ECHO: Enhanced Cardiovascular Health through Audible Observations

Cardiovascular diseases (CVDs) stand as the primary reason for worldwide deaths. The phonocardiogram (PCG) analysis provides an inexpensive screening tool which uses non-invasive methods yet automated systems encounter two main obstacles from background interference, sensor precision issues and unbalanced patient data distribution that makes it hard to detect rare cardiac abnormalities. The research develops and tests an original deep learning system which solves these problems. The pre-processing stage of this method divides PCG signals into cardiac cycles before using wavelet-based denoising to enhance Signal-to-Noise Ratio (SNR) values. The system generates a new hybrid feature map through vertical stacking of multiple feature sets which includes Mel-spectrograms and MFCCs for sensor distortion resistance and wavelet and statistical features for additive noise resistance. The network accepts the complete feature map as a two-dimensional input which it processes through a custom Convolutional Neural Network (CNN). The network architecture receives an improvement through the addition of a Convolutional Block Attention Module (CBAM) which enables the model to discover important diagnostic areas through its ability to concentrate on essential spatial and channel interactions. The training approach solves class imbalance problems through data-level minority class oversampling and algorithmic Focal Loss function application which makes the model focus on difficult-to-classify samples. The system achieved an 85% sensitivity rate and F1-score of [0.85] when tested on the 2016 PhysioNet Challenge dataset to outperform standard models without the proposed feature map and loss function. The research demonstrates that uniting hybrid feature development with deep learning attention mechanisms and training methods for handling imbalanced data creates an optimal system for PCG classification tasks. The developed system provides a dependable method for automatic cardiac screening which works well in both hospital-based and home-based patient monitoring systems.