Effectiveness of wilson amplitude for the detection of murmur from the pcg records

Abstract

Methods employed for the automatic detection of valve ailments from the heart records is a skilled task in cardiology. However, automated approaches, proposed for envisaging the cardiovascular diseases greatly depend on the features mined from the heart sound. The analysis of Phonocardiogram (PCG) signals, offers adequate information about the functioning of the heart. Feature extraction techniques in the time domain have analytical simplicity and less computational complexity. In this paper, the effectiveness of the feature namely Wilson amplitude for the detection of murmur from heart signal is investigated and is tested with different threshold (5–50 mV) levels. It is found that the Wilson amplitude at 20 mV threshold is capable to detect the murmur from PCG signal with 88.33% accuracy, 76.67% sensitivity and 100% specificity than other thresholds.