{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1360298345524252032.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1016/j.jjcc.2021.08.029"}},{"identifier":{"@type":"URI","@value":"https://api.elsevier.com/content/article/PII:S091450872100232X?httpAccept=text/xml"}},{"identifier":{"@type":"URI","@value":"https://api.elsevier.com/content/article/PII:S091450872100232X?httpAccept=text/plain"}},{"identifier":{"@type":"PMID","@value":"34544652"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@value":"Deep learning model to detect significant aortic regurgitation using electrocardiography"}],"description":[{"notation":[{"@value":"Aortic regurgitation (AR) is a common heart disease, with a relatively high prevalence of 4.9% in the Framingham Heart Study. Because the prevalence increases with advancing age, an upward shift in the age distribution may increase the burden of AR. To provide an effective screening method for AR, we developed a deep learning-based artificial intelligence algorithm for the diagnosis of significant AR using electrocardiography (ECG).Our dataset comprised 29,859 paired data of ECG and echocardiography, including 412 AR cases, from January 2015 to December 2019. This dataset was divided into training, validation, and test datasets. We developed a multi-input neural network model, which comprised a two-dimensional convolutional neural network (2D-CNN) using raw ECG data and a fully connected deep neural network (FC-DNN) using ECG features, and compared its performance with the performances of a 2D-CNN model and other machine learning models. In addition, we used gradient-weighted class activation mapping (Grad-CAM) to identify which parts of ECG waveforms had the most effect on algorithm decision making.The area under the receiver operating characteristic curve of the multi-input model (0.802; 95% CI, 0.762-0.837) was significantly greater than that of the 2D-CNN model alone (0.734; 95% CI, 0.679-0.783; p0.001) and those of other machine learning models. Grad-CAM demonstrated that the multi-input model tended to focus on the QRS complex in leads I and aVL when detecting AR.The multi-input deep learning model using 12-lead ECG data could detect significant AR with modest predictive value."}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380298345524252043","@type":"Researcher","foaf:name":[{"@value":"Shinnosuke Sawano"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252045","@type":"Researcher","foaf:name":[{"@value":"Satoshi Kodera"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252040","@type":"Researcher","foaf:name":[{"@value":"Susumu Katsushika"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252037","@type":"Researcher","foaf:name":[{"@value":"Mitsuhiko Nakamoto"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252035","@type":"Researcher","foaf:name":[{"@value":"Kota Ninomiya"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252034","@type":"Researcher","foaf:name":[{"@value":"Hiroki Shinohara"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252038","@type":"Researcher","foaf:name":[{"@value":"Yasutomi Higashikuni"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252047","@type":"Researcher","foaf:name":[{"@value":"Koki Nakanishi"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252039","@type":"Researcher","foaf:name":[{"@value":"Tomoko Nakao"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252036","@type":"Researcher","foaf:name":[{"@value":"Tomohisa Seki"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252044","@type":"Researcher","foaf:name":[{"@value":"Norifumi Takeda"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252041","@type":"Researcher","foaf:name":[{"@value":"Katsuhito Fujiu"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252042","@type":"Researcher","foaf:name":[{"@value":"Masao Daimon"}]},{"@id":"https://cir.nii.ac.jp/crid/1420564276171718016","@type":"Researcher","personIdentifier":[{"@type":"KAKEN_RESEARCHERS","@value":"20396683"},{"@type":"NRID","@value":"1000020396683"},{"@type":"NRID","@value":"9000314067661"},{"@type":"NRID","@value":"9000412211804"},{"@type":"NRID","@value":"9000003877316"},{"@type":"NRID","@value":"9000384339950"},{"@type":"NRID","@value":"9000398259765"},{"@type":"NRID","@value":"9000412085736"},{"@type":"NRID","@value":"9000414813069"},{"@type":"NRID","@value":"9000404629529"},{"@type":"NRID","@value":"9000004037887"},{"@type":"NRID","@value":"9000391677499"},{"@type":"NRID","@value":"9000324641423"},{"@type":"NRID","@value":"9000290820275"},{"@type":"NRID","@value":"9000408652304"},{"@type":"NRID","@value":"9000345350621"},{"@type":"NRID","@value":"9000414514134"},{"@type":"NRID","@value":"9000391677054"},{"@type":"NRID","@value":"9000345350617"},{"@type":"NRID","@value":"9000257831323"},{"@type":"NRID","@value":"9000311066137"},{"@type":"NRID","@value":"9000409988047"},{"@type":"NRID","@value":"9000399380621"},{"@type":"NRID","@value":"9000345350669"},{"@type":"NRID","@value":"9000314067028"},{"@type":"NRID","@value":"9000408424227"},{"@type":"NRID","@value":"9000377394956"},{"@type":"NRID","@value":"9000257776384"},{"@type":"NRID","@value":"9000380480219"},{"@type":"NRID","@value":"9000290821401"},{"@type":"NRID","@value":"9000414514151"},{"@type":"NRID","@value":"9000410299159"},{"@type":"NRID","@value":"9000410299075"},{"@type":"NRID","@value":"9000397684516"},{"@type":"NRID","@value":"9000257776703"},{"@type":"NRID","@value":"9000415313875"},{"@type":"NRID","@value":"9000403989412"},{"@type":"NRID","@value":"9000409784711"},{"@type":"RESEARCHMAP","@value":"https://researchmap.jp/akzwcardio"}],"foaf:name":[{"@value":"Hiroshi Akazawa"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252032","@type":"Researcher","foaf:name":[{"@value":"Hiroyuki Morita"}]},{"@id":"https://cir.nii.ac.jp/crid/1380298345524252033","@type":"Researcher","foaf:name":[{"@value":"Issei Komuro"}]}],"publication":{"publicationIdentifier":[{"@type":"PISSN","@value":"09145087"}],"prism:publicationName":[{"@value":"Journal of Cardiology"}],"dc:publisher":[{"@value":"Elsevier BV"}],"prism:publicationDate":"2022-03","prism:volume":"79","prism:number":"3","prism:startingPage":"334","prism:endingPage":"341"},"reviewed":"false","dcterms:accessRights":"http://purl.org/coar/access_right/c_abf2","dc:rights":["https://www.elsevier.com/tdm/userlicense/1.0/","https://www.elsevier.com/legal/tdmrep-license","http://creativecommons.org/licenses/by-nc-nd/4.0/"],"url":[{"@id":"https://api.elsevier.com/content/article/PII:S091450872100232X?httpAccept=text/xml"},{"@id":"https://api.elsevier.com/content/article/PII:S091450872100232X?httpAccept=text/plain"}],"createdAt":"2021-09-17","modifiedAt":"2025-10-12","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=Electrocardiography","dc:title":"Electrocardiography"},{"@id":"https://cir.nii.ac.jp/all?q=Deep%20Learning","dc:title":"Deep Learning"},{"@id":"https://cir.nii.ac.jp/all?q=Artificial%20Intelligence","dc:title":"Artificial Intelligence"},{"@id":"https://cir.nii.ac.jp/all?q=Aortic%20Valve%20Insufficiency","dc:title":"Aortic Valve Insufficiency"},{"@id":"https://cir.nii.ac.jp/all?q=Humans","dc:title":"Humans"},{"@id":"https://cir.nii.ac.jp/all?q=Algorithms","dc:title":"Algorithms"},{"@id":"https://cir.nii.ac.jp/all?q=Retrospective%20Studies","dc:title":"Retrospective Studies"}],"project":[{"@id":"https://cir.nii.ac.jp/crid/1040006432273886848","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"21K08023"},{"@type":"JGN","@value":"JP21K08023"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-21K08023/"}],"notation":[{"@language":"ja","@value":"マルファン症候群において血管内皮由来酸化ストレスに起因する大動脈瘤形成の分子病態"},{"@language":"en","@value":"Molecular pathogenesis of endothelial oxidative stress-triggered formation of aortic aneurysm in Marfan syndrome"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360011145969971456","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292621015209472","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Prevalence and clinical determinants of mitral, tricuspid, and aortic regurgitation (the Framingham Heart Study)"}]},{"@id":"https://cir.nii.ac.jp/crid/1360302866851079808","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Age prediction from coronary angiography using a deep neural network: Age as a potential label to extract prognosis-related imaging features"}]},{"@id":"https://cir.nii.ac.jp/crid/1360306905610253696","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"TRAITER: transformer-guided diagnosis and prognosis of heart failure using cell nuclear morphology and DNA damage marker"}]},{"@id":"https://cir.nii.ac.jp/crid/1360584346301720064","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Predictors of Progression in Patients With Stage B Aortic Regurgitation"}]},{"@id":"https://cir.nii.ac.jp/crid/1360584346481702656","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Aortic Valve Regurgitation: A Comprehensive Review"}]},{"@id":"https://cir.nii.ac.jp/crid/1360587984078315904","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Applying masked autoencoder-based self-supervised learning for high-capability vision transformers of electrocardiographies"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855567870783488","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach"}]},{"@id":"https://cir.nii.ac.jp/crid/1360855568717875328","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The ventricular complex in left ventricular hypertrophy as obtained by unipolar precordial and limb leads"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865817585820544","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Causes of false-negative auscultation of regurgitant lesions"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865817586610048","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Prevalence and correlates of aortic regurgitation in american indians: the Strong Heart Study"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865817586881664","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Artificial intelligence capable of detecting left ventricular hypertrophy: pushing the limits of the electrocardiogram?"}]},{"@id":"https://cir.nii.ac.jp/crid/1360865818239596416","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Doppler and echocardiographic characteristics of patients having an Austin Flint murmur."}]},{"@id":"https://cir.nii.ac.jp/crid/1361131419403811584","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"New artificial intelligence prediction model using serial prothrombin time international normalized ratio measurements in atrial fibrillation patients on vitamin K antagonists: GARFIELD-AF"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418519907043840","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Valvular Heart Disease"}]},{"@id":"https://cir.nii.ac.jp/crid/1361418521437038208","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Valvular Heart Disease: Diagnosis and Management"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981469239703936","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs"}]},{"@id":"https://cir.nii.ac.jp/crid/1362262943455919872","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction"}]},{"@id":"https://cir.nii.ac.jp/crid/1362544419903332864","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Electrocardiographic diagnosis of acute myocardial infarction: Current concepts for the clinician"}]},{"@id":"https://cir.nii.ac.jp/crid/1363388844210719488","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Deep Learning–Based Algorithm for Detecting Aortic Stenosis Using Electrocardiography"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951795812155136","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233268549425152","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Recommendations for Noninvasive Evaluation of Native Valvular Regurgitation"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270717161728","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Artificial intelligence for detecting mitral regurgitation using electrocardiography"}]},{"@id":"https://cir.nii.ac.jp/crid/1370865816799447175","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management"}]},{"@id":"https://cir.nii.ac.jp/crid/1370865816799447176","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Grad-cam: Visual explanations from deep networks via gradient-based localization"}]},{"@id":"https://cir.nii.ac.jp/crid/1370865816799447177","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Causability and explainability of artificial intelligence in medicine"}]},{"@id":"https://cir.nii.ac.jp/crid/1390017511236219520","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Multimodality Risk Assessment of Patients with Ischemic Heart Disease Using Deep Learning Models Applied to Electrocardiograms and Chest X-rays"}]},{"@id":"https://cir.nii.ac.jp/crid/1390575064368851584","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Automatic Detection of Left Ventricular Dilatation and Hypertrophy from Electrocardiograms Using Deep Learning"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1016/j.jjcc.2021.08.029"},{"@type":"KAKEN","@value":"PRODUCT-25082815"},{"@type":"OPENAIRE","@value":"doi_dedup___::f28d93a9025721a1dade94b17bf4cd9f"},{"@type":"CROSSREF","@value":"10.1536/ihj.23-402_references_DOI_BsdM2ZnRbk5bIHWbYPz3SE5ot0C"},{"@type":"CROSSREF","@value":"10.1371/journal.pone.0276928_references_DOI_BsdM2ZnRbk5bIHWbYPz3SE5ot0C"},{"@type":"CROSSREF","@value":"10.1093/bioinformatics/btae610_references_DOI_BsdM2ZnRbk5bIHWbYPz3SE5ot0C"},{"@type":"CROSSREF","@value":"10.1536/ihj.22-132_references_DOI_BsdM2ZnRbk5bIHWbYPz3SE5ot0C"},{"@type":"CROSSREF","@value":"10.1371/journal.pone.0307978_references_DOI_BsdM2ZnRbk5bIHWbYPz3SE5ot0C"}]}