Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/39543 |
Resumo: | In recent years, computerized methods for analyzing respiratory function have gained increased attention within the scientific community. This study proposes a deep-learning model to estimate the dimensionless respiratory airflow using only respiratory sound without prior calibration. We developed hybrid deep learning models (CNN + LSTM) to extract features from the respiratory sound and model their temporal dependencies. Then, we used an ensemble approach to combine multiple outputs of our models and obtain the respiratory airflow waveform for entire respiratory audio signals as the final output. We conducted a comprehensive set of experiments and evaluated the models using several regression evaluation metrics to assess how the models would perform in various circumstances of different complexity. The methods were developed and evaluated considering respiratory sound and electrical impedance tomography (EIT) data from 50 respiratory patients (15 female and 35 male with an average age of 67.4 ± 8.9 years and body mass index of 27.8 ± 5.6 ). An external assessment was conducted using an external database, the Respiratory Sound Database (RSD). This was an indirect evaluation because the RSD does not provide the ground truth values of the dimensionless respiratory airflow. In the most complex evaluation task (Task II), we achieved the following results for the estimation of the normalized dimensionless respiratory airflow curve: mean absolute error = 0.134 ± 0.061; root mean squared error = 0.170 ± 0.075; dynamic time warping similarity = 3.282 ± 1.514; Pearson correlation coefficient = 0.770 ± 0.235. External assessment with the RSD showed that the performance of our model decreased when devices different from the ones used for their training were considered. Our study demonstrated that deep learning models could reliably estimate the dimensionless respiratory airflow. |
id |
RCAP_9cba247caf7adf1c82bb1a2efdb5f74c |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/39543 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory soundRespiratory sound analysisElectrical impedance tomographyDimensionless respiratory airflowFlow–sound relationshipAcoustical airflow estimationIn recent years, computerized methods for analyzing respiratory function have gained increased attention within the scientific community. This study proposes a deep-learning model to estimate the dimensionless respiratory airflow using only respiratory sound without prior calibration. We developed hybrid deep learning models (CNN + LSTM) to extract features from the respiratory sound and model their temporal dependencies. Then, we used an ensemble approach to combine multiple outputs of our models and obtain the respiratory airflow waveform for entire respiratory audio signals as the final output. We conducted a comprehensive set of experiments and evaluated the models using several regression evaluation metrics to assess how the models would perform in various circumstances of different complexity. The methods were developed and evaluated considering respiratory sound and electrical impedance tomography (EIT) data from 50 respiratory patients (15 female and 35 male with an average age of 67.4 ± 8.9 years and body mass index of 27.8 ± 5.6 ). An external assessment was conducted using an external database, the Respiratory Sound Database (RSD). This was an indirect evaluation because the RSD does not provide the ground truth values of the dimensionless respiratory airflow. In the most complex evaluation task (Task II), we achieved the following results for the estimation of the normalized dimensionless respiratory airflow curve: mean absolute error = 0.134 ± 0.061; root mean squared error = 0.170 ± 0.075; dynamic time warping similarity = 3.282 ± 1.514; Pearson correlation coefficient = 0.770 ± 0.235. External assessment with the RSD showed that the performance of our model decreased when devices different from the ones used for their training were considered. Our study demonstrated that deep learning models could reliably estimate the dimensionless respiratory airflow.Elsevier2023-10-17T16:37:15Z2024-01-01T00:00:00Z2024-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10773/39543eng1746-809410.1016/j.bspc.2023.105451Pessoa, DiogoRocha, Bruno MachadoGomes, MariaRodrigues, GuilhermePetmezas, GeorgiosCheimariotis, Grigorios-ArisMaglaveras, NicosMarques, AldaFrerichs, InézCarvalho, Paulo dePaiva, Rui Pedroinfo: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:RCAAP2024-02-22T12:17:20Zoai:ria.ua.pt:10773/39543Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:09:44.459305Repositório 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 |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
title |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
spellingShingle |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound Pessoa, Diogo Respiratory sound analysis Electrical impedance tomography Dimensionless respiratory airflow Flow–sound relationship Acoustical airflow estimation |
title_short |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
title_full |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
title_fullStr |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
title_full_unstemmed |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
title_sort |
Ensemble deep learning model for dimensionless respiratory airflow estimation using respiratory sound |
author |
Pessoa, Diogo |
author_facet |
Pessoa, Diogo Rocha, Bruno Machado Gomes, Maria Rodrigues, Guilherme Petmezas, Georgios Cheimariotis, Grigorios-Aris Maglaveras, Nicos Marques, Alda Frerichs, Inéz Carvalho, Paulo de Paiva, Rui Pedro |
author_role |
author |
author2 |
Rocha, Bruno Machado Gomes, Maria Rodrigues, Guilherme Petmezas, Georgios Cheimariotis, Grigorios-Aris Maglaveras, Nicos Marques, Alda Frerichs, Inéz Carvalho, Paulo de Paiva, Rui Pedro |
author2_role |
author author author author author author author author author author |
dc.contributor.author.fl_str_mv |
Pessoa, Diogo Rocha, Bruno Machado Gomes, Maria Rodrigues, Guilherme Petmezas, Georgios Cheimariotis, Grigorios-Aris Maglaveras, Nicos Marques, Alda Frerichs, Inéz Carvalho, Paulo de Paiva, Rui Pedro |
dc.subject.por.fl_str_mv |
Respiratory sound analysis Electrical impedance tomography Dimensionless respiratory airflow Flow–sound relationship Acoustical airflow estimation |
topic |
Respiratory sound analysis Electrical impedance tomography Dimensionless respiratory airflow Flow–sound relationship Acoustical airflow estimation |
description |
In recent years, computerized methods for analyzing respiratory function have gained increased attention within the scientific community. This study proposes a deep-learning model to estimate the dimensionless respiratory airflow using only respiratory sound without prior calibration. We developed hybrid deep learning models (CNN + LSTM) to extract features from the respiratory sound and model their temporal dependencies. Then, we used an ensemble approach to combine multiple outputs of our models and obtain the respiratory airflow waveform for entire respiratory audio signals as the final output. We conducted a comprehensive set of experiments and evaluated the models using several regression evaluation metrics to assess how the models would perform in various circumstances of different complexity. The methods were developed and evaluated considering respiratory sound and electrical impedance tomography (EIT) data from 50 respiratory patients (15 female and 35 male with an average age of 67.4 ± 8.9 years and body mass index of 27.8 ± 5.6 ). An external assessment was conducted using an external database, the Respiratory Sound Database (RSD). This was an indirect evaluation because the RSD does not provide the ground truth values of the dimensionless respiratory airflow. In the most complex evaluation task (Task II), we achieved the following results for the estimation of the normalized dimensionless respiratory airflow curve: mean absolute error = 0.134 ± 0.061; root mean squared error = 0.170 ± 0.075; dynamic time warping similarity = 3.282 ± 1.514; Pearson correlation coefficient = 0.770 ± 0.235. External assessment with the RSD showed that the performance of our model decreased when devices different from the ones used for their training were considered. Our study demonstrated that deep learning models could reliably estimate the dimensionless respiratory airflow. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-10-17T16:37:15Z 2024-01-01T00:00:00Z 2024-01 |
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/10773/39543 |
url |
http://hdl.handle.net/10773/39543 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1746-8094 10.1016/j.bspc.2023.105451 |
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.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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_ |
1799137747805405184 |