Noise-Robust Contrastive Learning with an MFCC-Conformer For Coronary Artery Disease Detection
This work addresses noise robustness in real-world CAD detection from audio signals, offering an incremental improvement for healthcare applications.
The paper tackled the problem of detecting coronary artery disease from noisy phonocardiogram signals by developing a multichannel noisy-segment rejection algorithm and an MFCC-Conformer classifier, achieving 78.4% accuracy and 78.2% balanced accuracy on 297 subjects, with improvements of 4.1% and 4.3% over a baseline without rejection.
Cardiovascular diseases (CVD) are the leading cause of death worldwide, with coronary artery disease (CAD) comprising the largest subcategory of CVDs. Recently, there has been increased focus on detecting CAD using phonocardiogram (PCG) signals, with high success in clinical environments with low noise and optimal sensor placement. Multichannel techniques have been found to be more robust to noise; however, achieving robust performance on real-world data remains a challenge. This work utilises a novel multichannel energy-based noisy-segment rejection algorithm, using heart and noise-reference microphones, to discard audio segments with large amounts of nonstationary noise before training a deep learning classifier. This conformer-based classifier takes mel-frequency cepstral coefficients (MFCCs) from multiple channels, further helping improve the model's noise robustness. The proposed method achieved 78.4% accuracy and 78.2% balanced accuracy on 297 subjects, representing improvements of 4.1% and 4.3%, respectively, compared to training without noisy-segment rejection.