{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T23:45:22Z","timestamp":1791416722781,"version":"4.3.3"},"reference-count":55,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"20","content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["JAHA"],"published-print":{"date-parts":[[2023,10,17]]},"abstract":"<jats:sec sec-type=\"background\" xml:lang=\"en\">\n            <jats:title>Background<\/jats:title>\n            <jats:p xml:lang=\"en\">The success of cardiac auscultation varies widely among medical professionals, which can lead to missed treatments for structural heart disease. Applying machine learning to cardiac auscultation could address this problem, but despite recent interest, few algorithms have been brought to clinical practice. We evaluated a novel suite of Food and Drug Administration\u2010cleared algorithms trained via deep learning on &gt;15\u2009000 heart sound recordings.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec xml:lang=\"en\">\n            <jats:title>Methods and Results<\/jats:title>\n            <jats:p xml:lang=\"en\">We validated the algorithms on a data set of 2375 recordings from 615 unique subjects. This data set was collected in real clinical environments using commercially available digital stethoscopes, annotated by board\u2010certified cardiologists, and paired with echocardiograms as the gold standard. To model the algorithm in clinical practice, we compared its performance against 10 clinicians on a subset of the validation database. Our algorithm reliably detected structural murmurs with a sensitivity of 85.6% and specificity of 84.4%. When limiting the analysis to clearly audible murmurs in adults, performance improved to a sensitivity of 97.9% and specificity of 90.6%. The algorithm also reported timing within the cardiac cycle, differentiating between systolic and diastolic murmurs. Despite optimizing acoustics for the clinicians, the algorithm substantially outperformed the clinicians (average clinician accuracy, 77.9%; algorithm accuracy, 84.7%.)<\/jats:p>\n          <\/jats:sec>\n          <jats:sec xml:lang=\"en\">\n            <jats:title>Conclusions<\/jats:title>\n            <jats:p xml:lang=\"en\">The algorithms accurately identified murmurs associated with structural heart disease. Our results illustrate a marked contrast between the consistency of the algorithm and the substantial interobserver variability of clinicians. Our results suggest that adopting machine learning algorithms into clinical practice could improve the detection of structural heart disease to facilitate patient care.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1161\/jaha.123.030377","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T10:18:05Z","timestamp":1697192285000},"update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":44,"title":["Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease"],"prefix":"10.1161","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3203-8754","authenticated-orcid":false,"given":"John","family":"Prince","sequence":"first","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8211-7699","authenticated-orcid":false,"given":"John","family":"Maidens","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spencer","family":"Kieu","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3867-9592","authenticated-orcid":false,"given":"Caroline","family":"Currie","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Barbosa","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody","family":"Hitchcock","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2067-3002","authenticated-orcid":false,"given":"Adam","family":"Saltman","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8806-6183","authenticated-orcid":false,"given":"Kambiz","family":"Norozi","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Pediatric Cardiology Western University London ON Canada"},{"name":"Department of Pediatric Cardiology and Intensive Care Medicine Hannover Medical School Hannover Germany"},{"name":"Children Health Research Institute London ON Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Wiesner","sequence":"additional","affiliation":[{"name":"Cox Medical Center Springfield MO USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7004-2140","authenticated-orcid":false,"given":"Nicholas","family":"Slamon","sequence":"additional","affiliation":[{"name":"Nemours Children\u2019s Hospital, Delaware Wilmington DE USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erica","family":"Del Grippo","sequence":"additional","affiliation":[{"name":"Nemours Children\u2019s Hospital, Delaware Wilmington DE USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9127-9275","authenticated-orcid":false,"given":"Deepak","family":"Padmanabhan","sequence":"additional","affiliation":[{"name":"Sri Jayadeva Institute of Cardiovascular Sciences and Research Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7147-3732","authenticated-orcid":false,"given":"Anand","family":"Subramanian","sequence":"additional","affiliation":[{"name":"Sri Jayadeva Institute of Cardiovascular Sciences and Research Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cholenahalli","family":"Manjunath","sequence":"additional","affiliation":[{"name":"Sri Jayadeva Institute of Cardiovascular Sciences and Research Bengaluru India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Chorba","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Zuckerberg San Francisco General Hospital, Department of Medicine University of California San Francisco San Francisco CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subramaniam","family":"Venkatraman","sequence":"additional","affiliation":[{"name":"Eko Devices, Inc. Oakland CA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41569-021-00570-z"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.119.043391"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehz948"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000000923"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2019.4235"},{"key":"e_1_3_2_7_2","volume-title":"Health Care Spending and the Medicare Program: A Data Book","unstructured":"Health Care Spending and the Medicare Program: A Data Book. Medicare Payment Advisory Commission. Accessed July 26, 2023. https:\/\/www.medpac.gov\/wp\u2010content\/uploads\/2023\/07\/July2023_MedPAC_DataBook_SEC.pdf"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/clc.22810"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2010.08.008"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2015-308635"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2020.2497"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehab395"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1997.03550090041030"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2022.16667"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2018-313393"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.2459\/JCM.0b013e3283649953"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1111\/chd.12328"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2603787"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2010.110"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CIDM.2007.368902"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2475278"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5625940"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2011.0170"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.628"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(02)00281-7"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1142\/S0219519414500468"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2009.01.003"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2009.10.003"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.120.019905"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103733"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2870759"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/37\/12\/2181"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1080\/03091900601015162"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.23.e215"},{"issue":"43","key":"e_1_3_2_35_2","first-page":"609","article-title":"Classification of normal\/abnormal heart sound recordings: the PhysioNet\/Computing in Cardiology Challenge 2016","volume":"2016","author":"Clifford GD","year":"2010","unstructured":"Clifford GD, Liu C, Moody B, Springer D, Silva I, Li Q, Mark RG. Classification of normal\/abnormal heart sound recordings: the PhysioNet\/Computing in Cardiology Challenge 2016. Comput Cardiol. 2010;2016(43):609\u2013612.","journal-title":"Comput Cardiol"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1378\/chest.91.6.870"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1001\/archpedi.1952.02040100038003"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2022.0399"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00246-018-2036-z"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.5220\/0004234403370340"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1101\/2022.08.11.22278688"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5627633"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1161\/circ.136.suppl_1.17004"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"e_1_3_2_45_2","article-title":"Adam: a method for stochastic optimization","volume":"2014","author":"Kingma DP","year":"2014","unstructured":"Kingma DP, Ba JL. Adam: a method for stochastic optimization. arXiv preprint arXiv. 2014;2014:1412.6980.","journal-title":"arXiv preprint arXiv"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2017.01.007"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2008.11.029"},{"key":"e_1_3_2_48_2","unstructured":"ANSI\u2010AAMI . Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms. American National Standards Institute; 1999."},{"key":"e_1_3_2_49_2","first-page":"625","article-title":"Support vector machine hidden semi\u2010markov model\u2010based heart sound segmentation","volume":"2014","author":"Springer DB","year":"2014","unstructured":"Springer DB, Tarassenko L, Clifford GD. Support vector machine hidden semi\u2010markov model\u2010based heart sound segmentation. Comput Cardiol. 2014;2014:625\u2013628.","journal-title":"Comput Cardiol"},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1002\/9780470317082","volume-title":"Statistical Methods in Diagnostic Medicine","author":"Zhou X\u2010H","year":"2002","unstructured":"Zhou X\u2010H, Obuchowski N, McClish D. Statistical Methods in Diagnostic Medicine. Wiley Series in Probability and Statistics, 2nd ed. 2002, Chapter 6: Sample Size Calculation, 193\u2013229."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1002\/joa3.12062"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9343(00)00673-2"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0002-9343(97)89452-1"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2019-314940"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.08.1035"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1093\/ehjdh\/ztac029"}],"container-title":["Journal of the American Heart Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/JAHA.123.030377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T12:44:19Z","timestamp":1715604259000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/JAHA.123.030377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,17]]},"references-count":55,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2023,10,17]]}},"alternative-id":["10.1161\/JAHA.123.030377"],"URL":"https:\/\/doi.org\/10.1161\/jaha.123.030377","relation":{},"ISSN":["2047-9980"],"issn-type":[{"value":"2047-9980","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,17]]},"assertion":[{"value":"2023-03-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e030377"}}