Abstract: S. Ghiasi, M. Abdollahpur, N. Madani, A. Ghaffari (2017)

Introduction: Auscultation of heart sounds using digital stethoscope technology is an effective method for the diagnosis of various cardiovascular disorders. The characteristics of phonocardiography (PCG) signals can be represented by developing a computer based algorithm as a complementary tool to facilitate clinicians. Aims: This paper aims to address an effective feature extraction and classification technique to improve the detection of two common categories of cardiac arrhythmias, Mitral Valve Prolapse (MVP) and Coronary Artery Disease (CAD) using the heart sound recordings from PhysioNet/Computing in Cardiology 2016 challenge. Methods: Band pass Butterworth filtering is employed to pre-process PCG signals. After detecting heart beats using common segmentation algorithms, beats which are less contaminated by noise are selected using a combination of time and time-frequency analysis. Since heart murmurs are engendered from various abnormalities in the heart, they show different characteristics. To characterize these complexities in each abnormality, Recurrence Quantification Analysis is applied. In this method the Recurrence plots which represent the mechanisms underlying the heart dynamics are quantified into recursive parameters. These set of nonlinear features show a great discrimination between classes. The resulting features are transformed to a new space using Fisher's discriminant analysis (FDA), a dimensionally reduction technique, to reduce the computational complexity of the algorithm. The classification process is in two stage. First, the new dimension-reduced feature vector is the input of the fuzzy C-means clustering (FCM) to predict normal and abnormal class. Then, the obtained 10 dimensional feature vector form RQA analysis feds into a pattern recognition artificial neural network (ANN) to classify CAD and MVP recordings Results: Using PCG signals of CAD, MVP and normal recordings from PhysioNet/Computing in Cardiology 2016, normal signals are easily discriminated from abnormal recordings and for classifying CAD from MVP recordings the sensitivity, specificity and accuracy of 0.853, 0.844 and 0.848 are achieved on the test set, respectively., keywords

Please note: The abstracts of the bibliography database may underly other copyrights.

Ihr Browser versucht gerade eine Seite aus dem sogenannten Internet auszudrucken. Das Internet ist ein weltweites Netzwerk von Computern, das den Menschen ganz neue Möglichkeiten der Kommunikation bietet.

Da Politiker im Regelfall von neuen Dingen nichts verstehen, halten wir es für notwendig, sie davor zu schützen. Dies ist im beidseitigen Interesse, da unnötige Angstzustände bei Ihnen verhindert werden, ebenso wie es uns vor profilierungs- und machtsüchtigen Politikern schützt.

Sollten Sie der Meinung sein, dass Sie diese Internetseite dennoch sehen sollten, so können Sie jederzeit durch normalen Gebrauch eines Internetbrowsers darauf zugreifen. Dazu sind aber minimale Computerkenntnisse erforderlich. Sollten Sie diese nicht haben, vergessen Sie einfach dieses Internet und lassen uns in Ruhe.

Die Umgehung dieser Ausdrucksperre ist nach §95a UrhG verboten.

Mehr Informationen unter www.politiker-stopp.de.

Nonlinear analysis of heart sounds for the detection of cardiac disorders using recurrence quantification analysis