{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T04:22:00Z","timestamp":1775794920895,"version":"3.50.1"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005713","name":"Technical University of Munich","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005713","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Else Kr\u00f6ner-Fresenius Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Aims<\/jats:title>\n                  <jats:p>Hypothesizing that aortic outflow velocity profiles contain more valuable information about aortic valve obstruction and left ventricular contractility than can be captured by the human eye, features of the complex geometry of Doppler tracings from patients with severe aortic stenosis (AS) were extracted by a convolutional neural network (CNN).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods and results<\/jats:title>\n                  <jats:p>After pre-training a CNN (VGG-16) on a large data set (ImageNet data set; 14 million images belonging to 1000 classes), the convolutional part was employed to transform Doppler tracings to 1D arrays. Among 366 eligible patients [age: 79.8 \u00b1 6.77 years; 146 (39.9%) women] with pre-procedural echocardiography and right heart catheterization prior to transcatheter aortic valve replacement (TAVR), good quality Doppler tracings from 101 patients were analysed. The convolutional part of the pre-trained VGG-16 model in conjunction with principal component analysis and k-means clustering distinguished two shapes of aortic outflow velocity profiles. Kaplan\u2013Meier analysis revealed that mortality in patients from Cluster 2 (n = 40, 39.6%) was significantly increased [hazard ratio (HR) for 2-year mortality: 3; 95% confidence interval (CI): 1\u20138.9]. Apart from reduced cardiac output and mean aortic valve gradient, patients from Cluster 2 were also characterized by signs of pulmonary hypertension, impaired right ventricular function, and right atrial enlargement. After training an extreme gradient boosting algorithm on these 101 patients, validation on the remaining 265 patients confirmed that patients assigned to Cluster 2 show increased mortality (HR for 2-year mortality: 2.6; 95% CI: 1.4\u20135.1, P-value: 0.004).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Transfer learning enables sophisticated pattern recognition even in clinical data sets of limited size. Importantly, it is the left ventricular compensation capacity in the face of increased afterload, and not so much the actual obstruction of the aortic valve, that determines fate after TAVR.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztac004","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T07:31:10Z","timestamp":1650612670000},"page":"153-168","source":"Crossref","is-referenced-by-count":18,"title":["Harnessing feature extraction capacities from a pre-trained convolutional neural network (VGG-16) for the unsupervised distinction of aortic outflow velocity profiles in patients with severe aortic stenosis"],"prefix":"10.1093","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1798-550X","authenticated-orcid":false,"given":"Mark","family":"Lachmann","sequence":"first","affiliation":[{"name":"First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Stra\u00dfe 22 , 81675 Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4823-3247","authenticated-orcid":false,"given":"Elena","family":"Rippen","sequence":"additional","affiliation":[{"name":"First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Stra\u00dfe 22 , 81675 Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5683-5889","authenticated-orcid":false,"given":"Daniel","family":"Rueckert","sequence":"additional","affiliation":[{"name":"Institute for AI and Informatics in Medicine, Faculty of Informatics and Medicine, Klinikum rechts der Isar, Technical University of Munich , Munich , Germany"},{"name":"Department of Computing, Imperial College London , London , UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tibor","family":"Schuster","sequence":"additional","affiliation":[{"name":"Department of Family Medicine, McGill University , Montreal, Quebec , Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0728-2819","authenticated-orcid":false,"given":"Erion","family":"Xhepa","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7159-8271","authenticated-orcid":false,"given":"Moritz","family":"von Scheidt","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Costanza","family":"Pellegrini","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9077-1447","authenticated-orcid":false,"given":"Teresa","family":"Trenkwalder","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"Rheude","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9634-5908","authenticated-orcid":false,"given":"Anja","family":"Stundl","sequence":"additional","affiliation":[{"name":"First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Stra\u00dfe 22 , 81675 Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruth","family":"Thalmann","sequence":"additional","affiliation":[{"name":"First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Stra\u00dfe 22 , 81675 Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Harmsen","sequence":"additional","affiliation":[{"name":"Department of Physics, University of Johannesburg , Auckland Park , South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinsuke","family":"Yuasa","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Keio University School of Medicine , Minato, Tokyo , Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6428-3001","authenticated-orcid":false,"given":"Heribert","family":"Schunkert","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4341-891X","authenticated-orcid":false,"given":"Adnan","family":"Kastrati","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Joner","sequence":"additional","affiliation":[{"name":"Department of Cardiology, German Heart Centre Munich, Technical University of Munich , Munich , Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1046-7275","authenticated-orcid":false,"given":"Christian","family":"Kupatt","sequence":"additional","affiliation":[{"name":"First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Stra\u00dfe 22 , 81675 Munich, Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4948-4846","authenticated-orcid":false,"given":"Karl Ludwig","family":"Laugwitz","sequence":"additional","affiliation":[{"name":"First Department of Medicine, Klinikum rechts der Isar, Technical University of Munich , Ismaninger Stra\u00dfe 22 , 81675 Munich, Germany"},{"name":"DZHK (German Centre for Cardiovascular Research), partner site Munich Heart Alliance , Munich , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,4,22]]},"reference":[{"key":"2022111811394918200_ztac004-B1","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1038\/s41591-020-0870-z","article-title":"Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network","volume":"26","author":"Raghunath","year":"2020","journal-title":"Nat Med"},{"key":"2022111811394918200_ztac004-B2","doi-asserted-by":"crossref","first-page":"3111","DOI":"10.1038\/s41467-019-11012-3","article-title":"Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences","volume":"10","author":"Fries","year":"2019","journal-title":"Nat Commun"},{"key":"2022111811394918200_ztac004-B3","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1093\/eurheartj\/ehy915","article-title":"Machine learning algorithms estimating prognosis and guiding therapy in adult congenital heart disease: data from a single tertiary centre including 10 019 patients","volume":"40","author":"Diller","year":"2019","journal-title":"Eur Heart J"},{"key":"2022111811394918200_ztac004-B4","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1056\/NEJMoa1901183","article-title":"Large-scale assessment of a smartwatch to identify atrial fibrillation","volume":"381","author":"Perez","year":"2019","journal-title":"N Engl J Med"},{"key":"2022111811394918200_ztac004-B5","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCIMAGING.119.009707","article-title":"Unsupervised cluster analysis of patients with aortic stenosis reveals distinct population with different phenotypes and outcomes","volume":"13","author":"Kwak","year":"2020","journal-title":"Circ Cardiovasc Imaging"},{"key":"2022111811394918200_ztac004-B6","doi-asserted-by":"crossref","first-page":"1707","DOI":"10.1016\/j.jcmg.2021.03.020","article-title":"A machine-learning framework to identify distinct phenotypes of aortic stenosis severity","volume":"14","author":"Sengupta","year":"2021","journal-title":"JACC Cardiovasc Imaging"},{"key":"2022111811394918200_ztac004-B7","doi-asserted-by":"crossref","first-page":"3351","DOI":"10.1093\/eurheartj\/ehx381","article-title":"Staging classification of aortic stenosis based on the extent of cardiac damage","volume":"38","author":"G\u00e9n\u00e9reux","year":"2017","journal-title":"Eur Heart J"},{"key":"2022111811394918200_ztac004-B8","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1056\/NEJMoa1202277","article-title":"Transcatheter aortic-valve replacement for inoperable severe aortic stenosis","volume":"366","author":"Makkar","year":"2012","journal-title":"N Engl J Med"},{"key":"2022111811394918200_ztac004-B9","doi-asserted-by":"crossref","first-page":"2739","DOI":"10.1093\/eurheartj\/ehx391","article-title":"2017 ESC\/EACTS Guidelines for the management of valvular heart disease","volume":"38","author":"Baumgartner","year":"2017","journal-title":"Eur Heart J"},{"key":"2022111811394918200_ztac004-B10","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1136\/heartjnl-2020-316684","article-title":"Determinants and prognostic value of echocardiographic first-phase ejection fraction in aortic stenosis","volume":"106","author":"Bing","year":"2020","journal-title":"Heart"},{"key":"2022111811394918200_ztac004-B11","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1136\/hrt.2005.079038","article-title":"Low \u2018gradient\u2019, low flow aortic stenosis","volume":"92","author":"Chambers","year":"2006","journal-title":"Heart"},{"key":"2022111811394918200_ztac004-B12","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"2022111811394918200_ztac004-B13","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest\u2013non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"key":"2022111811394918200_ztac004-B14","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"2022111811394918200_ztac004-B15","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2022111811394918200_ztac004-B16","doi-asserted-by":"crossref","first-page":"2127","DOI":"10.1016\/j.jcin.2021.08.034","article-title":"Subphenotyping of patients with aortic stenosis by unsupervised agglomerative clustering of echocardiographic and hemodynamic data","volume":"14","author":"Lachmann","year":"2021","journal-title":"JACC Cardiovasc Interv"},{"key":"2022111811394918200_ztac004-B17","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1002\/ejhf.1322","article-title":"Haemodynamic mechanisms and long-term prognostic impact of pulmonary hypertension in patients with severe aortic stenosis undergoing valve replacement: Impact of PH in severe aortic stenosis","volume":"21","author":"Weber","year":"2019","journal-title":"Eur J Heart Fail"},{"key":"2022111811394918200_ztac004-B18","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.jcmg.2020.09.031","article-title":"Structural and functional correlates of gradient-area patterns in severe aortic stenosis and normal ejection fraction","volume":"14","author":"Slimani","year":"2021","journal-title":"JACC Cardiovasc Imaging"},{"key":"2022111811394918200_ztac004-B19","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1136\/heartjnl-2017-311978","article-title":"Outcomes of persistent pulmonary hypertension following transcatheter aortic valve replacement","volume":"104","author":"Masri","year":"2018","journal-title":"Heart"},{"key":"2022111811394918200_ztac004-B20","doi-asserted-by":"crossref","first-page":"2659","DOI":"10.1093\/eurheartj\/ehy251","article-title":"The incidence and prognostic implications of worsening right ventricular function after surgical or transcatheter aortic valve replacement: insights from PARTNER IIA","volume":"39","author":"Cremer","year":"2018","journal-title":"Eur Heart J"},{"key":"2022111811394918200_ztac004-B21","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/j.jcmg.2017.12.015","article-title":"Prognostic value of right ventricular dysfunction on clinical outcomes after transcatheter aortic valve replacement","volume":"12","author":"Asami","year":"2019","journal-title":"JACC Cardiovasc Imaging"},{"key":"2022111811394918200_ztac004-B22","doi-asserted-by":"crossref","first-page":"570689","DOI":"10.3389\/fcvm.2020.570689","article-title":"Multimodality imaging for discordant low-gradient aortic stenosis: assessing the valve and the myocardium","volume":"7","author":"Guzzetti","year":"2020","journal-title":"Front Cardiovasc Med"},{"key":"2022111811394918200_ztac004-B23","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1016\/j.jcmg.2021.05.027","article-title":"Considering the hazards of aortic valve stenosis","volume":"14","author":"Little","year":"2021","journal-title":"JACC Cardiovasc Imaging"},{"key":"2022111811394918200_ztac004-B24","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.ahj.2016.08.009","article-title":"Rationale and design of the Transcatheter Aortic Valve Replacement to Unload the Left ventricle in patients with Advanced heart failure (TAVR UNLOAD) trial","volume":"182","author":"Spitzer","year":"2016","journal-title":"Am Heart J"},{"key":"2022111811394918200_ztac004-B25","doi-asserted-by":"crossref","first-page":"2856","DOI":"10.1161\/CIRCULATIONAHA.106.668681","article-title":"Paradoxical low-flow, low-gradient severe aortic stenosis despite preserved ejection fraction is associated with higher afterload and reduced survival","volume":"115","author":"Hachicha","year":"2007","journal-title":"Circulation"},{"key":"2022111811394918200_ztac004-B26","doi-asserted-by":"crossref","first-page":"2645","DOI":"10.1093\/eurheartj\/ehw096","article-title":"Low-gradient aortic stenosis","volume":"37","author":"Clavel","year":"2016","journal-title":"Eur Heart J"},{"key":"2022111811394918200_ztac004-B27","first-page":"50","article-title":"European union regulations on algorithmic decision-making and a \u201cright to explanation\u201d","volume":"38","author":"Goodman","year":"2017","journal-title":"AI Mag"},{"key":"2022111811394918200_ztac004-B28","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"key":"2022111811394918200_ztac004-B29","doi-asserted-by":"crossref","first-page":"e021873","DOI":"10.1161\/JAHA.121.021873","article-title":"Relationship between the ratio of acceleration time\/ejection time and mortality in patients with high-gradient severe aortic stenosis","volume":"10","author":"Altes","year":"2021","journal-title":"J Am Heart Assoc"},{"key":"2022111811394918200_ztac004-B30","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCIMAGING.116.005207","article-title":"Beyond Bernoulli: improving the accuracy and precision of noninvasive estimation of peak pressure drops","volume":"10","author":"Donati","year":"2017","journal-title":"Circ Cardiovasc Imaging"},{"key":"2022111811394918200_ztac004-B31","first-page":"1135","author":"Ribeiro","year":"2016"},{"key":"2022111811394918200_ztac004-B32","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"AI for radiographic COVID-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2022111811394918200_ztac004-B33","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1162\/neco.1996.8.7.1341","article-title":"The lack of a priori distinctions between learning algorithms","volume":"8","author":"Wolpert","year":"1996","journal-title":"Neural Comput"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/advance-article-pdf\/doi\/10.1093\/ehjdh\/ztac004\/43153389\/ztac004.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/3\/2\/153\/47117014\/ztac004.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/3\/2\/153\/47117014\/ztac004.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T11:46:55Z","timestamp":1668772015000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/3\/2\/153\/6555836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,22]]},"references-count":33,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,4,22]]},"published-print":{"date-parts":[[2022,7,6]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztac004","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,6,22]]},"published":{"date-parts":[[2022,4,22]]}}}