clinically Relevant Sound-based Features in COVID-19 Identification
Matias, Pedro
COVID-19
data-centric
Databases
Feature extraction
feature extraction
Larynx
Lungs
machine learning
Machine learning
Pandemics
Respiratory system
signal processing
Signal processing
speech
Speech recognition
vocal tract
Computer Science(all)
Materials Science(all)
Engineering(all)
Electrical and Electronic Engineering
title_short Clinically Relevant Sound-based Features in COVID-19 Identification
title_full Clinically Relevant Sound-based Features in COVID-19 Identification
title_fullStr Clinically Relevant Sound-based Features in COVID-19 Identification
title_full_unstemmed Clinically Relevant Sound-based Features in COVID-19 Identification
title_sort Clinically Relevant Sound-based Features in COVID-19 Identification
author Matias, Pedro
author_facet Matias, Pedro
Costa, Joao
Carreiro, Andre V.
Gamboa, Hugo
Sousa, Ines
Gomez, Pedro
Sousa, Joana
Neuparth, N
Carreiro-Martins, Pedro
Soares, Filipe
author_role author
author2 Costa, Joao
Carreiro, Andre V.
Gamboa, Hugo
Sousa, Ines
Gomez, Pedro
Sousa, Joana
Neuparth, N
Carreiro-Martins, Pedro
Soares, Filipe
author2_role author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv LIBPhys-UNL
Faculdade de Ciências e Tecnologia (FCT)
NOVA Medical School|Faculdade de Ciências Médicas (NMS|FCM)
Comprehensive Health Research Centre (CHRC) - pólo NMS
RUN
dc.contributor.author.fl_str_mv Matias, Pedro
Costa, Joao
Carreiro, Andre V.
Gamboa, Hugo
Sousa, Ines
Gomez, Pedro
Sousa, Joana
Neuparth, N
Carreiro-Martins, Pedro
Soares, Filipe
dc.subject.por.fl_str_mv COVID-19
data-centric
Databases
Feature extraction
feature extraction
Larynx
Lungs
machine learning
Machine learning
Pandemics
Respiratory system
signal processing
Signal processing
speech
Speech recognition
vocal tract
Computer Science(all)
Materials Science(all)
Engineering(all)
Electrical and Electronic Engineering
topic COVID-19
data-centric
Databases
Feature extraction
feature extraction
Larynx
Lungs
machine learning
Machine learning
Pandemics
Respiratory system
signal processing
Signal processing
speech
Speech recognition
vocal tract
Computer Science(all)
Materials Science(all)
Engineering(all)
Electrical and Electronic Engineering
description Publisher Copyright: Author
publishDate 2022
dc.date.none.fl_str_mv 2022-10-24T22:13:42Z
2022-10-03
2022-10-03T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/144963
url http://hdl.handle.net/10362/144963
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2169-3536
PURE: 47286236
https://doi.org/10.1109/ACCESS.2022.3211295
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138110966071296

Registros relacionados