{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T23:39:52Z","timestamp":1789169992586,"version":"build-2803163510"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T00:00:00Z","timestamp":1673568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Interfaculty Research Cooperation"},{"name":"University of Bern"},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100023177","name":"Fondation Pierre Mercier pour la science","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100023177","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100006390","name":"University of Lausanne","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006390","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,2,13]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Assessing the integrity of neural functions in coma after cardiac arrest remains an open challenge. Prognostication of coma outcome relies mainly on visual expert scoring of physiological signals, which is prone to subjectivity and leaves a considerable number of patients in a \u2018grey zone\u2019, with uncertain prognosis. Quantitative analysis of EEG responses to auditory stimuli can provide a window into neural functions in coma and information about patients\u2019 chances of awakening. However, responses to standardized auditory stimulation are far from being used in a clinical routine due to heterogeneous and cumbersome protocols. Here, we hypothesize that convolutional neural networks can assist in extracting interpretable patterns of EEG responses to auditory stimuli during the first day of coma that are predictive of patients\u2019 chances of awakening and survival at 3 months. We used convolutional neural networks (CNNs) to model single-trial EEG responses to auditory stimuli in the first day of coma, under standardized sedation and targeted temperature management, in a multicentre and multiprotocol patient cohort and predict outcome at 3 months. The use of CNNs resulted in a positive predictive power for predicting awakening of 0.83 \u00b1 0.04 and 0.81 \u00b1 0.06 and an area under the curve in predicting outcome of 0.69 \u00b1 0.05 and 0.70 \u00b1 0.05, for patients undergoing therapeutic hypothermia and normothermia, respectively. These results also persisted in a subset of patients that were in a clinical \u2018grey zone\u2019. The network\u2019s confidence in predicting outcome was based on interpretable features: it strongly correlated to the neural synchrony and complexity of EEG responses and was modulated by independent clinical evaluations, such as the EEG reactivity, background burst-suppression or motor responses. Our results highlight the strong potential of interpretable deep learning algorithms in combination with auditory stimulation to improve prognostication of coma outcome.<\/jats:p>","DOI":"10.1093\/brain\/awac340","type":"journal-article","created":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T01:45:44Z","timestamp":1673660744000},"page":"778-788","source":"Crossref","is-referenced-by-count":41,"title":["Auditory stimulation and deep learning predict awakening from coma after cardiac arrest"],"prefix":"10.1093","volume":"146","author":[{"given":"Florence M","family":"Aellen","sequence":"first","affiliation":[{"name":"Institute of Computer Science, University of Bern , Bern , Switzerland"},{"name":"Zentrum f\u00fcr Experimentelle Neurologie, Department of Neurology, Inselspital, Bern University Hospital, University of Bern , Bern , Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sigurd L","family":"Alnes","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of Bern , Bern , Switzerland"},{"name":"Zentrum f\u00fcr Experimentelle Neurologie, Department of Neurology, Inselspital, Bern University Hospital, University of Bern , Bern , Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Loosli","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of Bern , Bern , Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea O","family":"Rossetti","sequence":"additional","affiliation":[{"name":"Neurology Service, Department of Clinical Neurosciences, Lausanne University Hospital and University of Lausanne , Lausanne , Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Zubler","sequence":"additional","affiliation":[{"name":"Sleep-Wake-Epilepsy-Center, Department of Neurology, Inselspital, Bern University Hospital, University of Bern , Bern , Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marzia","family":"De Lucia","sequence":"additional","affiliation":[{"name":"Laboratory for Research in Neuroimaging (LREN), Department of Clinical Neurosciences, Centre Hospitalier Universitaire Vaudois (CHUV) , Lausanne , Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athina","family":"Tzovara","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of Bern , Bern , Switzerland"},{"name":"Zentrum f\u00fcr Experimentelle Neurologie, Department of Neurology, Inselspital, Bern University Hospital, University of Bern , Bern , Switzerland"},{"name":"Sleep Wake Epilepsy Center\u2014NeuroTec, Department of Neurology, Inselspital, Bern University Hospital, University of Bern , Bern , Switzerland"},{"name":"Helen Wills Neuroscience Institute, University of California Berkeley , Berkeley, CA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"2023021318521204300_awac340-B1","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1016\/S1474-4422(16)00015-6","article-title":"Neurological prognostication of outcome in patients in coma after cardiac arrest","volume":"15","author":"Rossetti","year":"2016","journal-title":"Lancet Neurol"},{"key":"2023021318521204300_awac340-B2","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1016\/S0140-6736(21)00953-3","article-title":"Brain injury after cardiac arrest","volume":"398","author":"Perkins","year":"2021","journal-title":"Lancet"},{"key":"2023021318521204300_awac340-B3","doi-asserted-by":"crossref","first-page":"2397","DOI":"10.1016\/j.clinph.2015.03.017","article-title":"Interrater variability of EEG interpretation in comatose cardiac arrest patients","volume":"126","author":"Westhall","year":"2015","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B4","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1212\/01.WNL.0000134670.10384.E2","article-title":"Predictive value of sensory and cognitive evoked potentials for awakening from coma","volume":"63","author":"Fischer","year":"2004","journal-title":"Neurology"},{"key":"2023021318521204300_awac340-B5","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.clinph.2006.11.019","article-title":"Predicting coma and other low responsive patients outcome using event-related brain potentials: A meta-analysis","volume":"118","author":"Daltrozzo","year":"2007","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B6","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1007\/s10548-013-0335-5","article-title":"MMN and novelty P3 in coma and other altered states of consciousness: A review","volume":"27","author":"Morlet","year":"2014","journal-title":"Brain Topogr"},{"key":"2023021318521204300_awac340-B7","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s12028-021-01308-y","article-title":"The combination of N60 with mismatch negativity improves the prediction of awakening from coma","volume":"36(3)","author":"Liu","year":"2022","journal-title":"Neurocrit Care"},{"key":"2023021318521204300_awac340-B8","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s00134-021-06368-4","article-title":"European Resuscitation Council and European Society of Intensive Care Medicine Guidelines 2021: Post-resuscitation care","volume":"47","author":"Nolan","year":"2021","journal-title":"Intensive Care Med"},{"key":"2023021318521204300_awac340-B9","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1016\/S1388-2457(99)00131-5","article-title":"Mismatch negativity and late auditory evoked potentials in comatose patients","volume":"110","author":"Fischer","year":"1999","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B10","doi-asserted-by":"crossref","first-page":"2224","DOI":"10.1016\/j.clinph.2008.03.035","article-title":"Novelty P3 elicited by the subject\u2019s own name in comatose patients","volume":"119","author":"Fischer","year":"2008","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B11","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/0140-6736(93)90453-N","article-title":"Electrophysiological indicator of awakening from coma","volume":"341","author":"Kane","year":"1993","journal-title":"Lancet"},{"key":"2023021318521204300_awac340-B12","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1016\/j.clinph.2004.10.009","article-title":"Auditory mismatch negativity is a good predictor of awakening in comatose patients: A fast and reliable procedure","volume":"116","author":"Naccache","year":"2005","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B13","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.apmr.2004.08.011","article-title":"Late auditory and event-related potentials can be useful to predict good functional outcome after coma","volume":"86","author":"Luaut\u00e9","year":"2005","journal-title":"Arch Phys Med Rehabil"},{"key":"2023021318521204300_awac340-B14","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1093\/brain\/aws264","article-title":"Progression of auditory discrimination based on neural decoding predicts awakening from coma","volume":"136","author":"Tzovara","year":"2013","journal-title":"Brain"},{"key":"2023021318521204300_awac340-B15","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1002\/ana.24622","article-title":"Prediction of awakening from hypothermic postanoxic coma based on auditory discrimination: Awakening from postanoxic coma","volume":"79","author":"Tzovara","year":"2016","journal-title":"Ann Neurol"},{"key":"2023021318521204300_awac340-B16","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.resuscitation.2017.07.012","article-title":"Auditory discrimination improvement predicts awakening of postanoxic comatose patients treated with targeted temperature management at 36\u00b0C","volume":"118","author":"Pfeiffer","year":"2017","journal-title":"Resuscitation"},{"key":"2023021318521204300_awac340-B17","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1002\/acn3.600","article-title":"Somatosensory and auditory deviance detection for outcome prediction during postanoxic coma","volume":"5","author":"Pfeiffer","year":"2018","journal-title":"Ann Clin Transl Neurol"},{"key":"2023021318521204300_awac340-B18","doi-asserted-by":"crossref","first-page":"118638","DOI":"10.1016\/j.neuroimage.2021.118638","article-title":"Complementary roles of neural synchrony and complexity for indexing consciousness and chances of surviving in acute coma","volume":"245","author":"Alnes","year":"2021","journal-title":"NeuroImage"},{"key":"2023021318521204300_awac340-B19","doi-asserted-by":"crossref","first-page":"031001","DOI":"10.1088\/1741-2552\/ab0ab5","article-title":"Deep learning for electroencephalogram (EEG) classification tasks: A review","volume":"16","author":"Craik","year":"2019","journal-title":"J Neural Eng"},{"key":"2023021318521204300_awac340-B20","doi-asserted-by":"crossref","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep learning-based electroencephalography analysis: A systematic review","volume":"16","author":"Roy","year":"2019","journal-title":"J Neural Eng"},{"key":"2023021318521204300_awac340-B21","doi-asserted-by":"crossref","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNet: A compact convolutional neural network for EEG-based brain\u2013computer interfaces","volume":"15","author":"Lawhern","year":"2018","journal-title":"J Neural Eng"},{"key":"2023021318521204300_awac340-B22","doi-asserted-by":"crossref","first-page":"109367","DOI":"10.1016\/j.jneumeth.2021.109367","article-title":"Convolutional neural networks for decoding electroencephalography responses and visualizing trial by trial changes in discriminant features","volume":"364","author":"Aellen","year":"2021","journal-title":"J Neurosci Methods"},{"key":"2023021318521204300_awac340-B23","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1097\/CCM.0000000000003854","article-title":"Outcome prediction in postanoxic coma with deep learning","volume":"47","author":"Tjepkema-Cloostermans","year":"2019","journal-title":"Crit Care Med"},{"key":"2023021318521204300_awac340-B24","doi-asserted-by":"crossref","first-page":"4606","DOI":"10.1002\/hbm.24724","article-title":"EEG-based outcome prediction after cardiac arrest with convolutional neural networks: Performance and visualization of discriminative features","volume":"40","author":"Jonas","year":"2019","journal-title":"Hum Brain Mapp"},{"key":"2023021318521204300_awac340-B25","first-page":"1813","article-title":"Predicting neurological outcome from electroencephalogram dynamics in comatose patients after cardiac arrest with deep learning","volume":"69(5)","author":"Zheng","year":"2021","journal-title":"IEEE Trans Biomed Eng"},{"key":"2023021318521204300_awac340-B26","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.bbe.2021.11.003","article-title":"A novel approach for detection of consciousness level in comatose patients from EEG signals with 1-D convolutional neural network","volume":"42","author":"Alt\u0131ntop","year":"2022","journal-title":"Biocybern Biomed Eng"},{"key":"2023021318521204300_awac340-B27","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1212\/WNL.0000000000002462","article-title":"Standardized EEG interpretation accurately predicts prognosis after cardiac arrest","volume":"86","author":"Westhall","year":"2016","journal-title":"Neurology"},{"key":"2023021318521204300_awac340-B28","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1056\/NEJMoa1310519","article-title":"Targeted temperature management at 33\u00b0C versus 36\u00b0C after cardiac arrest","volume":"369","author":"Nielsen","year":"2013","journal-title":"N Engl J Med"},{"key":"2023021318521204300_awac340-B29","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1002\/ana.21984","article-title":"Prognostication after cardiac arrest and hypothermia: A prospective study","volume":"67(3)","author":"Rossetti","year":"2010","journal-title":"Ann Neurol"},{"key":"2023021318521204300_awac340-B30","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s12028-017-0393-8","article-title":"Multimodal outcome prognostication after cardiac arrest and targeted temperature management: Analysis at 36\u00b0C","volume":"28","author":"Tsetsou","year":"2018","journal-title":"Neurocrit Care"},{"key":"2023021318521204300_awac340-B31","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.resuscitation.2015.07.018","article-title":"European Resuscitation Council and European Society of Intensive Care Medicine Guidelines for post-resuscitation care 2015","volume":"95","author":"Nolan","year":"2015","journal-title":"Resuscitation"},{"key":"2023021318521204300_awac340-B32","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1001\/jama.291.7.870","article-title":"Is this patient dead, vegetative, or severely neurologically impaired? Assessing outcome for comatose survivors of cardiac arrest","volume":"291","author":"Booth","year":"2004","journal-title":"JAMA"},{"key":"2023021318521204300_awac340-B33","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/0013-4694(87)90141-6","article-title":"Mapping of scalp potentials by surface spline interpolation","volume":"66","author":"Perrin","year":"1987","journal-title":"Electroencephalogr Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B34","author":"Kingma"},{"key":"2023021318521204300_awac340-B35","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/3-540-49430-8_3","volume-title":"Neural networks: Tricks of the trade","author":"Prechelt","year":"1998"},{"key":"2023021318521204300_awac340-B36","volume-title":"Detection theory: A user\u2019s guide","author":"Macmillan","year":"2005","edition":"2nd ed"},{"key":"2023021318521204300_awac340-B37","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1002\/(SICI)1097-0193(1999)8:4<194::AID-HBM4>3.0.CO;2-C","article-title":"Measuring phase synchrony in brain signals","volume":"8","author":"Lachaux","year":"1999","journal-title":"Hum Brain Mapp"},{"key":"2023021318521204300_awac340-B38","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1109\/TIT.1976.1055501","article-title":"On the complexity of finite sequences","volume":"22","author":"Lempel","year":"1976","journal-title":"IEEE Trans Inf Theory"},{"key":"2023021318521204300_awac340-B39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1097\/WNP.0000000000000806","article-title":"American Clinical Neurophysiology Society\u2019s standardized critical care EEG terminology: 2021 version","volume":"38","author":"Hirsch","year":"2021","journal-title":"J Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B40","doi-asserted-by":"crossref","first-page":"987","DOI":"10.3390\/s19050987","article-title":"Removal of artifacts from EEG signals: A review","volume":"19","author":"Jiang","year":"2019","journal-title":"Sensors (Basel)"},{"key":"2023021318521204300_awac340-B41","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.resuscitation.2016.06.032","article-title":"Prediction of cognitive outcome based on the progression of auditory discrimination during coma","volume":"106","author":"Juan","year":"2016","journal-title":"Resuscitation"},{"key":"2023021318521204300_awac340-B42","doi-asserted-by":"crossref","first-page":"e286","DOI":"10.1097\/CCM.0000000000002946","article-title":"How do you feel? Subjective perception of recovery as a reliable surrogate of cognitive and functional outcome in cardiac arrest survivors","volume":"46","author":"Juan","year":"2018","journal-title":"Crit Care Med"},{"key":"2023021318521204300_awac340-B43","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.clinph.2017.01.020","article-title":"EEG synchronization measures are early outcome predictors in comatose patients after cardiac arrest","volume":"128","author":"Zubler","year":"2017","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B44","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1016\/j.clinph.2021.02.011","article-title":"EEG functional connectivity contributes to outcome prediction of postanoxic coma","volume":"132","author":"Carrasco-G\u00f3mez","year":"2021","journal-title":"Clin Neurophysiol"},{"key":"2023021318521204300_awac340-B45","doi-asserted-by":"crossref","first-page":"e674","DOI":"10.1097\/CCM.0000000000002337","article-title":"Electroencephalography predicts poor and good outcomes after cardiac arrest: A two-center study","volume":"45","author":"Rossetti","year":"2017","journal-title":"Crit Care Med"},{"key":"2023021318521204300_awac340-B46","doi-asserted-by":"crossref","first-page":"4616","DOI":"10.1038\/s41467-019-12658-9","article-title":"Consciousness-specific dynamic interactions of brain integration and functional diversity","volume":"10","author":"Luppi","year":"2019","journal-title":"Nat Commun"},{"key":"2023021318521204300_awac340-B47","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1016\/j.clinph.2021.03.047","article-title":"Assessment of a standardized EEG reactivity protocol after cardiac arrest","volume":"132","author":"Caroyer","year":"2021","journal-title":"Clin Neurophysiol"}],"container-title":["Brain"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/brain\/advance-article-pdf\/doi\/10.1093\/brain\/awac340\/48703034\/awac340.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/brain\/article-pdf\/146\/2\/778\/49171789\/awac340.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/brain\/article-pdf\/146\/2\/778\/49171789\/awac340.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T10:25:04Z","timestamp":1701080704000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/brain\/article\/146\/2\/778\/6987138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,13]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1,13]]},"published-print":{"date-parts":[[2023,2,13]]}},"URL":"https:\/\/doi.org\/10.1093\/brain\/awac340","relation":{},"ISSN":["0006-8950","1460-2156"],"issn-type":[{"value":"0006-8950","type":"print"},{"value":"1460-2156","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,2,1]]},"published":{"date-parts":[[2023,1,13]]}}}