Cargando…
DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries
The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to develop DeepBreath : a deep learni...
Autores principales: | , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10238513/ https://www.ncbi.nlm.nih.gov/pubmed/37268730 http://dx.doi.org/10.1038/s41746-023-00838-3 |
_version_ | 1785053311005622272 |
---|---|
author | Heitmann, Julien Glangetas, Alban Doenz, Jonathan Dervaux, Juliane Shama, Deeksha M. Garcia, Daniel Hinjos Benissa, Mohamed Rida Cantais, Aymeric Perez, Alexandre Müller, Daniel Chavdarova, Tatjana Ruchonnet-Metrailler, Isabelle Siebert, Johan N. Lacroix, Laurence Jaggi, Martin Gervaix, Alain Hartley, Mary-Anne |
author_facet | Heitmann, Julien Glangetas, Alban Doenz, Jonathan Dervaux, Juliane Shama, Deeksha M. Garcia, Daniel Hinjos Benissa, Mohamed Rida Cantais, Aymeric Perez, Alexandre Müller, Daniel Chavdarova, Tatjana Ruchonnet-Metrailler, Isabelle Siebert, Johan N. Lacroix, Laurence Jaggi, Martin Gervaix, Alain Hartley, Mary-Anne |
author_sort | Heitmann, Julien |
collection | PubMed |
description | The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to develop DeepBreath : a deep learning model identifying the audible signatures of acute respiratory illness in children. It comprises a convolutional neural network followed by a logistic regression classifier, aggregating estimates on recordings from eight thoracic sites into a single prediction at the patient-level. Patients were either healthy controls (29%) or had one of three acute respiratory illnesses (71%) including pneumonia, wheezing disorders (bronchitis/asthma), and bronchiolitis). To ensure objective estimates on model generalisability, DeepBreath is trained on patients from two countries (Switzerland, Brazil), and results are reported on an internal 5-fold cross-validation as well as externally validated (extval) on three other countries (Senegal, Cameroon, Morocco). DeepBreath differentiated healthy and pathological breathing with an Area Under the Receiver-Operator Characteristic (AUROC) of 0.93 (standard deviation [SD] ± 0.01 on internal validation). Similarly promising results were obtained for pneumonia (AUROC 0.75 ± 0.10), wheezing disorders (AUROC 0.91 ± 0.03), and bronchiolitis (AUROC 0.94 ± 0.02). Extval AUROCs were 0.89, 0.74, 0.74 and 0.87 respectively. All either matched or were significant improvements on a clinical baseline model using age and respiratory rate. Temporal attention showed clear alignment between model prediction and independently annotated respiratory cycles, providing evidence that DeepBreath extracts physiologically meaningful representations. DeepBreath provides a framework for interpretable deep learning to identify the objective audio signatures of respiratory pathology. |
format | Online Article Text |
id | pubmed-10238513 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-102385132023-06-04 DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries Heitmann, Julien Glangetas, Alban Doenz, Jonathan Dervaux, Juliane Shama, Deeksha M. Garcia, Daniel Hinjos Benissa, Mohamed Rida Cantais, Aymeric Perez, Alexandre Müller, Daniel Chavdarova, Tatjana Ruchonnet-Metrailler, Isabelle Siebert, Johan N. Lacroix, Laurence Jaggi, Martin Gervaix, Alain Hartley, Mary-Anne NPJ Digit Med Article The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to develop DeepBreath : a deep learning model identifying the audible signatures of acute respiratory illness in children. It comprises a convolutional neural network followed by a logistic regression classifier, aggregating estimates on recordings from eight thoracic sites into a single prediction at the patient-level. Patients were either healthy controls (29%) or had one of three acute respiratory illnesses (71%) including pneumonia, wheezing disorders (bronchitis/asthma), and bronchiolitis). To ensure objective estimates on model generalisability, DeepBreath is trained on patients from two countries (Switzerland, Brazil), and results are reported on an internal 5-fold cross-validation as well as externally validated (extval) on three other countries (Senegal, Cameroon, Morocco). DeepBreath differentiated healthy and pathological breathing with an Area Under the Receiver-Operator Characteristic (AUROC) of 0.93 (standard deviation [SD] ± 0.01 on internal validation). Similarly promising results were obtained for pneumonia (AUROC 0.75 ± 0.10), wheezing disorders (AUROC 0.91 ± 0.03), and bronchiolitis (AUROC 0.94 ± 0.02). Extval AUROCs were 0.89, 0.74, 0.74 and 0.87 respectively. All either matched or were significant improvements on a clinical baseline model using age and respiratory rate. Temporal attention showed clear alignment between model prediction and independently annotated respiratory cycles, providing evidence that DeepBreath extracts physiologically meaningful representations. DeepBreath provides a framework for interpretable deep learning to identify the objective audio signatures of respiratory pathology. Nature Publishing Group UK 2023-06-02 /pmc/articles/PMC10238513/ /pubmed/37268730 http://dx.doi.org/10.1038/s41746-023-00838-3 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Heitmann, Julien Glangetas, Alban Doenz, Jonathan Dervaux, Juliane Shama, Deeksha M. Garcia, Daniel Hinjos Benissa, Mohamed Rida Cantais, Aymeric Perez, Alexandre Müller, Daniel Chavdarova, Tatjana Ruchonnet-Metrailler, Isabelle Siebert, Johan N. Lacroix, Laurence Jaggi, Martin Gervaix, Alain Hartley, Mary-Anne DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
title | DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
title_full | DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
title_fullStr | DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
title_full_unstemmed | DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
title_short | DeepBreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
title_sort | deepbreath—automated detection of respiratory pathology from lung auscultation in 572 pediatric outpatients across 5 countries |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10238513/ https://www.ncbi.nlm.nih.gov/pubmed/37268730 http://dx.doi.org/10.1038/s41746-023-00838-3 |
work_keys_str_mv | AT heitmannjulien deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT glangetasalban deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT doenzjonathan deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT dervauxjuliane deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT shamadeeksham deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT garciadanielhinjos deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT benissamohamedrida deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT cantaisaymeric deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT perezalexandre deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT mullerdaniel deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT chavdarovatatjana deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT ruchonnetmetraillerisabelle deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT siebertjohann deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT lacroixlaurence deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT jaggimartin deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT gervaixalain deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT hartleymaryanne deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries AT deepbreathautomateddetectionofrespiratorypathologyfromlungauscultationin572pediatricoutpatientsacross5countries |