Key result
Low-cost AI stethoscope classifies normal and abnormal heart sounds with up to ~99% accuracy.
Why the study?
Accurate auscultation for cardiovascular and respiratory disease screening requires domain expertise that resource-constrained countries often lack.
Does a low-cost AI-enabled digital stethoscope accurately distinguish between normal and cardiovascular disease-related heart sounds?
Does a low-cost AI-enabled digital stethoscope accurately distinguish between normal and cardiovascular disease-related heart sounds?
Effect estimate: Accuracy 89.9%-98.5%
A prototype low-cost AI-enabled digital stethoscope demonstrated high validation accuracy (89.9%-98.5%) in classifying normal versus abnormal heart sounds, showing potential for automated CVD screening in resource-constrained settings.
May support automated screening in low-resource settings; leaves open prospective clinical validation.
Auscultation plays a significant role in the screening and clinical diagnosis of cardiovascular and respiratory diseases (CVDs). Experience and domain expertise knowledge are required for accurate diagnosis. However, many resource-constrained countries may not have sufficient expertise. This study, therefore, focuses on the preliminary development and evaluation of a low-cost digital stethoscope which leverages machine learning to distinguish between normal and cardiovascular disease (CVD) related heart sounds. A prototype of a battery-powered digital stethoscope was developed, and the preliminary results showed that the system could capture heart sounds with good quality. Using a PhysioNet Dataset, Machine Learning models (Fine-K-Nearest neighbour FKNN, Gaussian kernel support vector machines GSVMs and Deep Convolutional Neural Networks CNNs) were trained on temporal-frequency derived features of phonocardiogram signals (PCG) by Wavelet scattering and Short-Time-Fast-Fourier Transform (SFFT). The overall validation accuracy range was 89.9%-98.5% and the models could effectively classify normal and abnormal heart sounds. These promising results are essential for screening and the early detection of cardiovascular diseases, enabling timely intervention and disease management in low-resource countries. The work contributes to AI research aimed at enhancing CVD diagnosis and screening.
No takes yet. Share an insight, caveat, or question.
Chikweto et al. (2024) studied Cardiovascular diseases. Low-cost AI-enabled digital stethoscope with machine learning models was evaluated on Classification of normal and abnormal heart sounds (Accuracy 89.9%-98.5%). A low-cost AI-enabled digital stethoscope using machine learning models successfully classified normal and abnormal heart sounds with an overall validation accuracy ranging from 89.9% to 98.5%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: