Segmented vs. Non-Segmented Heart Sound Classification: Impact of Feature Extraction and Machine Learning Models

Cardiovascular diseases remain a leading cause of mortality worldwide, emphasizing the importance of early diagnosis. Heart sound analysis offers a non-invasive avenue for detecting cardiac abnormalities. This study systematically evaluates the effect of segmentation on phonocardiogram (PCG) classification performance. Unlike conventional fixed-window or HSMM-based methods, a data-adaptive segmentation approach combining Shannon energy and Otsu thresholding is proposed. After segmentation, features are extracted using Empirical Mode Decomposition (EMD) and Mel-Frequency Cepstral Coefficients (MFCCs), followed by classification with k-Nearest Neighbor (kNN), Support Vector Machine (SVM), and Random Forest (RF). Experiments on the PhysioNet/CinC 2016 and Pascal datasets revealed that segmentation markedly enhances classification accuracy. The optimal results were achieved using kNN with segmented EMD features, attaining 99.97% accuracy, 99.98% sensitivity, and 99.96% specificity; segmented MFCC features also provided high accuracy (99.37%). In contrast, non-segmented models yielded substantially lower performance. Principal Component Analysis (PCA) is applied for dimensionality reduction, preserving classification efficiency while minimizing computational cost. These findings demonstrate the critical importance of effective segmentation in heart sound classification and establish the proposed Shannon–Otsu-based method as a robust, interpretable, and resource-efficient tool for automated cardiac diagnostics. Using annotated PhysioNet recordings, segmentation achieved ~90% sensitivity for S1/S2 detection. A limitation is the absence of full segment annotations in the Pascal dataset, which prevents comprehensive timing-error evaluation.