A framework for AI-assisted detection of Patent Ductus Arteriosus from neonatal phonocardiogram

Show simple item record

dc.contributor.author Gómez-Quintana, Sergi
dc.contributor.author Schwarz, Christoph E.
dc.contributor.author Shelevytsky, Ihor
dc.contributor.author Shelevytska, Victoriya
dc.contributor.author Semenova, Oksana
dc.contributor.author Factor, Andreea
dc.contributor.author Popovici, Emanuel
dc.contributor.author Temko, Andriy
dc.date.accessioned 2022-08-03T14:39:40Z
dc.date.available 2022-08-03T14:39:40Z
dc.date.issued 2021-02-05
dc.identifier.citation Gómez-Quintana, S., Schwarz, C. E., Shelevytsky, I., Shelevytska, V., Semenova, O.,Factor, A., Popovici, E. and Temko, A. (2021) 'A framework for AI-assisted detection of Patent Ductus Arteriosus from neonatal phonocardiogram', Healthcare, 9(2), 169 (19pp). doi: 10.3390/healthcare9020169 en
dc.identifier.volume 9 en
dc.identifier.issued 2 en
dc.identifier.startpage 1 en
dc.identifier.endpage 19 en
dc.identifier.uri http://hdl.handle.net/10468/13450
dc.identifier.doi 10.3390/healthcare9020169 en
dc.description.abstract The current diagnosis of Congenital Heart Disease (CHD) in neonates relies on echocardiography. Its limited availability requires alternative screening procedures to prioritise newborns awaiting ultrasound. The routine screening for CHD is performed using a multidimensional clinical examination including (but not limited to) auscultation and pulse oximetry. While auscultation might be subjective with some heart abnormalities not always audible it increases the ability to detect heart defects. This work aims at developing an objective clinical decision support tool based on machine learning (ML) to facilitate differentiation of sounds with signatures of Patent Ductus Arteriosus (PDA)/CHDs, in clinical settings. The heart sounds are pre-processed and segmented, followed by feature extraction. The features are fed into a boosted decision tree classifier to estimate the probability of PDA or CHDs. Several mechanisms to combine information from different auscultation points, as well as consecutive sound cycles, are presented. The system is evaluated on a large clinical dataset of heart sounds from 265 term and late-preterm newborns recorded within the first six days of life. The developed system reaches an area under the curve (AUC) of 78% at detecting CHD and 77% at detecting PDA. The obtained results for PDA detection compare favourably with the level of accuracy achieved by an experienced neonatologist when assessed on the same cohort. en
dc.description.sponsorship Science Foundation Ireland (Centre for Research Training in Artificial Intelligence under Grant No 18/CRT/6223; TIDA 17/TIDA/504); Wellcome Trust Seed Award 200704/Z/16/Z); Grand Challenges Canada (R-ST-POC-1707-07709); Deutsche Forschungsgemeinschaft (420536451) en
dc.format.mimetype application/pdf en
dc.language.iso en en
dc.publisher MDPI en
dc.rights © 2021, the Authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. en
dc.rights.uri https://creativecommons.org/licenses/by/4.0/ en
dc.subject Heart sound en
dc.subject Neonates en
dc.subject Congenital heart defects en
dc.subject Machine learning en
dc.subject Boosted decision trees en
dc.subject Patent ductus arteriosus en
dc.subject Phonocardiogram en
dc.title A framework for AI-assisted detection of Patent Ductus Arteriosus from neonatal phonocardiogram en
dc.type Article (peer-reviewed) en
dc.internal.authorcontactother Emanuel Popovici, Electrical & Electronic Engineering, University College Cork, Cork, Ireland. +353-21-490-3000 Email: e.popovici@ucc.ie en
dc.internal.availability Full text available en
dc.date.updated 2022-08-03T14:28:01Z
dc.description.version Published Version en
dc.internal.rssid 595538672
dc.internal.wokid WOS:000622574300001
dc.contributor.funder Science Foundation Ireland en
dc.contributor.funder Deutsche Forschungsgemeinschaft en
dc.contributor.funder Wellcome Trust en
dc.contributor.funder Grand Challenges Canada en
dc.description.status Peer reviewed en
dc.identifier.journaltitle Healthcare en
dc.internal.copyrightchecked Yes
dc.internal.licenseacceptance Yes en
dc.internal.IRISemailaddress e.popovici@ucc.ie en
dc.identifier.articleid 169 en
dc.identifier.eissn 2227-9032


Files in this item

This item appears in the following Collection(s)

Show simple item record

© 2021, the Authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Except where otherwise noted, this item's license is described as © 2021, the Authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
This website uses cookies. By using this website, you consent to the use of cookies in accordance with the UCC Privacy and Cookies Statement. For more information about cookies and how you can disable them, visit our Privacy and Cookies statement