{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T20:03:12Z","timestamp":1792180992194,"version":"4.4.0"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T00:00:00Z","timestamp":1672099200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hospital-level project of the Second Affiliated Hospital of Nanchang University","award":["No. 2021efyC02"],"award-info":[{"award-number":["No. 2021efyC02"]}]},{"name":"Jiangxi Provincial Science and Technology Department Project","award":["No. 20208031"],"award-info":[{"award-number":["No. 20208031"]}]},{"name":"Major Projects of Institute of Chinese Materia Medica China Academy of Chinese Medical Sciences","award":["No. ZZ15-WT-04"],"award-info":[{"award-number":["No. ZZ15-WT-04"]}]},{"name":"Jiangxi Provincial Education Department Project","award":["No. GJJ200133"],"award-info":[{"award-number":["No. GJJ200133"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Objective<\/jats:title>\n<jats:p>Ischemic stroke (IS) with subsequent cerebrocardiac syndrome (CCS) has a poor prognosis. We aimed to investigate electrocardiogram (ECG) changes after IS with artificial intelligence (AI).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We collected ECGs from a healthy population and patients with IS, and then analyzed participant demographics and ECG parameters to identify abnormal features in post-IS ECGs. Next, we trained the convolutional neural network (CNN), random forest (RF) and support vector machine (SVM) models to automatically detect the changes in the ECGs; Additionally, We compared the CNN scores of good prognosis (mRS \u2264 2) and poor prognosis (mRS &gt; 2) to assess the prognostic value of CNN model. Finally, we used gradient class activation map (Grad-CAM) to localize the key abnormalities.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Among the 3506 ECGs of the IS patients, 2764 ECGs (78.84%) led to an abnormal diagnosis. Then we divided ECGs in the primary cohort into three groups, normal ECGs (N-Ns), abnormal ECGs after the first ischemic stroke (A-ISs), and normal ECGs after the first ischemic stroke (N-ISs). Basic demographic and ECG parameter analyses showed that heart rate, QT interval, and P-R interval were significantly different between 673 N-ISs and 3546 N-Ns (<jats:italic>p<\/jats:italic> &lt; 0.05). The CNN has the best performance among the three models in distinguishing A-ISs and N-Ns (AUC: 0.88, 95%CI = 0.86\u20130.90). The prediction scores of the A-ISs and N-ISs obtained from the all three models are statistically different from the N-Ns (<jats:italic>p<\/jats:italic> &lt; 0.001). Futhermore, the CNN scores of the two groups (mRS &gt; 2 and mRS \u2264 2) were significantly different (<jats:italic>p<\/jats:italic> &lt; 0.05). Finally, Grad-CAM revealed that the V4 lead may harbor the highest probability of abnormality.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Our study showed that a high proportion of post-IS ECGs harbored abnormal changes. Our CNN model can systematically assess anomalies in and prognosticate post-IS ECGs.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0279706","type":"journal-article","created":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T18:32:51Z","timestamp":1672165971000},"page":"e0279706","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Assessing electrocardiogram changes after ischemic stroke with artificial intelligence"],"prefix":"10.1371","volume":"17","author":[{"given":"Ziqiang","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Lou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zujue","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingping","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangqin","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5863-3829","authenticated-orcid":true,"given":"Libin","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,12,27]]},"reference":[{"issue":"10154","key":"pone.0279706.ref001","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1016\/S0140-6736(18)31269-8","article-title":"Prevention of stroke: a global perspective","volume":"392","author":"JD Pandian","year":"2018","journal-title":"Lancet (London, England)"},{"issue":"25","key":"pone.0279706.ref002","doi-asserted-by":"crossref","first-page":"2429","DOI":"10.1056\/NEJMoa1804492","article-title":"Global, Regional, and Country-Specific Lifetime Risks of Stroke, 1990 and 2016","volume":"379","author":"VL Feigin","year":"2018","journal-title":"The New England Journal of Medicine"},{"issue":"4","key":"pone.0279706.ref003","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1161\/CIRCRESAHA.117.311170","article-title":"Brain-Heart Interaction: Cardiac Complications After Stroke","volume":"121","author":"Z Chen","year":"2017","journal-title":"Circulation Research"},{"issue":"12","key":"pone.0279706.ref004","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1016\/S1474-4422(18)30336-3","article-title":"Stroke-heart syndrome: clinical presentation and underlying mechanisms","volume":"17","author":"JF Scheitz","year":"2018","journal-title":"The Lancet Neurology"},{"issue":"8","key":"pone.0279706.ref005","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1161\/01.STR.22.8.983","article-title":"Atrial fibrillation as an independent risk factor for stroke: the Framingham Study","volume":"22","author":"PA Wolf","year":"1991","journal-title":"Stroke"},{"issue":"6","key":"pone.0279706.ref006","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1161\/01.STR.15.6.990","article-title":"Myocardial damage from acute cerebral lesions","volume":"15","author":"A Kolin","year":"1984","journal-title":"Stroke"},{"issue":"8","key":"pone.0279706.ref007","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1161\/STROKEAHA.106.471813","article-title":"Predictors of early cardiac morbidity and mortality after ischemic stroke","volume":"38","author":"J Prosser","year":"2007","journal-title":"Stroke"},{"issue":"2","key":"pone.0279706.ref008","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1002\/ejhf.1100","article-title":"Heart and brain interaction in patients with heart failure: overview and proposal for a taxonomy. A position paper from the Study Group on Heart and Brain Interaction of the Heart Failure Association","volume":"20","author":"W Doehner","year":"2018","journal-title":"European Journal of Heart Failure"},{"issue":"2","key":"pone.0279706.ref009","doi-asserted-by":"crossref","first-page":"253","DOI":"10.3171\/jns.1992.77.2.0253","article-title":"Loss of cerebral regulation during cardiac output variations in focal cerebral ischemia","volume":"77","author":"BI Tranmer","year":"1992","journal-title":"Journal of Neurosurgery"},{"issue":"6","key":"pone.0279706.ref010","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1111\/j.1365-2796.2006.01639.x","article-title":"Electrocardiographic and troponin T changes in acute ischaemic stroke","volume":"259","author":"B Fure","year":"2006","journal-title":"Journal of Internal Medicine"},{"issue":"3","key":"pone.0279706.ref011","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.ijcard.2010.10.042","article-title":"Can prolonged QTc and cTNT level predict the acute and long-term prognosis of stroke?","volume":"155","author":"C Hjalmarsson","year":"2012","journal-title":"International Journal of Cardiology"},{"issue":"2","key":"pone.0279706.ref012","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1159\/000064733","article-title":"Electrocardiographic changes in patients with acute stroke: a systematic review","volume":"14","author":"G Khechinashvili","year":"2002","journal-title":"Cerebrovascular Diseases (Basel, Switzerland)."},{"issue":"5","key":"pone.0279706.ref013","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1001\/jamacardio.2020.7422","article-title":"Use of Artificial Intelligence and Deep Neural Networks in Evaluation of Patients With Electrocardiographically Concealed Long QT Syndrome From the Surface 12-Lead Electrocardiogram","volume":"6","author":"JM Bos","year":"2021","journal-title":"JAMA Cardiology"},{"issue":"10201","key":"pone.0279706.ref014","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/S0140-6736(19)31721-0","article-title":"An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction","volume":"394","author":"ZI Attia","year":"2019","journal-title":"Lancet (London, England)"},{"issue":"8","key":"pone.0279706.ref015","doi-asserted-by":"crossref","first-page":"e008437","DOI":"10.1161\/CIRCEP.120.008437","article-title":"Artificial Intelligence-Enabled ECG Algorithm to Identify Patients With Left Ventricular Systolic Dysfunction Presenting to the Emergency Department With Dyspnea","volume":"13","author":"D Adedinsewo","year":"2020","journal-title":"Circulation Arrhythmia and Electrophysiology"},{"issue":"23","key":"pone.0279706.ref016","doi-asserted-by":"crossref","first-page":"2668","DOI":"10.1016\/j.jacc.2018.03.521","article-title":"Artificial Intelligence in Cardiology","volume":"71","author":"KW Johnson","year":"2018","journal-title":"Journal of the American College of Cardiology"},{"issue":"10","key":"pone.0279706.ref017","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1016\/j.ajpath.2021.01.015","article-title":"Searching Images for Consensus: Can AI Remove Observer Variability in Pathology","volume":"191","author":"HR Tizhoosh","year":"2021","journal-title":"The American Journal of Pathology"},{"issue":"6","key":"pone.0279706.ref018","doi-asserted-by":"crossref","first-page":"1184","DOI":"10.2214\/AJR.18.20331","article-title":"What Does Deep Learning See? Insights From a Classifier Trained to Predict Contrast Enhancement Phase From CT Images.","volume":"211","author":"KA Philbrick","year":"2018","journal-title":"AJR American Journal of Roentgenology"},{"issue":"6","key":"pone.0279706.ref019","doi-asserted-by":"crossref","first-page":"1737","DOI":"10.1016\/S0735-1097(00)00976-1","article-title":"Centennial of the string galvanometer and the electrocardiogram","volume":"36","author":"C. Fisch","year":"2000","journal-title":"Journal of the American College of Cardiology"},{"issue":"1","key":"pone.0279706.ref020","doi-asserted-by":"crossref","DOI":"10.1161\/STROKEAHA.112.676551","article-title":"Atrial fibrillation in ischemic stroke: predicting response to thrombolysis and clinical outcomes","volume":"44","author":"G Saposnik","year":"2013","journal-title":"Stroke"},{"issue":"8","key":"pone.0279706.ref021","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1093\/europace\/euaa377","article-title":"Deep learning and the electrocardiogram: review of the current state-of-the-art.","volume":"23","author":"S Somani","year":"2021","journal-title":"Europace: European Pacing, Arrhythmias, and Cardiac Electrophysiology: Journal of the Working Groups On Cardiac Pacing, Arrhythmias, and Cardiac Cellular Electrophysiology of the European Society of Cardiology"},{"issue":"9","key":"pone.0279706.ref022","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"K He","year":"2015","journal-title":"IEEE Transactions On Pattern Analysis and Machine Intelligence"},{"key":"pone.0279706.ref023","first-page":"25","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"A Krizhevsky","year":"2012","journal-title":"Neural Information Processing Systems"},{"key":"pone.0279706.ref024","author":"K Simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition 2014 September 01"},{"issue":"1","key":"pone.0279706.ref025","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/s41591-018-0240-2","article-title":"Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram","volume":"25","author":"ZI Attia","year":"2019","journal-title":"Nature Medicine"},{"issue":"7","key":"pone.0279706.ref026","doi-asserted-by":"crossref","DOI":"10.1053\/j.gastro.2022.02.025","article-title":"Deep Learning-Based Classification of Hepatocellular Nodular Lesions on Whole-Slide Histopathologic Images","volume":"162","author":"N Cheng","year":"2022","journal-title":"Gastroenterology"},{"key":"pone.0279706.ref027","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.neunet.2020.09.017","article-title":"Deconvolutional neural network for image super-resolution","volume":"132","author":"F Cao","year":"2020","journal-title":"Neural Networks: the Official Journal of the International Neural Network Society"},{"issue":"22","key":"pone.0279706.ref028","doi-asserted-by":"crossref","first-page":"2804","DOI":"10.1093\/eurheartj\/ehs250","article-title":"Impact of resting heart rate on mortality, disability and cognitive decline in patients after ischaemic stroke","volume":"33","author":"M B\u00f6hm","year":"2012","journal-title":"European Heart Journal"},{"issue":"1","key":"pone.0279706.ref029","doi-asserted-by":"crossref","first-page":"66","DOI":"10.4103\/0972-2327.107710","article-title":"Electrocardiographic abnormalities in acute cerebrovascular events in patients with\/without cardiovascular disease","volume":"16","author":"M Togha","year":"2013","journal-title":"Annals of Indian Academy of Neurology"},{"issue":"5","key":"pone.0279706.ref030","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1111\/j.1368-5031.2004.00010.x","article-title":"Electrocardiographic changes in patients with ischaemic stroke and their prognostic importance","volume":"58","author":"A Dogan","year":"2004","journal-title":"International Journal of Clinical Practice"},{"key":"pone.0279706.ref031","doi-asserted-by":"crossref","first-page":"759822","DOI":"10.3389\/fneur.2021.759822","article-title":"Prognostic Significance of Prolonged Corrected QT Interval in Acute Ischemic Stroke.","volume":"12","author":"S-H Ahn","year":"2021","journal-title":"Frontiers In Neurology"},{"key":"pone.0279706.ref032","first-page":"201","article-title":"Assessment scales in stroke: clinimetric and clinical considerations","volume":"8","author":"JK Harrison","year":"2013","journal-title":"Clinical Interventions In Aging"},{"issue":"7","key":"pone.0279706.ref033","doi-asserted-by":"crossref","first-page":"2007","DOI":"10.1161\/STROKEAHA.117.017866","article-title":"Evolution of the Modified Rankin Scale and Its Use in Future Stroke Trials","volume":"48","author":"JP Broderick","year":"2017","journal-title":"Stroke"},{"issue":"5","key":"pone.0279706.ref034","doi-asserted-by":"crossref","first-page":"494","DOI":"10.3109\/07853890.2011.585345","article-title":"Electrocardiographic presentation of global ischemia in acute coronary syndrome predicts poor outcome","volume":"44","author":"KC Nikus","year":"2012","journal-title":"Annals of Medicine"},{"key":"pone.0279706.ref035","first-page":"3762149","article-title":"Clinical Characteristics, Management, and Outcomes of Suspected Poststroke Acute Coronary Syndrome","volume":"2017","author":"SM Biso","year":"2017","journal-title":"Cardiology Research and Practice"},{"issue":"6","key":"pone.0279706.ref036","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1111\/anec.12223","article-title":"Left ventricular hypertrophy: The relationship between the electrocardiogram and cardiovascular magnetic resonance imaging","volume":"19","author":"L Bacharova","year":"2014","journal-title":"Ann Noninvasive Electrocardiol"},{"issue":"13","key":"pone.0279706.ref037","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1016\/j.jacc.2017.01.037","article-title":"Electrocardiographic Criteria for the Diagnosis of Left Ventricular Hypertrophy","volume":"69","author":"JG Peguero","year":"2017","journal-title":"Journal of the American College of Cardiology"},{"issue":"2212","key":"pone.0279706.ref038","first-page":"20200258","article-title":"Optimal ECG-lead selection increases generalizability of deep learning on ECG abnormality classification.","volume":"379","author":"C Lai","year":"2021","journal-title":"Philosophical Transactions Series A, Mathematical, Physical, and Engineering Sciences"},{"issue":"23","key":"pone.0279706.ref039","doi-asserted-by":"crossref","first-page":"1976","DOI":"10.1212\/01.wnl.0000436937.32410.32","article-title":"B-type natriuretic peptides and mortality after stroke: a systematic review and meta-analysis","volume":"81","author":"T Garc\u00eda-Berrocoso","year":"2013","journal-title":"Neurology"},{"issue":"6","key":"pone.0279706.ref040","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1097\/HJH.0000000000001704","article-title":"Blood pressure in acute ischemic stroke: challenges in trial interpretation and clinical management: position of the ESH Working Group on Hypertension and the Brain","volume":"36","author":"D G\u0105secki","year":"2018","journal-title":"Journal of Hypertension"},{"issue":"3","key":"pone.0279706.ref041","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1016\/j.ijcard.2014.10.036","article-title":"Prognostic relevance of cardiac troponin T levels and their dynamic changes measured with a high-sensitivity assay in acute ischaemic stroke: analyses from the TRELAS cohort","volume":"177","author":"JF Scheitz","year":"2014","journal-title":"International Journal of Cardiology"},{"issue":"1","key":"pone.0279706.ref042","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1186\/s12877-021-02570-7","article-title":"Relationship between blood pressure levels and ischemic stroke, myocardial infarction, and mortality in very elderly patients taking antihypertensives: a nationwide population-based cohort study.","volume":"21","author":"M-S Song","year":"2021","journal-title":"BMC Geriatrics"},{"issue":"5","key":"pone.0279706.ref043","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1161\/STROKEAHA.116.014561","article-title":"Prevalence of Positive Troponin and Echocardiogram Findings and Association With Mortality in Acute Ischemic Stroke","volume":"48","author":"P Wrigley","year":"2017","journal-title":"Stroke"},{"issue":"7","key":"pone.0279706.ref044","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1161\/01.STR.20.7.871","article-title":"Measurements of acute cerebral infarction: lesion size by computed tomography","volume":"20","author":"T Brott","year":"1989","journal-title":"Stroke"},{"issue":"10","key":"pone.0279706.ref045","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1212\/WNL.26.10.924","article-title":"Computerized axial transverse tomography in cerebrovascular disease","volume":"26","author":"WR Kinkel","year":"1976","journal-title":"Neurology"},{"issue":"12","key":"pone.0279706.ref046","doi-asserted-by":"crossref","first-page":"2272","DOI":"10.1161\/01.STR.26.12.2272","article-title":"Measurement of infarct size using MRI predicts prognosis in middle cerebral artery infarction","volume":"26","author":"DE Saunders","year":"1995","journal-title":"Stroke"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0279706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T18:33:32Z","timestamp":1672166012000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0279706"}},"subtitle":[],"editor":[{"given":"Felix","family":"Albu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,12,27]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0279706","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,27]]}}}