Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients

Background: Effective and reliable monitoring of asthma at home is a relevant factor that may reduce the need to consult a doctor in person.Aim: We analyzed the possibility to determine intensities of pathological breath phenomena based on artificial intelligence (AI) analysis of sounds recorded dur...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Honorata Hafke-Dys, Barbara Kuźnar-Kamińska, Tomasz Grzywalski, Adam Maciaszek, Krzysztof Szarzyński, Jędrzej Kociński
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	asthma monitoring auscultation rhonchi wheezes stethoscope Physiology QP1-981
Acceso en línea:	https://doaj.org/article/91a5abcb5e0a496291bac5f6c0f4b45c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:91a5abcb5e0a496291bac5f6c0f4b45c
record_format	dspace
spelling	oai:doaj.org-article:91a5abcb5e0a496291bac5f6c0f4b45c2021-11-11T10:26:26ZArtificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients1664-042X10.3389/fphys.2021.745635https://doaj.org/article/91a5abcb5e0a496291bac5f6c0f4b45c2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fphys.2021.745635/fullhttps://doaj.org/toc/1664-042XBackground: Effective and reliable monitoring of asthma at home is a relevant factor that may reduce the need to consult a doctor in person.Aim: We analyzed the possibility to determine intensities of pathological breath phenomena based on artificial intelligence (AI) analysis of sounds recorded during standard stethoscope auscultation.Methods: The evaluation set comprising 1,043 auscultation examinations (9,319 recordings) was collected from 899 patients. Examinations were assigned to one of four groups: asthma with and without abnormal sounds (AA and AN, respectively), no-asthma with and without abnormal sounds (NA and NN, respectively). Presence of abnormal sounds was evaluated by a panel of 3 physicians that were blinded to the AI predictions. AI was trained on an independent set of 9,847 recordings to determine intensity scores (indexes) of wheezes, rhonchi, fine and coarse crackles and their combinations: continuous phenomena (wheezes + rhonchi) and all phenomena. The pair-comparison of groups of examinations based on Area Under ROC-Curve (AUC) was used to evaluate the performance of each index in discrimination between groups.Results: Best performance in separation between AA and AN was observed with Continuous Phenomena Index (AUC 0.94) while for NN and NA. All Phenomena Index (AUC 0.91) showed the best performance. AA showed slightly higher prevalence of wheezes compared to NA.Conclusions: The results showed a high efficiency of the AI to discriminate between the asthma patients with normal and abnormal sounds, thus this approach has a great potential and can be used to monitor asthma symptoms at home.Honorata Hafke-DysHonorata Hafke-DysBarbara Kuźnar-KamińskaTomasz GrzywalskiAdam MaciaszekKrzysztof SzarzyńskiJędrzej KocińskiJędrzej KocińskiFrontiers Media S.A.articleasthmamonitoringauscultationrhonchiwheezesstethoscopePhysiologyQP1-981ENFrontiers in Physiology, Vol 12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	asthma monitoring auscultation rhonchi wheezes stethoscope Physiology QP1-981
spellingShingle	asthma monitoring auscultation rhonchi wheezes stethoscope Physiology QP1-981 Honorata Hafke-Dys Honorata Hafke-Dys Barbara Kuźnar-Kamińska Tomasz Grzywalski Adam Maciaszek Krzysztof Szarzyński Jędrzej Kociński Jędrzej Kociński Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients
description	Background: Effective and reliable monitoring of asthma at home is a relevant factor that may reduce the need to consult a doctor in person.Aim: We analyzed the possibility to determine intensities of pathological breath phenomena based on artificial intelligence (AI) analysis of sounds recorded during standard stethoscope auscultation.Methods: The evaluation set comprising 1,043 auscultation examinations (9,319 recordings) was collected from 899 patients. Examinations were assigned to one of four groups: asthma with and without abnormal sounds (AA and AN, respectively), no-asthma with and without abnormal sounds (NA and NN, respectively). Presence of abnormal sounds was evaluated by a panel of 3 physicians that were blinded to the AI predictions. AI was trained on an independent set of 9,847 recordings to determine intensity scores (indexes) of wheezes, rhonchi, fine and coarse crackles and their combinations: continuous phenomena (wheezes + rhonchi) and all phenomena. The pair-comparison of groups of examinations based on Area Under ROC-Curve (AUC) was used to evaluate the performance of each index in discrimination between groups.Results: Best performance in separation between AA and AN was observed with Continuous Phenomena Index (AUC 0.94) while for NN and NA. All Phenomena Index (AUC 0.91) showed the best performance. AA showed slightly higher prevalence of wheezes compared to NA.Conclusions: The results showed a high efficiency of the AI to discriminate between the asthma patients with normal and abnormal sounds, thus this approach has a great potential and can be used to monitor asthma symptoms at home.
format	article
author	Honorata Hafke-Dys Honorata Hafke-Dys Barbara Kuźnar-Kamińska Tomasz Grzywalski Adam Maciaszek Krzysztof Szarzyński Jędrzej Kociński Jędrzej Kociński
author_facet	Honorata Hafke-Dys Honorata Hafke-Dys Barbara Kuźnar-Kamińska Tomasz Grzywalski Adam Maciaszek Krzysztof Szarzyński Jędrzej Kociński Jędrzej Kociński
author_sort	Honorata Hafke-Dys
title	Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients
title_short	Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients
title_full	Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients
title_fullStr	Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients
title_full_unstemmed	Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients
title_sort	artificial intelligence approach to the monitoring of respiratory sounds in asthmatic patients
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/91a5abcb5e0a496291bac5f6c0f4b45c
work_keys_str_mv	AT honoratahafkedys artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT honoratahafkedys artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT barbarakuznarkaminska artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT tomaszgrzywalski artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT adammaciaszek artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT krzysztofszarzynski artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT jedrzejkocinski artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients AT jedrzejkocinski artificialintelligenceapproachtothemonitoringofrespiratorysoundsinasthmaticpatients
_version_	1718439148945145856

Artificial Intelligence Approach to the Monitoring of Respiratory Sounds in Asthmatic Patients

Ejemplares similares