A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram

Gómez-Quintana, Sergi and Schwarz, Christoph E. and Shelevytsky, Ihor and Shelevytska, Victoriya and Semenova, Oksana and Factor, Andreea and Popovici, Emanuel and Temko, Andriy (2021) A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram. Healthcare, 9 (2). pp. 169-188. ISSN 2227-9032

[img] Text

Download (6MB)
Official URL: https://www.mdpi.com/journal/healthcare


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.

Item Type: Article
Additional Information: Citation: Gómez-Quintana, S.; Schwarz, C.E.; Shelevytsky, I.; Shelevytska, V.; Semenova, O.; Factor, A.; Popovici, E.; Temko, A. A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram. Healthcare 2021, 9, 169. https://doi.org/10.3390/healthcare9020169 Идентификационный номер: WOS:000622574300001 Идентификатор PubMed: 33562544
Uncontrolled Keywords: patent ductus arteriosus; phonocardiogram; heart sound; neonates; congenital heart defects; machine learning; boosted decision trees
Subjects: Pediatrics
Divisions: Faculty of Postgraduate Education > Department of Pediatrics, family medicine and clinical laboratory diagnostics FPE
Depositing User: Елена Шрамко
Date Deposited: 23 Mar 2021 08:46
Last Modified: 09 Jan 2023 13:25
URI: http://repo.dma.dp.ua/id/eprint/6365

Actions (login required)

View Item View Item