Abstract
Background
The diagnostic accuracy of the stethoscope is limited and highly dependent on clinical
expertise. Our purpose was to develop an electronic stethoscope, based on artificial
intelligence (AI) and infrasound, for the diagnosis of aortic stenosis (AS).
Methods
We used an electronic stethoscope (VoqX; Sanolla, Nesher, Israel) with subsonic capabilities
and acoustic range of 3-2000 Hz. The study had 2 stages. In the first stage, using
the VoqX, we recorded heart sounds from 100 patients referred for echocardiography
(derivation group), 50 with moderate or severe AS and 50 without valvular disease.
An AI-based supervised learning model was applied to the auscultation data from the
first 100 patients used for training, to construct a diagnostic algorithm that was
then tested on a validation group (50 other patients, 25 with AS and 25 without AS).
In the second stage, conducted at a different medical center, we tested the device
on 106 additional patients referred for echocardiography, which included patients
with other valvular diseases.
Results
Using data collected at the aortic and pulmonic auscultation points from the derivation
group, the AI-based algorithm identified moderate or severe AS with 86% sensitivity
and 100% specificity. When applied to the validation group, the sensitivity was 84%
and specificity 92%; and in the additional testing group, 90% and 84%, respectively.
The sensitivity was 55% for mild, 76% for moderate, and 93% for severe AS.
Conclusion
Our initial findings show that an AI-based stethoscope with infrasound capabilities
can accurately diagnose AS. AI-based electronic auscultation is a promising new tool
for automatic screening and diagnosis of valvular heart disease.
Keywords
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to The American Journal of MedicineAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- De l'auscultation médiate ou Traité du Diagnostic des Maladies des Poumons et du Coeur [A treatise on the diseases of the chest and on mediate auscultation].Chaude, Paris1819 ([in French])
- The first 200 years of cardiac auscultation and future perspectives.J Multidiscip Healthc. 2019; 12: 183-189
- Cardiac auscultatory skills of internal medicine and family practice trainees. A comparison of diagnostic proficiency.JAMA. 1997; 278: 717-722
- Hearing at low and infrasonic frequencies.Noise Health. 2004; 6: 37-57
- Clinical comparison of acoustic and electronic stethoscopes and design of a new electronic stethoscope.Am J Cardiol. 1998; 81: 653-656
- 2021 ESC/EACTS Guidelines for the management of valvular heart disease.Eur Heart J. 2022; 43: 561-632
- Contemporary presentation and management of valvular heart disease: the EUrobservational research programme valvular heart disease II survey.Circulation. 2019; 140: 1156-1169
- Global, regional, and national burden of calcific aortic valve and degenerative mitral valve diseases, 1990-2017.Circulation. 2020; 141: 1670-1680
- Heartbeat: improving diagnosis and management of aortic valve disease.Heart. 2018; 104: 1807-1809
- Cardiac auscultation poorly predicts the presence of valvular heart disease in asymptomatic primary care patients.Heart. 2018; 104: 1832-1835
- Patient screening for early detection of aortic stenosis (AS) - Review of current practice and future perspectives.J Thorac Dis. 2018; 10: 5584-5594
- Accuracy and efficacy of hand-held echocardiography in diagnosing valve disease: a systematic review.Am J Med. 2018; 131: 1155-1160
- Deep learning interpretation of echocardiograms.NPJ Digit Med. 2020; 3: 1-10
- Deep neural networks can predict new onset atrial fibrillation from the 12-lead ECG and help identify those at risk of atrial fibrillation-related stroke.Circulation. 2021; 143: 1287-1298
- Guidelines for performing a comprehensive transthoracic echocardiographic examination in adults: recommendations from the American Society of Echocardiography.J Am Soc Echocardiogr. 2019; 32: 1-64
- Recommendations on the echocardiographic assessment of aortic valve stenosis: a focused update from the European Association of Cardiovascular Imaging and the American Society of Echocardiography.J Am Soc Echocardiogr. 2017; 30: 372-392
- Classification of normal/abnormal heart sound recordings: the PhysioNet/Computing in Cardiology Challenge 2016.Comput Cardiol (2010). 2016; : 609-612
- Narrative review of the role of artificial intelligence to improve aortic valve disease management.J Thorac Dis. 2021; 13: 396-404
- Artificial intelligence-assisted auscultation of heart murmurs: validation by virtual clinical trial.Pediatr Cardiol. 2019; 40: 623-629
- Deep learning algorithm for automated cardiac murmur detection via a digital stethoscope platform.J Am Heart Assoc. 2021; 10e019905
- Cardiac auscultation in the modern era: premature requiem or Phoenix rising?.Cardiol Rev. 2017; 25: 205-210
- Accuracy of cardiac auscultation in the era of Doppler-echocardiography: a comparison between cardiologists and internists.Int J Cardiol. 2010; 138: 308-310
- Competency in cardiac examination skills in medical students, trainees, physicians, and faculty: a multicenter study.Arch Intern Med. 2006; 166: 610-616
Article Info
Publication History
Published online: May 27, 2022
Footnotes
Funding: The study was supported by Sanolla, Nesher, Israel.
Conflicts of Interest: The study was supported by Sanolla. NBH and DA are employees of Sanolla. AS is a consultant for Sanolla and holds stock options in Sanolla. SB is the medical director of Sanolla.
Authorship: All authors had access to the data and a role in writing the manuscript.
Identification
Copyright
© 2022 Elsevier Inc. All rights reserved.
