Cargando…

Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform

BACKGROUND: Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this...

Descripción completa

Detalles Bibliográficos
Autores principales: Chorba, John S., Shapiro, Avi M., Le, Le, Maidens, John, Prince, John, Pham, Steve, Kanzawa, Mia M., Barbosa, Daniel N., Currie, Caroline, Brooks, Catherine, White, Brent E., Huskin, Anna, Paek, Jason, Geocaris, Jack, Elnathan, Dinatu, Ronquillo, Ria, Kim, Roy, Alam, Zenith H., Mahadevan, Vaikom S., Fuller, Sophie G., Stalker, Grant W., Bravo, Sara A., Jean, Dina, Lee, John J., Gjergjindreaj, Medeona, Mihos, Christos G., Forman, Steven T., Venkatraman, Subramaniam, McCarthy, Patrick M., Thomas, James D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8200722/
https://www.ncbi.nlm.nih.gov/pubmed/33899504
http://dx.doi.org/10.1161/JAHA.120.019905
_version_ 1783707667283312640
author Chorba, John S.
Shapiro, Avi M.
Le, Le
Maidens, John
Prince, John
Pham, Steve
Kanzawa, Mia M.
Barbosa, Daniel N.
Currie, Caroline
Brooks, Catherine
White, Brent E.
Huskin, Anna
Paek, Jason
Geocaris, Jack
Elnathan, Dinatu
Ronquillo, Ria
Kim, Roy
Alam, Zenith H.
Mahadevan, Vaikom S.
Fuller, Sophie G.
Stalker, Grant W.
Bravo, Sara A.
Jean, Dina
Lee, John J.
Gjergjindreaj, Medeona
Mihos, Christos G.
Forman, Steven T.
Venkatraman, Subramaniam
McCarthy, Patrick M.
Thomas, James D.
author_facet Chorba, John S.
Shapiro, Avi M.
Le, Le
Maidens, John
Prince, John
Pham, Steve
Kanzawa, Mia M.
Barbosa, Daniel N.
Currie, Caroline
Brooks, Catherine
White, Brent E.
Huskin, Anna
Paek, Jason
Geocaris, Jack
Elnathan, Dinatu
Ronquillo, Ria
Kim, Roy
Alam, Zenith H.
Mahadevan, Vaikom S.
Fuller, Sophie G.
Stalker, Grant W.
Bravo, Sara A.
Jean, Dina
Lee, John J.
Gjergjindreaj, Medeona
Mihos, Christos G.
Forman, Steven T.
Venkatraman, Subramaniam
McCarthy, Patrick M.
Thomas, James D.
author_sort Chorba, John S.
collection PubMed
description BACKGROUND: Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. METHODS AND RESULTS: Using >34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 962 patients in a clinical study and collected recordings at the 4 primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by 3 expert cardiologists. Algorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1 intensity, sensitivity increased to 90.0%. Application of the algorithm at the appropriate anatomic auscultation location detected moderate‐to‐severe or greater aortic stenosis, with sensitivity of 93.2% and specificity of 86.0%, and moderate‐to‐severe or greater mitral regurgitation, with sensitivity of 66.2% and specificity of 94.6%. CONCLUSIONS: The deep learning algorithm’s ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists based on the annotated subset of our database. The findings suggest that such algorithms would have utility as front‐line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease. REGISTRATION: URL: https://clinicaltrials.gov; Unique Identifier: NCT03458806.
format Online
Article
Text
id pubmed-8200722
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-82007222021-06-15 Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform Chorba, John S. Shapiro, Avi M. Le, Le Maidens, John Prince, John Pham, Steve Kanzawa, Mia M. Barbosa, Daniel N. Currie, Caroline Brooks, Catherine White, Brent E. Huskin, Anna Paek, Jason Geocaris, Jack Elnathan, Dinatu Ronquillo, Ria Kim, Roy Alam, Zenith H. Mahadevan, Vaikom S. Fuller, Sophie G. Stalker, Grant W. Bravo, Sara A. Jean, Dina Lee, John J. Gjergjindreaj, Medeona Mihos, Christos G. Forman, Steven T. Venkatraman, Subramaniam McCarthy, Patrick M. Thomas, James D. J Am Heart Assoc Original Research BACKGROUND: Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. METHODS AND RESULTS: Using >34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 962 patients in a clinical study and collected recordings at the 4 primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by 3 expert cardiologists. Algorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1 intensity, sensitivity increased to 90.0%. Application of the algorithm at the appropriate anatomic auscultation location detected moderate‐to‐severe or greater aortic stenosis, with sensitivity of 93.2% and specificity of 86.0%, and moderate‐to‐severe or greater mitral regurgitation, with sensitivity of 66.2% and specificity of 94.6%. CONCLUSIONS: The deep learning algorithm’s ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists based on the annotated subset of our database. The findings suggest that such algorithms would have utility as front‐line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease. REGISTRATION: URL: https://clinicaltrials.gov; Unique Identifier: NCT03458806. John Wiley and Sons Inc. 2021-04-26 /pmc/articles/PMC8200722/ /pubmed/33899504 http://dx.doi.org/10.1161/JAHA.120.019905 Text en © 2021 The Authors and Eko Devices, Inc. Published on behalf of the American Heart Association, Inc., by Wiley. https://creativecommons.org/licenses/by-nc/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc/4.0/ (https://creativecommons.org/licenses/by-nc/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
spellingShingle Original Research
Chorba, John S.
Shapiro, Avi M.
Le, Le
Maidens, John
Prince, John
Pham, Steve
Kanzawa, Mia M.
Barbosa, Daniel N.
Currie, Caroline
Brooks, Catherine
White, Brent E.
Huskin, Anna
Paek, Jason
Geocaris, Jack
Elnathan, Dinatu
Ronquillo, Ria
Kim, Roy
Alam, Zenith H.
Mahadevan, Vaikom S.
Fuller, Sophie G.
Stalker, Grant W.
Bravo, Sara A.
Jean, Dina
Lee, John J.
Gjergjindreaj, Medeona
Mihos, Christos G.
Forman, Steven T.
Venkatraman, Subramaniam
McCarthy, Patrick M.
Thomas, James D.
Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform
title Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform
title_full Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform
title_fullStr Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform
title_full_unstemmed Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform
title_short Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform
title_sort deep learning algorithm for automated cardiac murmur detection via a digital stethoscope platform
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8200722/
https://www.ncbi.nlm.nih.gov/pubmed/33899504
http://dx.doi.org/10.1161/JAHA.120.019905
work_keys_str_mv AT chorbajohns deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT shapiroavim deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT lele deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT maidensjohn deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT princejohn deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT phamsteve deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT kanzawamiam deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT barbosadanieln deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT curriecaroline deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT brookscatherine deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT whitebrente deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT huskinanna deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT paekjason deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT geocarisjack deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT elnathandinatu deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT ronquilloria deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT kimroy deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT alamzenithh deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT mahadevanvaikoms deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT fullersophieg deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT stalkergrantw deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT bravosaraa deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT jeandina deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT leejohnj deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT gjergjindreajmedeona deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT mihoschristosg deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT formanstevent deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT venkatramansubramaniam deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT mccarthypatrickm deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform
AT thomasjamesd deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform