The MCAF-TabNet deep learning framework achieved 98.42% accuracy and an AUC of 0.991 for heart sound classification, outperforming state-of-the-art CNN and CRNN architectures.
Does MCAF-TabNet improve heart sound classification accuracy compared to state-of-the-art architectures in a benchmark PCG dataset?
MCAF-TabNet provides a highly accurate and interpretable deep learning framework for automated heart sound classification, potentially aiding in telehealth and point-of-care diagnostics.
Accurate interpretation of heart sounds remains a fundamental yet challenging task in the early diagnosis of cardiovascular diseases. Traditional auscultation relies heavily on clinical expertise, whereas automated approaches often struggle with signal variability, background noise, and overlapping murmurs that obscure vital diagnostic cues. Conventional machine learning methods rely on handcrafted features and fail to capture the intricate temporal–spectral dependencies inherent in phonocardiogram (PCG) signals. Deep learning models, though powerful, frequently lack interpretability and require large datasets, limiting their adoption in real-world clinical settings.To address these challenges, this paper presents MCAF-TabNet, an interpretable deep learning framework for heart sound classification. The model integrates a Multiscale Convolutional Encoder for hierarchical temporal–spectral feature extraction, a Channel Attention Module for adaptive channel reweighting, and a Feature Fusion Layer that combines deep representations with handcrafted acoustic descriptors. The fused features are processed by a TabNet Classifier, enabling sequential, attention-based feature selection and transparent decision-making. Experimental results on a benchmark PCG dataset demonstrate that the proposed framework achieves an accuracy of 98.42% and an AUC of 0.991, outperforming state-of-the-art CNN, CRNN, and attention-based architectures.The findings show that MCAF-TabNet effectively balances accuracy, interpretability, and robustness, overcoming the limitations of traditional models in noisy and data-limited conditions. Its transparent architecture not only enhances trust in automated diagnosis but also aligns closely with clinical decision-making principles. This work establishes MCAF-TabNet as a reliable foundation for intelligent, interpretable, and scalable cardiac auscultation systems, paving the way for practical deployment in telehealth and point-of-care diagnostics.
Ravi et al. (Thu,) conducted a other in Cardiovascular diseases. MCAF-TabNet vs. State-of-the-art CNN, CRNN, and attention-based architectures was evaluated on Heart sound classification accuracy. The MCAF-TabNet deep learning framework achieved 98.42% accuracy and an AUC of 0.991 for heart sound classification, outperforming state-of-the-art CNN and CRNN architectures.