{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:44:58Z","timestamp":1790775898790,"version":"4.1.0"},"reference-count":37,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T00:00:00Z","timestamp":1616112000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T00:00:00Z","timestamp":1616112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"crossref","award":["209325\/Z\/17\/Z"],"award-info":[{"award-number":["209325\/Z\/17\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Neural Eng."],"published-print":{"date-parts":[[2021,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>\n                  <jats:italic>Objective.<\/jats:italic> To develop an automated system to classify the severity of hypoxic-ischaemic encephalopathy injury (HIE) in neonates from the background electroencephalogram (EEG). <jats:italic>Approach<\/jats:italic>. By combining a quadratic time\u2013frequency distribution (TFD) with a convolutional neural network, we develop a system that classifies 4 EEG grades of HIE. The network learns directly from the two-dimensional TFD through 3 independent layers with convolution in the time, frequency, and time\u2013frequency directions. Computationally efficient algorithms make it feasible to transform each 5 min epoch to the time\u2013frequency domain by controlling for oversampling to reduce both computation and computer memory. The system is developed on EEG recordings from 54 neonates. Then the system is validated on a large unseen dataset of 338 h of EEG recordings from 91 neonates obtained across multiple international centres. <jats:italic>Main results.<\/jats:italic> The proposed EEG HIE-grading system achieves a leave-one-subject-out testing accuracy of 88.9% and kappa of 0.84 on the development dataset. Accuracy for the large unseen test dataset is 69.5% (95% confidence interval, CI: 65.3%\u201373.6%) and kappa of 0.54, which is a significant (<jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mi>P<\/mml:mi>\n                        <mml:mo>&lt;<\/mml:mo>\n                        <mml:mn>0.001<\/mml:mn>\n                     <\/mml:math>\n                     <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"jneabe8aeieqn1.gif\" xlink:type=\"simple\"\/>\n                  <\/jats:inline-formula>) improvement over a state-of-the-art feature-based method with an accuracy of 56.8% (95% CI: 51.4%\u201361.7%) and kappa of 0.39. Performance of the proposed system was unaffected when the number of channels in testing was reduced from 8 to 2\u2014accuracy for the large validation dataset remained at 69.5% (95% CI: 65.5%\u201374.0%). <jats:italic>Significance.<\/jats:italic> The proposed system outperforms the state-of-the-art machine learning algorithms for EEG grade classification on a large multi-centre unseen dataset, indicating the potential to assist clinical decision making for neonates with HIE.<\/jats:p>","DOI":"10.1088\/1741-2552\/abe8ae","type":"journal-article","created":{"date-parts":[[2021,2,22]],"date-time":"2021-02-22T22:31:45Z","timestamp":1614033105000},"page":"046007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":54,"title":["Grading hypoxic-ischemic encephalopathy in neonatal EEG with convolutional neural networks and quadratic time\u2013frequency distributions"],"prefix":"10.1088","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9416-7308","authenticated-orcid":false,"given":"Sumit A","family":"Raurale","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0920-5291","authenticated-orcid":false,"given":"Geraldine B","family":"Boylan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean R","family":"Mathieson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5039-1498","authenticated-orcid":false,"given":"William P","family":"Marnane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8155-0826","authenticated-orcid":false,"given":"Gordon","family":"Lightbody","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9021-1183","authenticated-orcid":false,"given":"John M","family":"O\u2019Toole","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,3,19]]},"reference":[{"key":"jneabe8aebib1","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1002\/ana.23647","article-title":"Neonatal encephalopathy: an inadequate term for hypoxic\u2013ischemic encephalopathy","volume":"72","author":"Volpe","year":"2012","journal-title":"Ann. Neurol."},{"key":"jneabe8aebib2","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/S0165-0173(99)00009-0","article-title":"Pathophysiology of perinatal brain damage","volume":"30","author":"Berger","year":"1999","journal-title":"Brain Res. Rev."},{"key":"jneabe8aebib3","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1056\/NEJMoa0900854","article-title":"Moderate hypothermia to treat perinatal asphyxial encephalopathy","volume":"361","author":"Azzopardi","year":"2009","journal-title":"New Engl. J. Med."},{"key":"jneabe8aebib4","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1016\/S0140-6736(05)17946-X","article-title":"Selective head cooling with mild systemic hypothermia after neonatal encephalopathy: multicentre randomised trial","volume":"365","author":"Gluckman","year":"2005","journal-title":"Lancet"},{"key":"jneabe8aebib5","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1542\/peds.2005-1524","article-title":"Prediction of seizures in asphyxiated neonates: correlation with continuous video-electroencephalographic monitoring","volume":"118","author":"Murray","year":"2006","journal-title":"Pediatrics"},{"key":"jneabe8aebib6","doi-asserted-by":"publisher","first-page":"e459","DOI":"10.1542\/peds.2008-2190","article-title":"Early EEG findings in hypoxic-ischemic encephalopathy predict outcomes at 2 years","volume":"124","author":"Murray","year":"2009","journal-title":"Pediatrics"},{"key":"jneabe8aebib7","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/s10439-012-0710-5","article-title":"An automated system for grading EEG abnormality in term neonates with hypoxic-ischaemic encephalopathy","volume":"41","author":"Stevenson","year":"2013","journal-title":"Ann. Biomed. Eng."},{"key":"jneabe8aebib8","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/11\/6\/066007","article-title":"Holistic approach for automated background EEG assessment in asphyxiated full-term infants","volume":"11","author":"Mati\u0107","year":"2014","journal-title":"J. Neural Eng."},{"key":"jneabe8aebib9","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TBME.2015.2477946","article-title":"Improving reliability of monitoring background EEG dynamics in asphyxiated infants","volume":"63","author":"Mati\u0107","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jneabe8aebib10","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/j.clinph.2015.05.024","article-title":"Grading hypoxic\u2013ischemic encephalopathy severity in neonatal EEG using GMM supervectors and the support vector machine","volume":"127","author":"Ahmed","year":"2016","journal-title":"Clin. Neurophysiol."},{"key":"jneabe8aebib11","doi-asserted-by":"publisher","first-page":"4125","DOI":"10.1109\/EMBC.2019.8857000","article-title":"Suitability of an inter-burst detection method for grading hypoxic-ischemic encephalopathy in newborn EEG","author":"Raurale","year":"2019"},{"key":"jneabe8aebib12","doi-asserted-by":"publisher","first-page":"721","DOI":"10.32604\/cmes.2020.07470","article-title":"Grading method for hypoxic-ischemic encephalopathy based on neonatal EEG","volume":"122","author":"Guo","year":"2020","journal-title":"Comput. Model. Eng. Sci."},{"key":"jneabe8aebib13","doi-asserted-by":"publisher","first-page":"6103","DOI":"10.1109\/EMBC44109.2020.9175337","article-title":"Grading the severity of hypoxic-ischemic encephalopathy in newborn EEG using a convolutional neural network","author":"Raurale","year":"2020"},{"key":"jneabe8aebib14","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ab5469","article-title":"A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants","volume":"17","author":"Ansari","year":"2020","journal-title":"J. Neural Eng."},{"key":"jneabe8aebib15","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065718500119","article-title":"Neonatal seizure detection using deep convolutional neural networks","volume":"29","author":"Ansari","year":"2019","journal-title":"Int. J. Neural Syst."},{"key":"jneabe8aebib16","doi-asserted-by":"publisher","first-page":"1545","DOI":"10.1109\/TMI.2019.2953054","article-title":"Deep learning analysis of coronary arteries in cardiac CT angiography for detection of patients requiring invasive coronary angiography","volume":"39","author":"Zreik","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"jneabe8aebib17","doi-asserted-by":"publisher","first-page":"207","DOI":"10.3389\/fnins.2020.00207","article-title":"Using deep convolutional neural networks for neonatal brain image segmentation","volume":"14","author":"Ding","year":"2020","journal-title":"Front. Neurosci."},{"key":"jneabe8aebib18","article-title":"SLEEPNET: automated sleep staging system via deep learning","author":"Biswal","year":"2017"},{"key":"jneabe8aebib19","doi-asserted-by":"publisher","first-page":"781","DOI":"10.3389\/fnins.2018.00781","article-title":"Automatic human sleep stage scoring using deep neural networks","volume":"12","author":"Malafeev","year":"2018","journal-title":"Front. Neurosci."},{"key":"jneabe8aebib20","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2020.3020381","article-title":"Towards more accurate automatic sleep staging via deep transfer learning","author":"Phan","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jneabe8aebib21","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/JBHI.2018.2871678","article-title":"A multi-view deep learning framework for EEG seizure detection","volume":"23","author":"Yuan","year":"2018","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"jneabe8aebib22","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/MSP.2013.2265914","article-title":"Time-frequency processing of nonstationary signals: Advanced TFD design to aid diagnosis with highlights from medical applications","volume":"30","author":"Boashash","year":"2013","journal-title":"IEEE Signal Process. Mag."},{"key":"jneabe8aebib23","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.sigpro.2016.08.017","article-title":"An automatic fast optimization of quadratic time-frequency distribution using the hybrid genetic algorithm","volume":"131","author":"Awal","year":"2017","journal-title":"Signal Process."},{"key":"jneabe8aebib24","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1016\/j.clinph.2010.12.059","article-title":"Quantitative EEG analysis in neonatal hypoxic ischaemic encephalopathy","volume":"122","author":"Korotchikova","year":"2011","journal-title":"Clin. Neurophysiol."},{"key":"jneabe8aebib25","doi-asserted-by":"publisher","first-page":"F493\u2013F501","DOI":"10.1136\/archdischild-2018-315624","article-title":"Characterisation of neonatal seizures and their treatment using continuous EEG monitoring: a multicentre experience","volume":"104","author":"Rennie","year":"2019","journal-title":"Arch. Dis. Child. Fetal Neonatal Ed."},{"key":"jneabe8aebib26","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1016\/S2352-4642(20)30239-X","article-title":"A machine-learning algorithm for neonatal seizure recognition: a multicentre, randomised, controlled trial","volume":"4","author":"Pavel","year":"2020","journal-title":"Lancet Child Adolescent Health"},{"key":"jneabe8aebib27","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TSP.2008.929325","article-title":"A new discrete analytic signal for reducing aliasing in the discrete Wigner-Ville distribution","volume":"56","author":"O\u2019Toole","year":"2008","journal-title":"IEEE Trans. Signal Process."},{"key":"jneabe8aebib28","doi-asserted-by":"publisher","first-page":"5799","DOI":"10.1109\/EMBC.2019.8856533","article-title":"Machine learning without a feature set for detecting bursts in the EEG of preterm infants","author":"O\u2019Toole","year":"2019"},{"key":"jneabe8aebib29","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1109\/EMBC44109.2020.9175154","article-title":"Detection of transient bursts in the EEG of preterm infants using time\u2013frequency distributions and machine learning","author":"Murphy","year":"2020"},{"key":"jneabe8aebib30","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.acha.2013.01.003","article-title":"Fast and memory-efficient algorithms for computing quadratic time\u2013frequency distributions","volume":"35","author":"O\u2019Toole","year":"2013","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"jneabe8aebib31","article-title":"NEURAL: quantitative features for newborn EEG using Matlab","author":"O\u2019Toole","year":"2017"},{"key":"jneabe8aebib32","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.seizure.2015.09.014","article-title":"Amplitude-integrated EEG for detection of neonatal seizures: a systematic review","volume":"33","author":"Rakshasbhuvankar","year":"2015","journal-title":"Seizure"},{"key":"jneabe8aebib33","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1177\/0883073817707411","article-title":"Amplitude integrated electroencephalography compared with conventional video EEG for neonatal seizure detection: a diagnostic accuracy study","volume":"32","author":"Rakshasbhuvankar","year":"2017","journal-title":"J. Child Neurol."},{"key":"jneabe8aebib34","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.neunet.2019.11.023","article-title":"Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture","volume":"123","author":"O\u2019Shea","year":"2020","journal-title":"Neural Netw."},{"key":"jneabe8aebib35","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065721500088","article-title":"Deep learning for EEG seizure detection in preterm infants","author":"O\u2019Shea","year":"2020","journal-title":"Int. J. Neural Syst."},{"key":"jneabe8aebib36","first-page":"4881","article-title":"Neonatal EEG interpretation and decision support framework for mobile platforms","author":"O\u2019Sullivan","year":"2018"},{"key":"jneabe8aebib37","first-page":"1","article-title":"Neonatal seizure detection using convolutional neural networks","author":"O\u2019Shea","year":"2017"}],"container-title":["Journal of Neural Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T20:13:22Z","timestamp":1642191202000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/abe8ae"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,19]]},"references-count":37,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,3,19]]},"published-print":{"date-parts":[[2021,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1741-2552\/abe8ae","relation":{},"ISSN":["1741-2560","1741-2552"],"issn-type":[{"value":"1741-2560","type":"print"},{"value":"1741-2552","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,19]]},"assertion":[{"value":"Grading hypoxic-ischemic encephalopathy in neonatal EEG with convolutional neural networks and quadratic time\u2013frequency distributions","name":"article_title","label":"Article Title"},{"value":"Journal of Neural Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-10-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-02-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-03-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}