Key result
PCG classification using KDE and a fine-tuned VGG19 model achieves 97% overall accuracy.
Why the study?
Traditional cardiac auscultation is not always feasible or affordable, and existing automated CVD screening methods rely on complex preprocessing steps and heart cycle segmentation.
A machine learning approach using kernel density estimation for signal duration extraction and a fine-tuned VGG19 model achieves high accuracy (0.97) in classifying normal and abnormal heart sounds.
The World Health Organization (WHO) highlights that cardiovascular diseases (CVDs) are one of the leading causes of death globally, with an estimated rise to over 23.6 million deaths by 2030. This alarming trend can be attributed to our unhealthy lifestyles and lack of attention towards early CVD diagnosis. Traditional cardiac auscultation, where a highly qualified cardiologist listens to the heart sounds, is a crucial diagnostic method, but not always feasible or affordable. Therefore, developing accessible and user-friendly CVD recognition solutions can encourage individuals to integrate regular heart screenings into their routine. Although many automatic CVD screening methods have been proposed, most of them rely on complex prepocessing steps and heart cycle segmentation processes. In this work, we introduce a simple and efficient approach for recognizing normal and abnormal PCG signals using Physionet data. We employ data selection techniques such as kernel density estimation (KDE) for signal duration extraction, signal-to-noise Ratio (SNR), and GMM clustering to improve the performance of 17 pretrained Keras CNN models. Our results indicate that using KDE to select the appropriate signal duration and fine-tuning the VGG19 model results in excellent classification performance with an overall accuracy of 0.97, sensitivity of 0.946, precision of 0.944, and specificity of 0.946.
No takes yet. Share an insight, caveat, or question.
Barnawi et al. (2023) studied Cardiovascular diseases (normal and abnormal PCG signals). KDE for signal duration extraction and fine-tuned VGG19 model vs. Other pretrained Keras CNN models was evaluated on Classification performance (overall accuracy). A PCG classification method using KDE for signal duration selection and a fine-tuned VGG19 model achieved excellent performance with an overall accuracy of 0.97 and sensitivity of 0.946.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: