Key result
X-CBNet deep learning achieves ~99% accuracy classifying valvular heart disease from phonocardiogram signals.
Why the study?
Traditional auscultation is subjective and automated models often lack interpretability, creating a need for accurate, explainable multi-class diagnostic tools for valvular heart disease using phonocardiograms.
Does the X-CBNet deep learning framework accurately predict and classify valvular heart disease using phonocardiogram signals?
Does the X-CBNet deep learning framework accurately predict and classify valvular heart disease using phonocardiogram signals?
The X-CBNet deep learning framework demonstrates high accuracy (>99%) and interpretability in classifying valvular heart diseases from phonocardiogram signals, offering a potential tool for automated clinical auscultation.
Valvular Heart Disease (VHD), caused by malfunctioning heart valves, poses significant diagnostic challenges due to the complexity of heart sound patterns and variability in clinical presentations. Traditional auscultation methods are subjective, and existing automated models often function as black boxes, offering limited insight into the reasoning behind predictions. Therefore, there is a pressing need for accurate, interpretable, and multi-class diagnostic tools to aid clinicians in early and reliable detection of VHD using phonocardiogram (PCG) signals. X-CBNet, a convolutional neural network (CNN) followed by a bidirectional long short-term memory (Bi-LSTM) network framework, is employed in this research to harness deep learning’s capability to achieve high diagnostic accuracy while ensuring interpretability through explainable AI methods. Melspectrograms are used to capture essential features of the phonocardiograms. The proposed model is designed as a five-class classifier distinguishing between aortic stenosis, mitral stenosis, mitral regurgitation, mitral valve prolapse, and normal heart sounds. Gradient-weighted class activation mapping (Grad-CAM) is utilized for explainability, generating heatmaps that visualize model decision-making. The proposed X-CBNet model achieved an overall accuracy of 99.15%. Per-class accuracies are: Normal 99.15%, Aortic Stenosis 98.43%, Mitral Regurgitation 98.79%, Mitral Stenosis 99.58%, and Mitral Valve Prolapse 99.80%. The model also achieved a macro-average AUC of 0.99 and a micro-average AUC of 0.98, while maintaining a misclassification rate of less than 1%. The Grad-CAM heatmaps further validate model decisions by highlighting class-discriminative features. The robust performance demonstrates that the proposed model is suitable for real-time clinical applications, offering enhanced transparency through the integration of explainable AI.
No takes yet. Share an insight, caveat, or question.
Padhy et al. (2025) studied Valvular Heart Disease (n=764). X-CBNet (CNN-BiLSTM framework) vs. Existing deep learning classifiers was evaluated on Overall classification accuracy. The X-CBNet deep learning framework achieved an overall accuracy of 99.15% in classifying valvular heart diseases from phonocardiogram signals while providing interpretability via Grad-CAM.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: