A deep neural network using audio files for detection of aortic stenosis
Open Access
- 19 April 2022
- journal article
- research article
- Published by Wiley in Clinical Cardiology
- Vol. 45 (6) , 657-663
Abstract
Background: Although aortic stenosis (AS) is the most common valvular heart disease in the western world, many affected patients remain undiagnosed. Auscultation is a readily available screening tool for AS. However, it requires a high level of professional expertise.Hypothesis: An AI algorithm can detect AS using audio files with the same accuracy as experienced cardiologists.Methods: A deep neural network (DNN) was trained by preprocessed audio files of 100 patients with AS and 100 controls. The DNN's performance was evaluated with a test data set of 40 patients. The primary outcome measures were sensitivity, specificity, and F1‐score. Results of the DNN were compared with the performance of cardiologists, residents, and medical students.Results: Eighteen percent of patients without AS and 22% of patients with AS showed an additional moderate or severe mitral regurgitation. The DNN showed a sensitivity of 0.90 (0.81–0.99), a specificity of 1, and an F1‐score of 0.95 (0.89–1.0) for the detection of AS. In comparison, we calculated an F1‐score of 0.94 (0.86–1.0) for cardiologists, 0.88 (0.78–0.98) for residents, and 0.88 (0.78–0.98) for students.Conclusions: The present study shows that deep learning‐guided auscultation predicts significant AS with similar accuracy as cardiologists. The results of this pilot study suggest that AI‐assisted auscultation may help general practitioners without special cardiology training in daily practice.Keywords
This publication has 27 references indexed in Scilit:
- S1 and S2 Heart Sound Recognition Using Deep Neural NetworksIEEE Transactions on Biomedical Engineering, 2016
- 5-year outcomes of transcatheter aortic valve replacement compared with standard treatment for patients with inoperable aortic stenosis (PARTNER 1): a randomised controlled trialThe Lancet, 2015
- Aortic Stenosis in the ElderlyJACC, 2013
- The promise of computer-assisted auscultation in screening for structural heart disease and clinical teaching : review articleCardioVascular Journal of Africa, 2012
- Respiratory modulation of heart sound morphologyAmerican Journal of Physiology-Heart and Circulatory Physiology, 2009
- Wither the Cardiac Physical Examination?JACC, 2006
- Competency in Cardiac Examination Skills in Medical Students, Trainees, Physicians, and FacultyArchives of internal medicine (1960), 2006
- Computer-assisted detection of systolic murmurs associated with hypertrophic cardiomyopathy: a pilot study.2004
- Cardiac Auscultatory Skills of Internal Medicine and Family Practice TraineesJAMA, 1997
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980