{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:44:29Z","timestamp":1790775869863,"version":"4.1.0"},"reference-count":44,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,2,5]],"date-time":"2021-02-05T00:00:00Z","timestamp":1612483200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science Foundation Ireland Centre for Research Training in Artificial Intelligence","award":["18\/CRT\/6223"],"award-info":[{"award-number":["18\/CRT\/6223"]}]},{"name":"Wellcome Trust Seed Award","award":["200704\/Z\/16\/Z"],"award-info":[{"award-number":["200704\/Z\/16\/Z"]}]},{"DOI":"10.13039\/501100004828","name":"Grand Challenges Canada","doi-asserted-by":"publisher","award":["R-ST-POC-1707-07709"],"award-info":[{"award-number":["R-ST-POC-1707-07709"]}],"id":[{"id":"10.13039\/501100004828","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science Fundation Ireland TIDA","award":["17\/TIDA\/504"],"award-info":[{"award-number":["17\/TIDA\/504"]}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["420536451"],"award-info":[{"award-number":["420536451"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Healthcare"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/healthcare9020169","type":"journal-article","created":{"date-parts":[[2021,2,5]],"date-time":"2021-02-05T08:33:48Z","timestamp":1612514028000},"page":"169","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram"],"prefix":"10.3390","volume":"9","author":[{"given":"Sergi","family":"G\u00f3mez-Quintana","sequence":"first","affiliation":[{"name":"Electrical and Electronic Engineering, University College Cork, T12 K8AF Cork, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0975-1575","authenticated-orcid":false,"given":"Christoph E.","family":"Schwarz","sequence":"additional","affiliation":[{"name":"Irish Centre for Maternal and Child Health Research, University College Cork, T12 K8AF Cork, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3067-5901","authenticated-orcid":false,"given":"Ihor","family":"Shelevytsky","sequence":"additional","affiliation":[{"name":"Faculty of Information Technologies, Kryvyi Rih Institute of Economics, 50479 Kryvyi Rih, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoriya","family":"Shelevytska","sequence":"additional","affiliation":[{"name":"Faculty of Postgraduate Education, Dnipropetrovsk Medical Academy of Health, 49098 Dnipro, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oksana","family":"Semenova","sequence":"additional","affiliation":[{"name":"Electrical and Electronic Engineering, University College Cork, T12 K8AF Cork, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreea","family":"Factor","sequence":"additional","affiliation":[{"name":"Department of Anatomy and Neuroscience, University College Cork, T12 K8AF Cork, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuel","family":"Popovici","sequence":"additional","affiliation":[{"name":"Electrical and Electronic Engineering, University College Cork, T12 K8AF Cork, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andriy","family":"Temko","sequence":"additional","affiliation":[{"name":"Electrical and Electronic Engineering, University College Cork, T12 K8AF Cork, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Knowles, R., Griebsch, I., Dezateux, C., Brown, J., Bull, C., and Wren, C. (2005). Newborn screening for congenital heart defects: A systematic review and cost-effectiveness analysis. Health Technol. Assess., 9.","DOI":"10.3310\/hta9440"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhang, Y.F., Zeng, X.L., Zhao, E.F., and Lu, H.W. (2015). Diagnostic Value of Fetal Echocardiography for Congenital Heart Disease: A Systematic Review and Meta-Analysis. Medicine, 94.","DOI":"10.1097\/MD.0000000000001759"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1002\/uog.10116","article-title":"Barriers to prenatal detection of congenital heart disease: A population-based study","volume":"40","author":"Pinto","year":"2012","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bakker, M.K., Bergman, J.E., Krikov, S., Amar, E., Cocchi, G., Cragan, J., de Walle, H.E.K., Gatt, M., Groisman, B., and Liu, S. (2019). Prenatal diagnosis and prevalence of critical congenital heart defects: An international retrospective cohort study. BMJ Open, 9.","DOI":"10.1136\/bmjopen-2018-028139"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Janicki, M.B., Fernandez, C.G., Wakefield, D., Shepherd, J.P., and Figueroa, R. (2020). Improving fetal congenital heart disease screening using a checklist-based approach. Prenat. Diagn., 40.","DOI":"10.1002\/pd.5581"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1002\/jum.14453","article-title":"Advancing prenatal detection of congenital heart disease: A novel screening protocol improves early diagnosis of complex congenital heart disease","volume":"37","author":"Letourneau","year":"2018","journal-title":"J. Ultrasound Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1159\/000262481","article-title":"Insights into the Pathogenesis and Genetic Background of Patency of the Ductus Arteriosus","volume":"98","author":"DeRuiter","year":"2010","journal-title":"Neonatology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1136\/adc.67.10_Spec_No.1217","article-title":"Intermittent ductal patency in healthy newborn infants: Demonstration by colour Doppler flow mapping","volume":"67","author":"Lim","year":"1992","journal-title":"Arch. Dis. Child."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nagasawa, H., Hamada, C., Wakabayashi, M., Nakagawa, Y., Nomura, S., and Kohno, Y. (2016). Time to spontaneous ductus arteriosus closure in full-term neonates. Open Heart, 3.","DOI":"10.1136\/openhrt-2016-000413"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1515\/JPM.2005.030","article-title":"Comparison of clinical criteria with echocardiographic findings in diagnosing PDA in preterm infants","volume":"33","author":"Alagarsamy","year":"2005","journal-title":"J. Perinat. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1001\/archpedi.1995.02170230090013","article-title":"Precision and Accuracy of Clinical and Radiological Signs in Premature Infants at Risk of Patent Ductus Arteriosus","volume":"149","author":"Davis","year":"1995","journal-title":"Arch. Pediatrics Adolesc. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1111\/j.1651-2227.2008.00745.x","article-title":"Patent ductus arteriosus evaluation by serial echocardiography in preterm infants","volume":"97","author":"Moody","year":"2008","journal-title":"Acta Paediatr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1111\/j.1440-1754.1994.tb00689.x","article-title":"A blinded comparison of clinical and echocardiographic evaluation of the preterm infant for patent ductus arteriosus","volume":"30","author":"Skelton","year":"1994","journal-title":"J. Paediatr. Child Health"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1002\/clc.20185","article-title":"The Impact of Computer-assisted Auscultation on Physician Referrals of Asymptomatic Patients with Heart Murmurs","volume":"31","author":"Watrous","year":"2008","journal-title":"Clin. Cardiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"143","DOI":"10.3399\/bjgp18X695213","article-title":"Artificial intelligence in medicine: Current trends and future possibilities","volume":"68","author":"Buch","year":"2018","journal-title":"Br. J. Gen. Pract."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1136\/svn-2017-000101","article-title":"Artificial intelligence in healthcare: Past, present and future","volume":"2","author":"Jiang","year":"2017","journal-title":"Stroke Vasc. Neurol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1088\/0967-3334\/37\/12\/2181","article-title":"An open-access database for the evaluation of heart sound algorithms","volume":"37","author":"Liu","year":"2016","journal-title":"Physiol. Meas."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"8316","DOI":"10.1109\/ACCESS.2018.2889437","article-title":"Algorithms for automatic analysis and classification of heart sounds-A systematic review","volume":"7","author":"Dwivedi","year":"2019","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Potes, C., Parvaneh, S., Rahman, A., and Conroy, B. (2016). Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. Comput. Cardiol. Conf., 621\u2013624.","DOI":"10.22489\/CinC.2016.182-399"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tang, H., Dai, Z., Jiang, Y., Li, T., and Liu, C. (2018). PCG classification using multidomain features and SVM classifier. BioMed Res. Int.","DOI":"10.1155\/2018\/4205027"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1111\/chd.12328","article-title":"Computerized Automatic Diagnosis of Innocent and Pathologic Murmurs in Pediatrics: A Pilot Study","volume":"11","author":"Lai","year":"2016","journal-title":"Congenit. Heart Dis."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-015-0359-3","article-title":"An Intelligent Phonocardiography for Automated Screening of Pediatric Heart Diseases","volume":"40","author":"Sepehri","year":"2016","journal-title":"J. Med. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.bspc.2011.05.009","article-title":"Application of phonocardiography on preterm infants with patent ductus arteriosus","volume":"6","author":"Balogh","year":"2011","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Amiri, A., Abtahi, M., Constant, N., and Mankodiya, K. (2017). Mobile Phonocardiogram Diagnosis in Newborns Using Support Vector Machine. Healthcare, 5.","DOI":"10.3390\/healthcare5010016"},{"key":"ref_25","first-page":"81","article-title":"Simulation Recording of an ECG, PCG, and PPG for Feature Extractions","volume":"10","author":"Abdulazez","year":"2017","journal-title":"Al-Khwarizmi Eng. J."},{"key":"ref_26","unstructured":"Karnath, B., and Thornton, W. (2002). Auscultation of the Heart. Hosp. Physician, 39\u201343."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Shelevytsky, I., Shelevytska, V., Golovko, V., and Semenov, B. (2018, January 21\u201325). Segmentation and Parametrisation of the Phonocardiogram for the Heart Conditions Classification in Newborns. Proceedings of the 2018 IEEE 2nd International Conference on Data Stream Mining and Processing, Lviv, Ukraine.","DOI":"10.1109\/DSMP.2018.8478495"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Schapire, R.E. (2003). The Boosting Approach to Machine Learning: An Overview, Springer.","DOI":"10.1007\/978-0-387-21579-2_9"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Saeb, S., Lonini, L., Jayaraman, A., Mohr, D., and Kording, K. (2016). Voodoo Machine Learning for Clinical Predictions. bioRxiv.","DOI":"10.1101\/059774"},{"key":"ref_32","unstructured":"Raschka, S. (2018). Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"Bradley","year":"1997","journal-title":"Pattern Recognit."},{"key":"ref_34","first-page":"13","article-title":"Recognising Abnormal Heart Sounds Using Deep Learning","volume":"1891","author":"Rubin","year":"2017","journal-title":"CEUR Workshop Proc."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Vernekar, S., Nair, S., Vijaysenan, D., and Ranjan, R. (2016). A novel approach for classification of normal\/abnormal phonocardiogram recordings using temporal signal analysis and machine learning. Comput. Cardiol. Conf., 1141\u20131144.","DOI":"10.22489\/CinC.2016.326-144"},{"key":"ref_36","first-page":"822","article-title":"Logistic regression-HSMM-based heart sound segmentation","volume":"63","author":"Springer","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/S0735-6757(99)90019-0","article-title":"Pulse oximetry: Principles and limitations","volume":"17","author":"Sinex","year":"1999","journal-title":"Am. J. Emerg. Med."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Du, C., Liu, D., Liu, G., and Wang, H. (2017). A Meta-Analysis about the Screening Role of Pulse Oximetry for Congenital Heart Disease. BioMed Res. Int.","DOI":"10.1155\/2017\/2123918"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1016\/S0140-6736(11)60753-8","article-title":"Pulse oximetry screening for congenital heart defects in newborn infants (PulseOx): A test accuracy study","volume":"378","author":"Ewer","year":"2011","journal-title":"Lancet"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1159\/000496621","article-title":"Commentary on \u201cPulse Oximetry Screening for Critical Congenital Heart Defects\u201d","volume":"117","author":"Oddie","year":"2020","journal-title":"Neonatology"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1016\/S0140-6736(14)60198-7","article-title":"Using Pulse Oximetry Combined with Clinical Evaluation to Screen Congenital Heart Disease in Early Neonatal Stage: A Chinese prospective screening study in 122,738 newborns","volume":"384","author":"Zhao","year":"2014","journal-title":"Lancet"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hu, X.J., Ma, X.J., Zhao, Q.M., Yan, W.L., Ge, X.L., Jia, B., Liu, F., Wu, L., Ye, M., and Liang, X.-c. (2017). Pulse oximetry and auscultation for congenital heart disease detection. Pediatrics, 140.","DOI":"10.1542\/peds.2017-1154"},{"key":"ref_43","unstructured":"Knowles, R., and Hunter, R. (2014). Screening for Congenital Heart Defects: External Review against Programme Appraisal Criteria for the UK NSC, University College London."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Granelli, A.D.W., Wennergren, M., Sandberg, K., Mellander, M., Bejlum, C., Ingan\u00e4s, L., Eriksson, M., Segerdahl, N., \u00c5gren, A., and Ekman-Joelsson, B.-M. (2009). Impact of pulse oximetry screening on the detection of duct dependent congenital heart disease: A Swedish prospective screening study in 39 821 newborns. BMJ, 338.","DOI":"10.1136\/bmj.a3037"}],"container-title":["Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9032\/9\/2\/169\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:19:51Z","timestamp":1760159991000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9032\/9\/2\/169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,5]]},"references-count":44,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["healthcare9020169"],"URL":"https:\/\/doi.org\/10.3390\/healthcare9020169","relation":{},"ISSN":["2227-9032"],"issn-type":[{"value":"2227-9032","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,5]]}}}