{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:03:04Z","timestamp":1778821384321,"version":"3.51.4"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2020,6,26]],"date-time":"2020-06-26T00:00:00Z","timestamp":1593129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"The Research Unit Hypertension and Cardiovascular Epidemiology"},{"name":"Internal Funds KU Leuven","award":["PDM\/19\/153"],"award-info":[{"award-number":["PDM\/19\/153"]}]},{"DOI":"10.13039\/501100003130","name":"Research Foundation Flanders","doi-asserted-by":"publisher","award":["G.0880.13"],"award-info":[{"award-number":["G.0880.13"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Research Foundation Flanders","doi-asserted-by":"publisher","award":["11Z0916N"],"award-info":[{"award-number":["11Z0916N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Research Foundation Flanders","doi-asserted-by":"publisher","award":["G0C5319N"],"award-info":[{"award-number":["G0C5319N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Aims<\/jats:title>\n                  <jats:p>Both left ventricular (LV) diastolic dysfunction (LVDD) and hypertrophy (LVH) as assessed by echocardiography are independent prognostic markers of future cardiovascular events in the community. However, selective screening strategies to identify individuals at risk who would benefit most from cardiac phenotyping are lacking. We, therefore, assessed the utility of several machine learning (ML) classifiers built on routinely measured clinical, biochemical, and electrocardiographic features for detecting subclinical LV abnormalities.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods and results<\/jats:title>\n                  <jats:p>We included 1407 participants (mean age, 51\u2009years, 51% women) randomly recruited from the general population. We used echocardiographic parameters reflecting LV diastolic function and structure to define LV abnormalities (LVDD, n\u2009=\u2009252; LVH, n\u2009=\u2009272). Next, four supervised ML algorithms (XGBoost, AdaBoost, Random Forest (RF), Support Vector Machines, and Logistic regression) were used to build classifiers based on clinical data (67 features) to categorize LVDD and LVH. We applied a nested 10-fold cross-validation set-up. XGBoost and RF classifiers exhibited a high area under the receiver operating characteristic curve with values between 86.2% and 88.1% for predicting LVDD and between 77.7% and 78.5% for predicting LVH. Age, body mass index, different components of blood pressure, history of hypertension, antihypertensive treatment, and various electrocardiographic variables were the top selected features for predicting LVDD and LVH.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>XGBoost and RF classifiers combining routinely measured clinical, laboratory, and electrocardiographic data predicted LVDD and LVH with high accuracy. These ML classifiers might be useful to pre-select individuals in whom further echocardiographic examination, monitoring, and preventive measures are warranted.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/ehjci\/jeaa135","type":"journal-article","created":{"date-parts":[[2020,5,6]],"date-time":"2020-05-06T03:20:04Z","timestamp":1588735204000},"page":"1208-1217","source":"Crossref","is-referenced-by-count":17,"title":["Applying machine learning to detect early stages of cardiac remodelling and dysfunction"],"prefix":"10.1093","volume":"22","author":[{"given":"Franti\u0161ek","family":"Sabov\u010dik","sequence":"first","affiliation":[{"name":"Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven Department of Cardiovascular Sciences, University of Leuven, Campus Sint Rafa\u00ebl, Kapucijnenvoer 33, Block h, Box 7001, B 3000 Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8059-7692","authenticated-orcid":false,"given":"Nicholas","family":"Cauwenberghs","sequence":"additional","affiliation":[{"name":"Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven Department of Cardiovascular Sciences, University of Leuven, Campus Sint Rafa\u00ebl, Kapucijnenvoer 33, Block h, Box 7001, B 3000 Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8440-742X","authenticated-orcid":false,"given":"Dmitry","family":"Kouznetsov","sequence":"additional","affiliation":[{"name":"Department of Life Science and Technologies, IMEC, Kapeldreef 75, 3001 Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francois","family":"Haddad","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine, Stanford University School of Medicine, and Stanford Cardiovascular Institute, 300 Pasteur Dr H2170, Stanford, CA 94305, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0950-0012","authenticated-orcid":false,"given":"Amparo","family":"Alonso-Betanzos","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of A Coru\u00f1a, Campus de Elvi\u00f1a 15071, A Coru\u00f1a (03082), Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Celine","family":"Vens","sequence":"additional","affiliation":[{"name":"Public Health and Primary Care, Kulak Kortrijk Campus, University of Leuven, Etienne Sabbelaan 53 - bus 7700, 8500 Kortrijk, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6278-1979","authenticated-orcid":false,"given":"Tatiana","family":"Kuznetsova","sequence":"additional","affiliation":[{"name":"Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven Department of Cardiovascular Sciences, University of Leuven, Campus Sint Rafa\u00ebl, Kapucijnenvoer 33, Block h, Box 7001, B 3000 Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,6,26]]},"reference":[{"key":"2021101918541167200_jeaa135-B1","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"2021101918541167200_jeaa135-B2","first-page":"1805","article-title":"Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges","volume":"38","author":"Goldstein","year":"2017","journal-title":"Eur Heart J"},{"key":"2021101918541167200_jeaa135-B3","doi-asserted-by":"crossref","first-page":"e147","DOI":"10.1016\/j.jacc.2013.05.019","article-title":"2013 ACCF\/AHA guideline for the management of heart failure: a report of the American College of Cardiology Foundation\/American Heart Association Task Force on Practice Guidelines","volume":"62","author":"Yancy","year":"2013","journal-title":"J Am Coll Cardiol"},{"key":"2021101918541167200_jeaa135-B4","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.jacc.2007.03.048","article-title":"Echocardiography in heart failure: applications, utility, and new horizons","volume":"50","author":"Kirkpatrick","year":"2007","journal-title":"J Am Coll Cardiol"},{"key":"2021101918541167200_jeaa135-B5","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1067\/mhj.2001.113218","article-title":"Prognostic implications of left ventricular hypertrophy","volume":"141","author":"Vakili","year":"2001","journal-title":"Am Heart J"},{"key":"2021101918541167200_jeaa135-B6","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.ijcard.2019.09.061","article-title":"The 2013 ACC\/AHA risk score and subclinical cardiac remodeling and dysfunction: complementary in cardiovascular disease prediction","volume":"297","author":"Cauwenberghs","year":"2019","journal-title":"Int J Cardiol"},{"key":"2021101918541167200_jeaa135-B7","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.1093\/eurheartj\/ehy339","article-title":"2018 ESC\/ESH Guidelines for the management of arterial hypertension","volume":"39","author":"Williams","year":"2018","journal-title":"Eur Heart J"},{"key":"2021101918541167200_jeaa135-B8","doi-asserted-by":"crossref","first-page":"e004661","DOI":"10.1161\/CIRCIMAGING.116.004661","article-title":"Additive prognostic value of left ventricular systolic dysfunction in a population-based cohort","volume":"9","author":"Kuznetsova","year":"2016","journal-title":"Circ Cardiovasc Imaging"},{"key":"2021101918541167200_jeaa135-B9","first-page":"161","article-title":"An empirical comparison of supervised learning algorithms","volume":"148","author":"Caruana","year":"2006","journal-title":"ACM Int Conf Proc Ser"},{"key":"2021101918541167200_jeaa135-B10","first-page":"785","author":"Chen","year":"2016"},{"key":"2021101918541167200_jeaa135-B11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2021101918541167200_jeaa135-B12","doi-asserted-by":"crossref","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","article-title":"Multi-class AdaBoost","volume":"2","author":"Zhu","year":"2009","journal-title":"Stat Interface"},{"key":"2021101918541167200_jeaa135-B13","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/S0925-2312(03)00373-4","article-title":"Advanced support vector machines and kernel methods","volume":"55","author":"Sanchez","year":"2003","journal-title":"Neurocomputing"},{"key":"2021101918541167200_jeaa135-B14","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2021101918541167200_jeaa135-B15","first-page":"853","volume-title":"Data Mining and Knowledge Discovery Handbook","author":"Chawla","year":"2006"},{"key":"2021101918541167200_jeaa135-B16","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1142\/S0218001409007326","article-title":"Classification of imbalanced data: a review","volume":"23","author":"Sun","year":"2009","journal-title":"Int J Patt Recogn Artif Intell"},{"key":"2021101918541167200_jeaa135-B17","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/1758-2946-6-10","article-title":"Cross-validation pitfalls when selecting and assessing regression and classification models","volume":"6","author":"Krstajic","year":"2014","journal-title":"J Cheminform"},{"key":"2021101918541167200_jeaa135-B18","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recogn Lett"},{"key":"2021101918541167200_jeaa135-B19","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1016\/j.jclinepi.2015.02.010","article-title":"The precision\u2013recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases","volume":"68","author":"Ozenne","year":"2015","journal-title":"J Clin Epidemiol"},{"key":"2021101918541167200_jeaa135-B20","first-page":"451","volume-title":"Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2013. Lecture Notes in Computer Science","author":"Boyd"},{"key":"2021101918541167200_jeaa135-B21","first-page":"51","author":"Bouckaert","year":"2003"},{"key":"2021101918541167200_jeaa135-B22","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1126\/science.1227001","article-title":"Can non-communicable diseases be prevented? Lessons from studies of populations and individuals","volume":"337","author":"Ezzati","year":"2012","journal-title":"Science"},{"key":"2021101918541167200_jeaa135-B23","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1586\/erc.10.3","article-title":"Systolic and diastolic left ventricular dysfunction: from risk factors to overt heart failure","volume":"8","author":"Kuznetsova","year":"2010","journal-title":"Expert Rev Cardiovasc Ther"},{"key":"2021101918541167200_jeaa135-B24","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"Bzdok","year":"2018","journal-title":"Nat Methods"},{"key":"2021101918541167200_jeaa135-B25","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","author":"Hastie","year":"2009"},{"key":"2021101918541167200_jeaa135-B26","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1016\/j.jcmg.2014.05.008","article-title":"The natural history of left ventricular geometry in the community: clinical correlates and prognostic significance of change in LV geometric pattern","volume":"7","author":"Lieb","year":"2014","journal-title":"JACC Cardiovasc Imaging"},{"key":"2021101918541167200_jeaa135-B27","doi-asserted-by":"crossref","first-page":"e002882","DOI":"10.1161\/CIRCIMAGING.114.002882","article-title":"Longitudinal changes in left ventricular diastolic function in a general population","volume":"8","author":"Kuznetsova","year":"2015","journal-title":"Circ Cardiovasc Imaging"},{"key":"2021101918541167200_jeaa135-B28","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.1016\/j.jacc.2018.02.024","article-title":"Prediction of abnormal myocardial relaxation from signal processed surface ECG","volume":"71","author":"Sengupta","year":"2018","journal-title":"J Am Coll Cardiol"},{"key":"2021101918541167200_jeaa135-B29","volume-title":"Encyclopedia of Machine Learning","author":"Brown","year":"2011"}],"container-title":["European Heart Journal - Cardiovascular Imaging"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/ehjcimaging\/article-pdf\/22\/10\/1208\/40759000\/jeaa135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/ehjcimaging\/article-pdf\/22\/10\/1208\/40759000\/jeaa135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T23:45:14Z","timestamp":1634773514000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjcimaging\/article\/22\/10\/1208\/5862911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,26]]},"references-count":29,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2020,6,26]]},"published-print":{"date-parts":[[2021,9,20]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjci\/jeaa135","relation":{},"ISSN":["2047-2404","2047-2412"],"issn-type":[{"value":"2047-2404","type":"print"},{"value":"2047-2412","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,10,1]]},"published":{"date-parts":[[2020,6,26]]}}}