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...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-05-01
|
| Series: | Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease |
| Subjects: | |
| Online Access: | https://www.ahajournals.org/doi/10.1161/JAHA.120.019905 |
| _version_ | 1811332298055876608 |
|---|---|
| author | John S. Chorba Avi M. Shapiro Le Le John Maidens John Prince Steve Pham Mia M. Kanzawa Daniel N. Barbosa Caroline Currie Catherine Brooks Brent E. White Anna Huskin Jason Paek Jack Geocaris Dinatu Elnathan Ria Ronquillo Roy Kim Zenith H. Alam Vaikom S. Mahadevan Sophie G. Fuller Grant W. Stalker Sara A. Bravo Dina Jean John J. Lee Medeona Gjergjindreaj Christos G. Mihos Steven T. Forman Subramaniam Venkatraman Patrick M. McCarthy James D. Thomas |
| author_facet | John S. Chorba Avi M. Shapiro Le Le John Maidens John Prince Steve Pham Mia M. Kanzawa Daniel N. Barbosa Caroline Currie Catherine Brooks Brent E. White Anna Huskin Jason Paek Jack Geocaris Dinatu Elnathan Ria Ronquillo Roy Kim Zenith H. Alam Vaikom S. Mahadevan Sophie G. Fuller Grant W. Stalker Sara A. Bravo Dina Jean John J. Lee Medeona Gjergjindreaj Christos G. Mihos Steven T. Forman Subramaniam Venkatraman Patrick M. McCarthy James D. Thomas |
| author_sort | John S. Chorba |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-04-13T16:34:42Z |
| format | Article |
| id | doaj.art-e45493abbc90480aa8c8c373ac9ed160 |
| institution | Directory Open Access Journal |
| issn | 2047-9980 |
| language | English |
| last_indexed | 2024-04-13T16:34:42Z |
| publishDate | 2021-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease |
| spelling | doaj.art-e45493abbc90480aa8c8c373ac9ed1602022-12-22T02:39:28ZengWileyJournal of the American Heart Association: Cardiovascular and Cerebrovascular Disease2047-99802021-05-0110910.1161/JAHA.120.019905Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope PlatformJohn S. Chorba0Avi M. Shapiro1Le Le2John Maidens3John Prince4Steve Pham5Mia M. Kanzawa6Daniel N. Barbosa7Caroline Currie8Catherine Brooks9Brent E. White10Anna Huskin11Jason Paek12Jack Geocaris13Dinatu Elnathan14Ria Ronquillo15Roy Kim16Zenith H. Alam17Vaikom S. Mahadevan18Sophie G. Fuller19Grant W. Stalker20Sara A. Bravo21Dina Jean22John J. Lee23Medeona Gjergjindreaj24Christos G. Mihos25Steven T. Forman26Subramaniam Venkatraman27Patrick M. McCarthy28James D. Thomas29Division of Cardiology University of California San Francisco San Francisco CAEko Oakland CAEko Oakland CAEko Oakland CAEko Oakland CAEko Oakland CAEko Oakland CAEko Oakland CAEko Oakland CAEko Oakland CADivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILDivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILDivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILDivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILDivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILLos Alamitos Cardiovascular Medical Group Los Alamitos CALos Alamitos Cardiovascular Medical Group Los Alamitos CAEchocardiography Laboratory Mount Sinai Heart InstituteMount Sinai Medical Center Miami Beach FLDivision of Cardiology University of California San Francisco San Francisco CADivision of Cardiology University of California San Francisco San Francisco CADivision of Cardiology University of California San Francisco San Francisco CADivision of Cardiology University of California San Francisco San Francisco CADivision of Cardiology University of California San Francisco San Francisco CAEchocardiography Laboratory Mount Sinai Heart InstituteMount Sinai Medical Center Miami Beach FLEchocardiography Laboratory Mount Sinai Heart InstituteMount Sinai Medical Center Miami Beach FLEchocardiography Laboratory Mount Sinai Heart InstituteMount Sinai Medical Center Miami Beach FLLos Alamitos Cardiovascular Medical Group Los Alamitos CAEko Oakland CADivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILDivision of Cardiology Bluhm Cardiovascular InstituteNorthwestern University Chicago ILBackground 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.https://www.ahajournals.org/doi/10.1161/JAHA.120.019905auscultationmachine learningneural networksphysical examinationvalvular heart disease |
| spellingShingle | John S. Chorba Avi M. Shapiro Le Le John Maidens John Prince Steve Pham Mia M. Kanzawa Daniel N. Barbosa Caroline Currie Catherine Brooks Brent E. White Anna Huskin Jason Paek Jack Geocaris Dinatu Elnathan Ria Ronquillo Roy Kim Zenith H. Alam Vaikom S. Mahadevan Sophie G. Fuller Grant W. Stalker Sara A. Bravo Dina Jean John J. Lee Medeona Gjergjindreaj Christos G. Mihos Steven T. Forman Subramaniam Venkatraman Patrick M. McCarthy James D. Thomas Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease auscultation machine learning neural networks physical examination valvular heart disease |
| 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 | auscultation machine learning neural networks physical examination valvular heart disease |
| url | https://www.ahajournals.org/doi/10.1161/JAHA.120.019905 |
| work_keys_str_mv | AT johnschorba deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT avimshapiro deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT lele deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT johnmaidens deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT johnprince deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT stevepham deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT miamkanzawa deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT danielnbarbosa deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT carolinecurrie deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT catherinebrooks deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT brentewhite deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT annahuskin deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT jasonpaek deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT jackgeocaris deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT dinatuelnathan deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT riaronquillo deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT roykim deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT zenithhalam deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT vaikomsmahadevan deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT sophiegfuller deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT grantwstalker deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT saraabravo deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT dinajean deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT johnjlee deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT medeonagjergjindreaj deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT christosgmihos deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT steventforman deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT subramaniamvenkatraman deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT patrickmmccarthy deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform AT jamesdthomas deeplearningalgorithmforautomatedcardiacmurmurdetectionviaadigitalstethoscopeplatform |