Key result
A deep learning algorithm for analyzing phonocardiographic signals achieved F1 scores >98% and specificities up to 99% for classifying four common valvular pathologies and normal heart sounds.
Why the study?
Can deep learning algorithms accurately classify normal and pathological heart sounds from phonocardiographic signals?
Can deep learning algorithms accurately classify normal and pathological heart sounds from phonocardiographic signals?
Effect estimate: F1 score >98%
Deep learning algorithms applied to phonocardiographic signals demonstrate high accuracy in classifying normal and pathological heart sounds, suggesting potential for assisted diagnosis systems.
May support AI-assisted phonocardiogram screening; leaves open prospective clinical validation before adoption.
Heart sounds are mainly the expressions of the opening and closing of the heart valves. Some sounds are produced by the interruption of laminar blood flow as it turns into turbulent flow, which is explained by abnormal functioning of the valves. The analysis of the phonocardiographic signals has made it possible to indicate that the normal and pathological records differ from each other concerning both temporal and spectral features. The present work describes the design and implementation based on deep neural networks and deep learning for the binary and multiclass classification of four common valvular pathologies and normal heart sounds. For feature extraction, three different techniques were considered: Discrete Wavelet Transform, Continuous Wavelet Transform and Mel Frequency Cepstral Coefficients. The performance of both approaches reached F1 scores higher than 98% and specificities in the “Normal” class of up to 99%, which considers the cases that can be misclassified as normal. These results place the present work as a highly competitive proposal for the generation of systems for assisted diagnosis.
No takes yet. Share an insight, caveat, or question.
Flores-Alonso et al. (2022) studied Heart valve diseases. Deep learning algorithm based on deep neural networks was evaluated on Binary and multiclass classification performance (F1 score and specificity) (F1 score >98%). A deep learning algorithm for analyzing phonocardiographic signals achieved F1 scores >98% and specificities up to 99% for classifying four common valvular pathologies and normal heart sounds.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: