Automated identification of innocent Still's murmur using a convolutional neural network
BackgroundStill's murmur is the most prevalent innocent heart murmur of childhood. Auscultation is the primary clinical tool to identify this murmur as innocent. Whereas pediatric cardiologists routinely perform this task, primary care providers are less successful in distinguishing Still'...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Pediatrics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fped.2022.923956/full |
| _version_ | 1818063315884048384 |
|---|---|
| author | Raj Shekhar Raj Shekhar Ganesh Vanama Titus John Titus John James Issac Youness Arjoune Robin W. Doroshow Robin W. Doroshow Robin W. Doroshow |
| author_facet | Raj Shekhar Raj Shekhar Ganesh Vanama Titus John Titus John James Issac Youness Arjoune Robin W. Doroshow Robin W. Doroshow Robin W. Doroshow |
| author_sort | Raj Shekhar |
| collection | DOAJ |
| description | BackgroundStill's murmur is the most prevalent innocent heart murmur of childhood. Auscultation is the primary clinical tool to identify this murmur as innocent. Whereas pediatric cardiologists routinely perform this task, primary care providers are less successful in distinguishing Still's murmur from the murmurs of true heart disease. This results in a large number of children with a Still's murmur being referred to pediatric cardiologists.ObjectivesTo develop a computer algorithm that can aid primary care providers to identify the innocent Still's murmur at the point of care, to substantially decrease over-referral.MethodsThe study included Still's murmurs, pathological murmurs, other innocent murmurs, and normal (i.e., non-murmur) heart sounds of 1,473 pediatric patients recorded using a commercial electronic stethoscope. The recordings with accompanying clinical diagnoses provided by a pediatric cardiologist were used to train and test the convolutional neural network-based algorithm.ResultsA comparative analysis showed that the algorithm using only the murmur sounds recorded at the lower left sternal border achieved the highest accuracy. The developed algorithm identified Still's murmur with 90.0% sensitivity and 98.3% specificity for the default decision threshold. The area under the receiver operating characteristic curve was 0.943.ConclusionsStill's murmur can be identified with high accuracy with the algorithm we developed. Using this approach, the algorithm could help to reduce the rate of unnecessary pediatric cardiologist referrals and use of echocardiography for a common benign finding. |
| first_indexed | 2024-12-10T14:18:09Z |
| format | Article |
| id | doaj.art-ad86f1b6825944ea89c6b4adb53ac93b |
| institution | Directory Open Access Journal |
| issn | 2296-2360 |
| language | English |
| last_indexed | 2024-12-10T14:18:09Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pediatrics |
| spelling | doaj.art-ad86f1b6825944ea89c6b4adb53ac93b2022-12-22T01:45:16ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602022-09-011010.3389/fped.2022.923956923956Automated identification of innocent Still's murmur using a convolutional neural networkRaj Shekhar0Raj Shekhar1Ganesh Vanama2Titus John3Titus John4James Issac5Youness Arjoune6Robin W. Doroshow7Robin W. Doroshow8Robin W. Doroshow9Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, United StatesAusculTech Dx, Silver Spring, MD, United StatesAusculTech Dx, Silver Spring, MD, United StatesSheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, United StatesAusculTech Dx, Silver Spring, MD, United StatesAusculTech Dx, Silver Spring, MD, United StatesSheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, United StatesSheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital, Washington, DC, United StatesAusculTech Dx, Silver Spring, MD, United StatesChildren's National Heart Institute, Children's National Hospital, Washington, DC, United StatesBackgroundStill's murmur is the most prevalent innocent heart murmur of childhood. Auscultation is the primary clinical tool to identify this murmur as innocent. Whereas pediatric cardiologists routinely perform this task, primary care providers are less successful in distinguishing Still's murmur from the murmurs of true heart disease. This results in a large number of children with a Still's murmur being referred to pediatric cardiologists.ObjectivesTo develop a computer algorithm that can aid primary care providers to identify the innocent Still's murmur at the point of care, to substantially decrease over-referral.MethodsThe study included Still's murmurs, pathological murmurs, other innocent murmurs, and normal (i.e., non-murmur) heart sounds of 1,473 pediatric patients recorded using a commercial electronic stethoscope. The recordings with accompanying clinical diagnoses provided by a pediatric cardiologist were used to train and test the convolutional neural network-based algorithm.ResultsA comparative analysis showed that the algorithm using only the murmur sounds recorded at the lower left sternal border achieved the highest accuracy. The developed algorithm identified Still's murmur with 90.0% sensitivity and 98.3% specificity for the default decision threshold. The area under the receiver operating characteristic curve was 0.943.ConclusionsStill's murmur can be identified with high accuracy with the algorithm we developed. Using this approach, the algorithm could help to reduce the rate of unnecessary pediatric cardiologist referrals and use of echocardiography for a common benign finding.https://www.frontiersin.org/articles/10.3389/fped.2022.923956/fullStill's murmurinnocent heart murmurconvolutional neural networkautomated identificationartificial intelligence |
| spellingShingle | Raj Shekhar Raj Shekhar Ganesh Vanama Titus John Titus John James Issac Youness Arjoune Robin W. Doroshow Robin W. Doroshow Robin W. Doroshow Automated identification of innocent Still's murmur using a convolutional neural network Frontiers in Pediatrics Still's murmur innocent heart murmur convolutional neural network automated identification artificial intelligence |
| title | Automated identification of innocent Still's murmur using a convolutional neural network |
| title_full | Automated identification of innocent Still's murmur using a convolutional neural network |
| title_fullStr | Automated identification of innocent Still's murmur using a convolutional neural network |
| title_full_unstemmed | Automated identification of innocent Still's murmur using a convolutional neural network |
| title_short | Automated identification of innocent Still's murmur using a convolutional neural network |
| title_sort | automated identification of innocent still s murmur using a convolutional neural network |
| topic | Still's murmur innocent heart murmur convolutional neural network automated identification artificial intelligence |
| url | https://www.frontiersin.org/articles/10.3389/fped.2022.923956/full |
| work_keys_str_mv | AT rajshekhar automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT rajshekhar automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT ganeshvanama automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT titusjohn automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT titusjohn automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT jamesissac automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT younessarjoune automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT robinwdoroshow automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT robinwdoroshow automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork AT robinwdoroshow automatedidentificationofinnocentstillsmurmurusingaconvolutionalneuralnetwork |