Automated noninvasive detection of coronary artery disease using wavelet-based neural networks

This study examines the utility of neural networks for detecting coronary artery disease noninvasively by using clinical examination variables and extracting useful information from the diastolic heart sounds associated with coronary occlusions. It has been widely reported that coronary stenoses produce sounds due to the turbulent blood flow in these vessels. These complex and highly attenuated signals taken from recordings made in of soundproof room were detected and analysed to provide the feature set based on extrema representation of the fast wavelet transform coefficients. In addition, some physical examination variables such as sex, age, body weight, smoking condition, plus diastolic and systolic blood pressures were included in the feature vector. This feature vector was used as the input pattern to the neural network