Abstract: A system and method for noninvasively detecting coronary artery disease. The system and method utilize a vasodilator drug to increase the signal-to-noise ratio of an acoustic signal that represents diastolic heart sounds of a patient. A wavelet transform is performed on the acoustic signal to provide parameters for a feature vector. Scaled clinical examination parameters such as a patient's sex, age, body weight, smoking condition, blood pressure, and family history are also included in the feature vector. The feature vector is used as an input pattern to neural networks. The output of the neural networks represent a diagnosis of coronary stenosis in a patient.

Abstract: A method and system for non-invasively detecting Coronary Artery Disease. The method comprises analyzing the diastolic heart sounds detected from a patient's chest cavity during the diastolic portion of the heart cycle in order to identify a low level auditory component associated with turbulent blood flow in partially occluded coronary arteries. These diastolic heart sounds are modeled using advanced signal processing techniques such as Autoregressive (AR), Autoregressive Moving Averaging (ARMA) and Eigenvector methods, so that the presence of such an auditory component may be reliably indicated even under high noise conditions. The system includes an acoustic transducer, pulse sensor device, signal processor means and a diagnostic display. Additionally, the system includes a controller for automatically sequencing data collection, analysis and display stages, therefore requiring a minimum of operator interaction.