Discovery of multiple level heart-sound morphological variability resulting from changes in physiological states

Heart sounds carry information about the mechanical activity of the cardiovascular system. This information includes the specific physiological state of the subject, and short term variability related to the respiratory cycle. The interpretation of the sounds and extraction of changes in the physiological state, while monitoring short term variability is still an open problem and is the subject of this paper. We present a novel computational framework for analysis of data with multi-level variability, caused by externally induced changes. The framework presented includes an initial clustering of the first heart sound (S1) according to the morphology, and further aggregation of clusters into super-clusters. The clusters and super clusters are two methods of data segmentation, each reflecting a different level of variability in the data. The framework is applied to heart sounds recorded during laparoscopic surgeries of six patients. Procedures of this kind include anesthesia and abdominal insufflation, which together with the respiratory cycle, induce changes to the heart sound signal. We demonstrate a separation of the heart sound morphology according to different physiological states. The physiological states considered are the respiratory cycle, and the stages of the surgery. We achieve results of 90 ± 4% classification accuracy of heart beats to operation stages. The proposed framework is general and can be used to analyze data characterized by multi-level variability for various other (biomedical) applications.