Detecting patent ductus arteriosus in neonatal phonocardiograms

Mohammad Ali Zamani, Ethan Grooby, James Lacey, Atul Malhotra, Faezeh Marzbanrad

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

Abstract

During fetal development, ductus arteriosus allows blood ejected by the right ventricle to bypass the lung. The persistence of this ductus after birth however is considered pathological and is termed patent ductus arteriosus (PDA). Using phonocardiograms (PCGs) acquired from a digital stethoscope, the objective is to explore discriminatory features and statistically analyse them. In this research, we obtained 48 PCG recordings from 41 neonates. 17 recordings (15 neonates) had PDA, 8 recordings (7 neonates) had other heart structure abnormalities identified during echocardiography and were excluded in this study, and 23 recordings (21 neonates) had no heart structure abnormalities based on clinical assessment. Recordings were denoised using non-negative matrix co-factorization. Denoised phonocardiograms were then segmented into S1, systolic, S2, and diastolic periods. Temporal (durations and maximum values), statistical (variance, skewness, and kurtosis), and power (total power, and 25-100Hz, 25-45 Hz, 45-80 Hz, 100-200 Hz, and 200-400Hz band powers) were obtained for each heart segment and relative ratios between segments calculated. Statistical tests were then performed to identify significant features for discriminating PCG recordings.

Original languageEnglish
Title of host publicationComputing in Cardiology, CinC 2023
EditorsGari Clifford, Matthew Reyna, Herman Taylor, May Wang, Omer Inan, Reza Sameni, Ali Bahrami Rad
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9798350382525
DOIs
Publication statusPublished - 2023
EventComputing in Cardiology 2023 - Atlanta, United States of America
Duration: 1 Oct 20234 Oct 2023
Conference number: 50th
https://cinc2023.org (Website)
https://cinc.org/final_program_papers_2023/ (Proceedings)

Publication series

NameComputing in Cardiology
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)2325-8861
ISSN (Electronic)2325-887X

Conference

ConferenceComputing in Cardiology 2023
Abbreviated titleCinC 2023
Country/TerritoryUnited States of America
CityAtlanta
Period1/10/234/10/23
Internet address

Cite this