Auditory-inspired heart sound temporal analysis for patent ductus arteriosus

Persistent patency of the arterial duct represents one of the most common lesions in the field of congenital cardiac disease. Failure of the ductus arteriosus closed within 48-96 hours of postnatal age results in a left to right shunt across the ductus and overloading of the pulmonary circulation. This is more likely to happen in premature neonates with respiratory distress syndrome. The assessment of the patent ductus arteriosis (PDA) with simple and noninvasive measurement equipment, such as phonocardiography (PCG), could be of great significance. Inspired by the auditory processing, we propose the cochlear spectrogram (CS) which is a novel spectro-temporal representation method to describe the cochlear responses of human hearing. Furthermore, the temporal correlogram (TC) method is used for analyze the temporal features of heart sounds. The preliminary study results recruited two infant cases of typical PDA, the heart murmur were recorded before and after-transcatheter closure of PDA using the AMPLATZER ductal occlude system. The proposed method could be used to evaluate the procedure response. Furthermore, we utilized the auditory-inspired heart sound temporal analysis with the combination of CS and TC method to predict closure outcome of preterm newborns with PDA in the future.

[1]  Neil Marlow,et al.  The EPICure Study: Outcomes to Discharge From Hospital for Infants Born at the Threshold of Viability , 2000, Pediatrics.

[2]  Malcolm Slaney Connecting correlograms to neurophysiology and psychoacoustics , 1997 .

[3]  Roy D. Patterson,et al.  A Dynamic Compressive Gammachirp Auditory Filterbank , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  G. E. Twente,et al.  Patent ductus arteriosus , 2013 .

[5]  D. Schneider,et al.  Patent Ductus Arteriosus , 2006, Circulation.

[6]  Malcolm Slaney,et al.  Lyon's Cochlear Model , 1997 .

[7]  Richard F. Lyon,et al.  A computational model of filtering, detection, and compression in the cochlea , 1982, ICASSP.

[8]  Qi Li,et al.  An auditory-based transfrom for audio signal processing , 2009, 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[9]  Qi Li,et al.  An Auditory-Based Feature Extraction Algorithm for Robust Speaker Identification Under Mismatched Conditions , 2011, IEEE Transactions on Audio, Speech, and Language Processing.