Screening for abnormal heart sounds and murmurs by implementing neural networks

[摘要] This thesis is concerned with the testing of an 'auscultation jacket as a means of recordingheart sounds and electrocardiography (ECG) data from patients. A classification systembased on Neural Networks, that is able to discriminate between normal and abnormal heartsounds and murmurs, has also been developed . The classification system uses the recordeddata as training and testing data. This classification system is proposed to serve as an aid tophysicians in diagnosing patients with cardiac abnormalities. Seventeen normal participantsand 14 participants that suffer from valve-related heart disease have been recorded with thejacket. The 'auscultation jacket shows great promise as a wearable health monitoringaid for application in rural areas and in the telemedicine industry. The Neural Networkclassification system is able to differentiate between normal and abnormal heart soundswith a sensitivity of 85.7% and a specificity of 94.1%.

[发布机构] Stellenbosch University