Artificial Intelligence-Assisted Auscultation of Heart Murmurs: Validation by Virtual Clinical Trial
Artificial intelligence (AI) has potential to improve the accuracy of screening for valvular and congenital heart disease by auscultation. However, despite recent advances in signal processing and classification algorithms focused on heart sounds, clinical acceptance of this technology has been limited, in part due to lack of objective performance data. We hypothesized that a heart murmur detection algorithm could be quantitatively and objectively evaluated by virtual clinical trial. All cases from the Johns Hopkins Cardiac Auscultatory Recording Database (CARD) with either a pathologic murmur, an innocent murmur or no murmur were selected. The test algorithm, developed independently of CARD, analyzed each recording using an automated batch processing protocol. 3180 heart sound recordings from 603 outpatient visits were selected from CARD. Algorithm estimation of heart rate was similar to gold standard. Sensitivity and specificity for detection of pathologic cases were 93% (CI 90–95%) and 81% (CI 75–85%), respectively, with accuracy 88% (CI 85–91%). Performance varied according to algorithm certainty measure, age of patient, heart rate, murmur intensity, location of recording on the chest and pathologic diagnosis. This is the first reported comprehensive and objective evaluation of an AI-based murmur detection algorithm to our knowledge. The test algorithm performed well in this virtual clinical trial. This strategy can be used to efficiently compare performance of other algorithms against the same dataset and improve understanding of the potential clinical usefulness of AI-assisted auscultation.
KeywordsAuscultation Artificial intelligence Algorithms Physical diagnosis/cardiovascular Congenital heart disease Valvular heart disease
We acknowledge Dhananjay Vaidya, MBBS, PhD, MPH, Johns Hopkins Biostatistics, Epidemiology and Data Management Core for assistance with statistical analysis.
Compliance with Ethical Standards
Conflict of interest
Andreas J. Reinisch is an employee and owner of CSD Labs. Michael J. Unterberger is an employee of CSD Labs. Andreas J. Schriefl is an employee and owner of CSD Labs. W. Reid Thompson declares no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors. The study dataset contained no protected health information; therefore, the study was exempted from Institutional Review Board approval.
- 16.Tuchinda C, Thompson WR (2001) Cardiac auscultatory recording database: delivering heart sounds through the internet. Proc AMIA Symp 2001:716–720Google Scholar
- 20.Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, Castells F, Roig JM, Silva I, Johnson AE, Syed Z, Schmidt SE, Papadaniil CD, Hadjileontiadis L, Naseri H, Moukadem A, Dieterlen A, Brandt C, Tang H, Samieinasab M, Samieinasab MR, Sameni R, Mark RG, Clifford GD (2016) An open access database for the evaluation of heart sound algorithms. Physiol Meas 37:2181–2213CrossRefPubMedGoogle Scholar
- 22.Bailey JJ, Berson AS, Garson A, Horan LG, Macfarlane PW, Mortara DW, Zywietz C (1990) Recommendations for standardization and specifications in automated electrocardiography: bandwidth and digital signal processing. A report for health professionals by an ad hoc writing group of the Committee on Electrocardiography and Cardiac Electrophysiology of the Council on Clinical Cardiology. Am Heart Assoc Circ 81:730–739Google Scholar
- 24.Wu G, Shen D, Sabuncu M (2016) Machine learning and medical imaging. Academic Press, New York, pp 197–212Google Scholar