Artificial-Intelligence-Enabled Digital Stethoscope Significantly Improves Point-of-Care Screening for Clinically Significant Valvular Heart Disease

Artificial-Intelligence-Enabled Digital Stethoscope Significantly Improves Point-of-Care Screening for Clinically Significant Valvular Heart Disease | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Short Report Artificial-Intelligence-Enabled Digital Stethoscope Significantly Improves Point-of-Care Screening for Clinically Significant Valvular Heart Disease Moshe Rancier, Igor Israel, Vimalson Monickam, Caroline Currie, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5649209/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Clinically significant valvular heart disease (VHD) affects 1 in 10 adults over 65 but often goes undiagnosed. In a real-world study of 368 patients, an AI-enabled digital stethoscope demonstrated significantly higher sensitivity than primary care providers (94.1% vs. 41.2%, p=0.002) for detecting audible VHD, albeit with slightly lower specificity. These results suggest that AI-assisted auscultation can enable earlier VHD detection in primary care, improving diagnosis, patient care, and outcomes. Health sciences/Diseases/Cardiovascular diseases/Valvular disease Health sciences/Health care/Diagnosis/Physical examination Figures Figure 1 Introduction Clinically significant valvular heart disease (VHD), defined as moderate or greater severity, affects 1 in 10 adults over 65 years old 1 , and is associated with reduced functional capacity, arrhythmia, heart failure, increased hospitalization, and death 1,2 . Unfortunately, symptoms of VHD are frequently nonspecific, and more than half of patients with moderate to severe disease are asymptomatic 3 . This often leads to delayed diagnosis and treatment, which, in addition to the reduced quality of life and increased mortality, poses a substantial financial burden to healthcare systems 1 . Murmurs are often an early clinical indicator of underlying VHD. However, cardiac auscultation, the current point-of-care clinical standard for VHD screening, has shown a 44% sensitivity when performed by experienced general practitioners for detecting clinically significant VHD, leaving many patients undiagnosed 4 . This significant shortcoming in cardiac auscultation has a large impact on patient outcomes. VHD is prevalent and can progress from moderate to severe within just one year, resulting in a sharp escalation in heart failure hospitalizations and mortality rates 2 . More accurate diagnostic methods are therefore of critical importance. This research letter describes the real-world performance of an independently validated, FDA-cleared suite of deep-learning-based artificial intelligence (AI) algorithms that detects and classifies cardiac murmurs associated with clinically significant VHD 5 . Paired with a digital stethoscope, this novel platform presents a powerful tool for consistent and reliable VHD screening. Here, we provide results of a real-world evaluation of our AI-based platform’s ability to better detect previously undiagnosed VHD in a point-of-care setting compared to conventional practice. The median age of the enrolled population was 70 years (IQR: 66 - 77), with 224 (61%) being female. The most common VHD risk factors in the study population were hypertension (79%, 292), hyperlipidemia (68%, 251), and diabetes mellitus (38%,141). Figure 1 demonstrates the performance of the AI and the PCPs at detecting patients with audible VHD, respectively. The AI showed more than a twofold improvement in sensitivity compared to PCP for detecting patients with audible VHD (94.1% vs. 41.2%, p =0.002) but with less specificity (84.9% vs. 95.7%, p <0.001). The AI identified 23 patients with previously undiagnosed clinically significant VHD compared to eight identified by the PCPs. Our study demonstrates that an AI-enabled digital stethoscope significantly outperforms standard-of-care auscultation in the overall detection of VHD. These results are consistent with previous implementations on independent datasets, further validating its ability to generalize across a wide range of clinical environments 5 . These results suggest that the implementation of digital stethoscopes with structural murmur detection AI into primary care settings leads to earlier detection of undiscovered VHD, thereby facilitating appropriate patient care and ultimately improving patient outcomes. Limitations must be acknowledged. The study's sample size was relatively small, which limited the ability to perform more detailed subgroup analyses. As a result, the findings may not capture the full range of outcomes in all patient subgroups. Despite this, our study provides valuable insights into the immediate clinical impact of a commercially available, novel, and easy-to-use point-of-care solution in a real-world setting. Methods From June 2021 to May 2023, this ongoing single-arm, single-blinded, prospective study enrolled 368 patients aged 50 years and older at risk for heart disease but without prior VHD diagnosis or history of murmur from three primary care clinics. Following collection of demographic and clinical data, a four-point cardiac auscultation was performed on each patient by (1) primary care practitioners (PCPs) according to the standard of care and (2) trained study coordinators equipped with digital stethoscopes to collect phonocardiogram (PCG) data for subsequent AI analysis. Five general practice clinicians (4 MDs, and 1 nurse practitioner) formed the group of PCPs. All procedures and protocols were approved by the Salus Institutional Review Board and the study is registered at clinicaltrials.gov (NCT05459545). An exam was labeled “positive” if a murmur was detected at any auscultation point. Each patient underwent an echocardiogram by a certified technician to confirm whether clinically significant VHD was present, and their PCG recordings were independently reviewed by an outside expert panel to confirm whether audible murmurs were present. PCP and expert panel were blinded to AI and echocardiogram results. Ground truth was defined as “audible VHD,” which was the combination of confirmed, clinically significant VHD per echocardiogram results, as well as confirmed, audible murmur per expert auscultation panel. Fisher’s exact test was used to compare the sensitivity and specificity of the AI vs. PCPs. Declarations Competing Interests CC, BV, DWVP, JP, RVM are affiliated with Eko Health that develops digital stethoscopes, software, and algorithms to detect cardiovascular and pulmonary disease. Disclosures CC, BV, DWVP, JP, RVM: current or former employees of Eko Health, Inc. Remaining authors have no relevant disclosures. Author Contribution M.R., C.C., E.L., and B.V. conceived of the idea. I.I., V.M., and D.W.vP. collected and organized data. J.P. and R.V.M analyzed the data. R.V.M, M.R, and C.C drafted the manuscript. M.R., R.V.M, and E.L. contributed to data discussion and manuscript revision. Data Availability Data available upon reasonable request. References d'Arcy JL, Coffey S, Loudon MA, et al. Large-scale community echocardiographic screening reveals a major burden of undiagnosed valvular heart disease in older people: the OxVALVE Population Cohort Study. Eur Heart J . Dec 14 2016;37(47):3515-3522. doi:10.1093/eurheartj/ehw229 Gada H, Vora A, Ramlawi B, et al. INCREASED RISK OF CLINICAL OUTCOMES IN MODERATE AORTIC STENOSIS PATIENTS. Journal of the American College of Cardiology . 2021/05/11 2021;77(18_Supplement_1):971-971. doi:10.1016/S0735-1097(21)02330-5 Généreux P, Stone GW, O'Gara PT, et al. Natural History, Diagnostic Approaches, and Therapeutic Strategies for Patients With Asymptomatic Severe Aortic Stenosis. J Am Coll Cardiol . May 17 2016;67(19):2263-2288. doi:10.1016/j.jacc.2016.02.057 Gardezi SKM, Myerson SG, Chambers J, et al. Cardiac auscultation poorly predicts the presence of valvular heart disease in asymptomatic primary care patients. Heart . Nov 2018;104(22):1832-1835. doi:10.1136/heartjnl-2018-313082 Prince J, Maidens J, Kieu S, et al. Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease. J Am Heart Assoc . 2023-10-17 2023;12(20)doi:10.1161/jaha.123.030377 Additional Declarations Competing interest reported. CC, BV, DWVP, JP, RVM are affiliated with Eko Health that develops digital stethoscopes, software, and algorithms to detect cardiovascular and pulmonary disease. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5649209","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":391538889,"identity":"80872286-18a7-490f-8249-9fbd390e24a7","order_by":0,"name":"Moshe Rancier","email":"","orcid":"","institution":"Mass General Brigham Community Physicians","correspondingAuthor":false,"prefix":"","firstName":"Moshe","middleName":"","lastName":"Rancier","suffix":""},{"id":391538890,"identity":"8384f6b7-442f-420e-9c59-42c3d017bd31","order_by":1,"name":"Igor Israel","email":"","orcid":"","institution":"Parker Jewish Institute for Health Care and Rehabilitation","correspondingAuthor":false,"prefix":"","firstName":"Igor","middleName":"","lastName":"Israel","suffix":""},{"id":391538891,"identity":"effb8f41-5802-46b1-acc6-5f9662ffc55a","order_by":2,"name":"Vimalson Monickam","email":"","orcid":"","institution":"Parker Jewish Institute for Health Care and Rehabilitation","correspondingAuthor":false,"prefix":"","firstName":"Vimalson","middleName":"","lastName":"Monickam","suffix":""},{"id":391538892,"identity":"b825c19a-357e-4329-bda0-8ff5720420be","order_by":3,"name":"Caroline Currie","email":"","orcid":"","institution":"Eko Health, Inc","correspondingAuthor":false,"prefix":"","firstName":"Caroline","middleName":"","lastName":"Currie","suffix":""},{"id":391538893,"identity":"1066c61e-b4e3-4f50-a3d3-26c3a69d35b3","order_by":4,"name":"Ben Verschoore","email":"","orcid":"","institution":"Eko Health, Inc","correspondingAuthor":false,"prefix":"","firstName":"Ben","middleName":"","lastName":"Verschoore","suffix":""},{"id":391538894,"identity":"5ea04090-10af-403d-9902-d06b246c26fe","order_by":5,"name":"Emileigh Lastowski","email":"","orcid":"","institution":"Eko Health, Inc","correspondingAuthor":false,"prefix":"","firstName":"Emileigh","middleName":"","lastName":"Lastowski","suffix":""},{"id":391538895,"identity":"8f8cd344-8852-4c64-9bd5-a5a4ef427196","order_by":6,"name":"Douglas W Pelt","email":"","orcid":"","institution":"Eko Health, Inc","correspondingAuthor":false,"prefix":"","firstName":"Douglas","middleName":"W","lastName":"Pelt","suffix":""},{"id":391538896,"identity":"3eb42cb8-7d30-47fd-a72a-58c76e660304","order_by":7,"name":"John Prince","email":"","orcid":"","institution":"Eko Health, Inc","correspondingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Prince","suffix":""},{"id":391538897,"identity":"82cf3950-1548-4bf6-b0b2-589408f73a6e","order_by":8,"name":"Rosalie V McDonough","email":"data:image/png;base64,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","orcid":"","institution":"Eko Health, Inc","correspondingAuthor":true,"prefix":"","firstName":"Rosalie","middleName":"V","lastName":"McDonough","suffix":""}],"badges":[],"createdAt":"2024-12-15 20:53:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5649209/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5649209/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72286455,"identity":"af255a8d-0a28-4dbc-8668-334ae3ffbad3","added_by":"auto","created_at":"2024-12-24 17:04:48","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":75248,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eConfusion matrices of PCP and Algorithm performance against ground truth detection of patients with audible VHD.\u003c/strong\u003e Audible VHD was defined as the presence of at least moderate disease severity on echocardiogram in addition to the presence of an audible murmur on PCG, as determined by consensus of an expert panel of annotators. A) PCP performance. In 7/17 cases, the presence of audible VHD was correctly identified, resulting in a sensitivity of 41.2% (i.e., false negative rate of 58.8%). PCPs correctly labeled 336/353 cases as having no audible heart murmur, resulting in a specificity of 95.7% (i.e., false positive rate of 4.3%). \u0026nbsp;B) Algorithm performance. In 16/17 cases, the presence of audible VHD was correctly identified, resulting in a sensitivity of 94.1% (i.e., false negative rate of 5.9%). The algorithm correctly identified 298/353 patients as having no audible murmur, resulting in a specificity of 84.9% (i.e., false positive rate of 15.1%). \u003cem\u003ePCP: Primary care provider; VHD: valvular heart disease; PCG: phonocardiogram\u003c/em\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-5649209/v1/a5b23e2b6ddc2a09edd9f612.png"},{"id":74650659,"identity":"d6c7d31e-3874-4736-bc2b-5c0b17c4b374","added_by":"auto","created_at":"2025-01-24 10:39:09","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":425506,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5649209/v1/c4e1feb6-07b6-463b-829b-2a3675473aa0.pdf"}],"financialInterests":"Competing interest reported. CC, BV, DWVP, JP, RVM are affiliated with Eko Health that develops digital stethoscopes, software, and algorithms to detect cardiovascular and pulmonary disease.","formattedTitle":"Artificial-Intelligence-Enabled Digital Stethoscope Significantly Improves Point-of-Care Screening for Clinically Significant Valvular Heart Disease","fulltext":[{"header":"Introduction","content":"\u003cp\u003eClinically significant valvular heart disease (VHD), defined as moderate or greater severity, affects 1 in 10 adults over 65 years old\u003csup\u003e1\u003c/sup\u003e, and is associated with reduced functional capacity, arrhythmia, heart failure, increased hospitalization, and death\u003csup\u003e1,2\u003c/sup\u003e. Unfortunately, symptoms of VHD are frequently nonspecific, and more than half of patients with moderate to severe disease are asymptomatic\u003csup\u003e3\u003c/sup\u003e. This often leads to delayed diagnosis and treatment, which, in addition to the reduced quality of life and increased mortality, poses a substantial financial burden to healthcare systems\u003csup\u003e1\u003c/sup\u003e. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMurmurs are often an early clinical indicator of underlying VHD. However, cardiac auscultation, the current point-of-care clinical standard for VHD screening, has shown a 44% sensitivity when performed by experienced general practitioners for detecting clinically significant VHD, leaving many patients undiagnosed\u003csup\u003e4\u003c/sup\u003e. This significant shortcoming in cardiac auscultation has a large impact on patient outcomes. VHD is prevalent and can progress from moderate to severe within just one year, resulting in a sharp escalation in heart failure hospitalizations and mortality rates\u003csup\u003e2\u003c/sup\u003e. More accurate diagnostic methods are therefore of critical importance.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThis research letter describes the real-world performance of an independently validated, FDA-cleared suite of deep-learning-based artificial intelligence (AI) algorithms that detects and classifies cardiac murmurs associated with clinically significant VHD\u003csup\u003e5\u003c/sup\u003e. Paired with a digital stethoscope, this novel platform presents a powerful tool for consistent and reliable VHD screening. Here, we provide results of a real-world evaluation of our AI-based platform\u0026rsquo;s ability to better detect previously undiagnosed VHD in a point-of-care setting compared to conventional practice.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe median age of the enrolled population was 70 years (IQR: 66 - 77), with 224 (61%) being female. The most common VHD risk factors in the study population were hypertension (79%, 292), hyperlipidemia (68%, 251), and diabetes mellitus (38%,141). Figure 1 demonstrates the performance of the AI and the PCPs at detecting patients with audible VHD, respectively.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe AI showed more than a twofold improvement in sensitivity compared to PCP for detecting patients with audible VHD (94.1% vs. 41.2%, \u003cem\u003ep\u003c/em\u003e=0.002) but with less specificity (84.9% vs. 95.7%, \u003cem\u003ep\u003c/em\u003e\u0026lt;0.001). The AI identified 23 patients with previously undiagnosed clinically significant VHD compared to eight identified by the PCPs. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eOur study demonstrates that an AI-enabled digital stethoscope significantly outperforms standard-of-care auscultation in the overall detection of VHD. These results are consistent with previous implementations on independent datasets, further validating its ability to generalize across a wide range of clinical environments\u003csup\u003e5\u003c/sup\u003e. These results suggest that the implementation of digital stethoscopes with structural murmur detection AI into primary care settings leads to earlier detection of undiscovered VHD, thereby facilitating appropriate patient care and ultimately improving patient outcomes. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eLimitations must be acknowledged. The study\u0026apos;s sample size was relatively small, which limited the ability to perform more detailed subgroup analyses. As a result, the findings may not capture the full range of outcomes in all patient subgroups. Despite this, our study provides valuable insights into the immediate clinical impact of a commercially available, novel, and easy-to-use point-of-care solution in a real-world setting.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003eFrom June 2021 to May 2023, this ongoing single-arm, single-blinded, prospective study enrolled 368 patients aged 50 years and older at risk for heart disease but without prior VHD diagnosis or history of murmur from three primary care clinics. Following collection of demographic and clinical data, a four-point cardiac auscultation was performed on each patient by (1) primary care practitioners (PCPs) according to the standard of care and (2) trained study coordinators equipped with digital stethoscopes to collect phonocardiogram (PCG) data for subsequent AI analysis. Five general practice clinicians (4 MDs, and 1 nurse practitioner) formed the group of PCPs. All procedures and protocols were approved by the Salus Institutional Review Board and the study is registered at clinicaltrials.gov (NCT05459545).\u003c/p\u003e \u003cp\u003eAn exam was labeled \u0026ldquo;positive\u0026rdquo; if a murmur was detected at any auscultation point. Each patient underwent an echocardiogram by a certified technician to confirm whether clinically significant VHD was present, and their PCG recordings were independently reviewed by an outside expert panel to confirm whether audible murmurs were present. PCP and expert panel were blinded to AI and echocardiogram results. Ground truth was defined as \u0026ldquo;audible VHD,\u0026rdquo; which was the combination of confirmed, clinically significant VHD per echocardiogram results, as well as confirmed, audible murmur per expert auscultation panel. Fisher\u0026rsquo;s exact test was used to compare the sensitivity and specificity of the AI vs. PCPs.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003e\u003cstrong\u003eCompeting Interests\u003c/strong\u003e\u003c/h2\u003e\n\u003cp\u003eCC, BV, DWVP, JP, RVM are affiliated with Eko Health that develops digital stethoscopes, software, and algorithms to detect cardiovascular and pulmonary disease.\u003c/p\u003e\n\u003ch2\u003eDisclosures\u003c/h2\u003e\n\u003cp\u003eCC, BV, DWVP, JP, RVM: current or former employees of Eko Health, Inc. Remaining authors have no relevant disclosures.\u003c/p\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\n\u003cp\u003eM.R., C.C., E.L., and B.V. conceived of the idea. I.I., V.M., and D.W.vP. collected and organized data. J.P. and R.V.M analyzed the data. R.V.M, M.R, and C.C drafted the manuscript. M.R., R.V.M, and E.L. contributed to data discussion and manuscript revision.\u003c/p\u003e\n\u003ch2\u003eData Availability\u003c/h2\u003e\n\u003cp\u003eData available upon reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003ed\u0026apos;Arcy JL, Coffey S, Loudon MA, et al. Large-scale community echocardiographic screening reveals a major burden of undiagnosed valvular heart disease in older people: the OxVALVE Population Cohort Study. \u003cem\u003eEur Heart J\u003c/em\u003e. Dec 14 2016;37(47):3515-3522. doi:10.1093/eurheartj/ehw229\u003c/li\u003e\n\u003cli\u003eGada H, Vora A, Ramlawi B, et al. INCREASED RISK OF CLINICAL OUTCOMES IN MODERATE AORTIC STENOSIS PATIENTS. \u003cem\u003eJournal of the American College of Cardiology\u003c/em\u003e. 2021/05/11 2021;77(18_Supplement_1):971-971. doi:10.1016/S0735-1097(21)02330-5\u003c/li\u003e\n\u003cli\u003eG\u0026eacute;n\u0026eacute;reux P, Stone GW, O\u0026apos;Gara PT, et al. Natural History, Diagnostic Approaches, and Therapeutic Strategies for Patients With Asymptomatic Severe Aortic Stenosis. \u003cem\u003eJ Am Coll Cardiol\u003c/em\u003e. May 17 2016;67(19):2263-2288. doi:10.1016/j.jacc.2016.02.057\u003c/li\u003e\n\u003cli\u003eGardezi SKM, Myerson SG, Chambers J, et al. Cardiac auscultation poorly predicts the presence of valvular heart disease in asymptomatic primary care patients. \u003cem\u003eHeart\u003c/em\u003e. Nov 2018;104(22):1832-1835. doi:10.1136/heartjnl-2018-313082\u003c/li\u003e\n\u003cli\u003ePrince J, Maidens J, Kieu S, et al. Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease. \u003cem\u003eJ Am Heart Assoc\u003c/em\u003e. 2023-10-17 2023;12(20)doi:10.1161/jaha.123.030377\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-5649209/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5649209/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eClinically significant valvular heart disease (VHD) affects 1 in 10 adults over 65 but often goes undiagnosed. In a real-world study of 368 patients, an AI-enabled digital stethoscope demonstrated significantly higher sensitivity than primary care providers (94.1% vs. 41.2%, p=0.002) for detecting audible VHD, albeit with slightly lower specificity. These results suggest that AI-assisted auscultation can enable earlier VHD detection in primary care, improving diagnosis, patient care, and outcomes.\u003c/p\u003e","manuscriptTitle":"Artificial-Intelligence-Enabled Digital Stethoscope Significantly Improves Point-of-Care Screening for Clinically Significant Valvular Heart Disease","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-24 17:04:44","doi":"10.21203/rs.3.rs-5649209/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"558e00bc-efc0-4f2d-94d8-dd0e4e25a9b2","owner":[],"postedDate":"December 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":41734029,"name":"Health sciences/Diseases/Cardiovascular diseases/Valvular disease"},{"id":41734030,"name":"Health sciences/Health care/Diagnosis/Physical examination"}],"tags":[],"updatedAt":"2025-01-24T10:38:56+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-24 17:04:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5649209","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5649209","identity":"rs-5649209","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}