{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:43:51Z","timestamp":1783572231878,"version":"3.55.0"},"reference-count":42,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2021,2,5]],"date-time":"2021-02-05T00:00:00Z","timestamp":1612483200000},"content-version":"unspecified","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2021,1,15]]},"published-print":{"date-parts":[[2021,2]]},"abstract":"<jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Brugada syndrome (BrS) is an ion channelopathy that predisposes affected patients to spontaneous ventricular tachycardia\/fibrillation (VT\/VF) and sudden cardiac death. The aim of this study is to examine the predictive factors of spontaneous VT\/VF.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>This was a territory-wide retrospective cohort study of patients diagnosed with BrS between 1997 and 2019. The primary outcome was spontaneous VT\/VF. Cox regression was used to identify significant risk predictors. Non-linear interactions between variables (latent patterns) were extracted using non-negative matrix factorisation (NMF) and used as inputs into the random survival forest (RSF) model.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>This study included 516 consecutive BrS patients (mean age of initial presentation=50\u00b116 years, male=92%) with a median follow-up of 86 (IQR: 45\u2013118) months. The cohort was divided into subgroups based on initial disease manifestation: asymptomatic (n=314), syncope (n=159) or VT\/VF (n=41). Annualised event rates per person-year were 1.70%, 0.05% and 0.01% for the VT\/VF, syncope and asymptomatic subgroups, respectively. Multivariate Cox regression analysis revealed initial presentation of VT\/VF (HR=24.0, 95% CI=1.21 to 479, p=0.037) and SD of P-wave duration (HR=1.07, 95% CI=1.00 to 1.13, p=0.044) were significant predictors. The NMF-RSF showed the best predictive performance compared with RSF and Cox regression models (precision: 0.87\u2009vs 0.83\u2009vs. 0.76, recall: 0.89\u2009vs. 0.85\u2009vs 0.73, F1-score: 0.88\u2009vs 0.84\u2009vs 0.74).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Clinical history, electrocardiographic markers and investigation results provide important information for risk stratification. Machine learning techniques using NMF and RSF significantly improves overall risk stratification performance.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/openhrt-2020-001505","type":"journal-article","created":{"date-parts":[[2021,2,7]],"date-time":"2021-02-07T02:39:24Z","timestamp":1612665564000},"page":"e001505","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":45,"title":["Territory-wide cohort study of Brugada syndrome in Hong Kong: predictors of long-term outcomes using random survival forests and non-negative matrix factorisation"],"prefix":"10.1136","volume":"8","author":[{"given":"Sharen","family":"Lee","sequence":"first","affiliation":[{"name":"Cardiovascular Analytics Group, Laboratory of Cardiovascular Physiology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiandong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Data Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ka Hou Christien","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Newcastle University, Newcastle upon Tyne, Tyne and Wear, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keith Sai Kit","family":"Leung","sequence":"additional","affiliation":[{"name":"Aston Medical School, Aston University, Birmingham, Birmingham, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ishan","family":"Lakhani","sequence":"additional","affiliation":[{"name":"Cardiovascular Analytics Group, Laboratory of Cardiovascular Physiology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian Chi Kei","family":"Wong","sequence":"additional","affiliation":[{"name":"Research department of Practice and Policy, University College London School of Pharmacy, London, UK"},{"name":"Centre for Safe Medication Practice and Research, Department of Pharmacology and Pharmacy, The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngai Shing","family":"Mok","sequence":"additional","affiliation":[{"name":"Department of Medicine and Geriatrics, Princess Margaret Hospital, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chloe","family":"Mak","sequence":"additional","affiliation":[{"name":"Department of Pathology, Hong Kong Children's Hospital, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamalan","family":"Jeevaratnam","sequence":"additional","affiliation":[{"name":"Faculty of Health and Medical Sciences, University of Surrey, Guildford, Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, City University of Hong Kong, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5510-1253","authenticated-orcid":false,"given":"Gary","family":"Tse","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease, Department of Cardiology, Tianjin Institute of Cardiology, The Second Hospital of Tianjin Medical University, Tianjin, China"},{"name":"Faculty of Health and Medical Sciences, University of Surrey, Guildford, Surrey, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2021,2,5]]},"reference":[{"key":"2025081710000801000_8.1.e001505.1","doi-asserted-by":"publisher","DOI":"10.6515\/ACS.201805_34(3).20180302B"},{"key":"2025081710000801000_8.1.e001505.2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.109.887026"},{"key":"2025081710000801000_8.1.e001505.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2011.08.064"},{"key":"2025081710000801000_8.1.e001505.4","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehq381"},{"key":"2025081710000801000_8.1.e001505.5","doi-asserted-by":"crossref","first-page":"1756","DOI":"10.1093\/eurheartj\/ehx119","article-title":"A score model to predict risk of events in patients with Brugada syndrome","volume":"38","author":"Sieira","year":"2017","journal-title":"Eur Heart J"},{"key":"2025081710000801000_8.1.e001505.6","doi-asserted-by":"publisher","DOI":"10.1093\/europace\/euw033"},{"key":"2025081710000801000_8.1.e001505.7","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1093\/europace\/euy144","article-title":"First-Degree atrioventricular block on basal electrocardiogram predicts future arrhythmic events in patients with Brugada syndrome: a long-term follow-up study from the Veneto region of northeastern Italy","volume":"21","author":"Migliore","year":"2019","journal-title":"Europace"},{"key":"2025081710000801000_8.1.e001505.8","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.117.027983"},{"key":"2025081710000801000_8.1.e001505.9","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.108.816892"},{"key":"2025081710000801000_8.1.e001505.10","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1161\/CIRCULATIONAHA.119.043670","article-title":"Prevalence of Brugada syndrome in a large population of young Singaporean men","volume":"141","author":"Shen","year":"2020","journal-title":"Circulation"},{"key":"2025081710000801000_8.1.e001505.11","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1016\/j.hrthm.2019.07.003","article-title":"Ethnic differences in patients with Brugada syndrome and arrhythmic events: new insights from survey on arrhythmic events in Brugada syndrome","volume":"16","author":"Milman","year":"2019","journal-title":"Heart Rhythm"},{"key":"2025081710000801000_8.1.e001505.12","doi-asserted-by":"crossref","first-page":"132","DOI":"10.3389\/fcvm.2018.00132","article-title":"Higher dispersion measures of conduction and repolarization in type 1 compared to non-type 1 Brugada syndrome patients: an electrocardiographic study from a single center","volume":"5","author":"Tse","year":"2018","journal-title":"Front Cardiovasc Med"},{"key":"2025081710000801000_8.1.e001505.13","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2020.00204","article-title":"Outcomes in Brugada syndrome patients with implantable cardioverter-defibrillators: insights from the SGLT2 registry","volume":"11","author":"Lee","year":"2020","journal-title":"Front Physiol"},{"key":"2025081710000801000_8.1.e001505.14","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.ijcard.2020.05.007","article-title":"Incidence and predictors of atrial fibrillation in a Chinese cohort of Brugada syndrome","volume":"314","author":"Tse","year":"2020","journal-title":"Int J Cardiol"},{"key":"2025081710000801000_8.1.e001505.15","doi-asserted-by":"crossref","first-page":"399","DOI":"10.3389\/fcvm.2020.618254","article-title":"Automated electrocardiogram analysis identifies novel predictors of ventricular arrhythmias in Brugada syndrome","volume":"7","author":"Tse","year":"2021","journal-title":"Front Cardiovasc Med"},{"key":"2025081710000801000_8.1.e001505.16","doi-asserted-by":"publisher","DOI":"10.1093\/europace\/euw235"},{"key":"2025081710000801000_8.1.e001505.17","first-page":"1457","article-title":"Non-Negative matrix factorization with Sparseness constraints","volume":"5","author":"Hoyer","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"2025081710000801000_8.1.e001505.18","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.joa.2013.01.004","article-title":"Epidemiology of Brugada syndrome in Japan and rest of the world","volume":"29","author":"Kamakura","year":"2013","journal-title":"Journal of Arrhythmia"},{"key":"2025081710000801000_8.1.e001505.19","first-page":"1911-1918","article-title":"Clinical characteristics and long-term clinical course of patients with Brugada syndrome without previous cardiac arrest: a multiparametric risk stratification approach","volume":"21","author":"Letsas","year":"2019","journal-title":"Europace"},{"key":"2025081710000801000_8.1.e001505.20","doi-asserted-by":"crossref","first-page":"217","DOI":"10.11622\/smedj.2014055","article-title":"Clinical characteristics and treatment outcomes of patients with Brugada syndrome in northeastern Thailand","volume":"55","author":"Makarawate","year":"2014","journal-title":"Singapore Med J"},{"key":"2025081710000801000_8.1.e001505.21","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1002\/joa3.12118","article-title":"Tpeak-Tend, Tpeak-Tend\/QT ratio and Tpeak-Tend dispersion for risk stratification in Brugada Syndrome: A systematic review and meta-analysis","volume":"34","author":"Tse","year":"2018","journal-title":"J Arrhythm"},{"key":"2025081710000801000_8.1.e001505.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.yjmcc.2010.07.012"},{"key":"2025081710000801000_8.1.e001505.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2013.04.009"},{"key":"2025081710000801000_8.1.e001505.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2014.01.072"},{"key":"2025081710000801000_8.1.e001505.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2016.01.024"},{"key":"2025081710000801000_8.1.e001505.26","first-page":"58","article-title":"High risk electrocardiographic markers in Brugada syndrome","volume":"18","author":"Asvestas","year":"2018","journal-title":"Int J Cardiol Heart Vasc"},{"key":"2025081710000801000_8.1.e001505.27","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.ijcard.2016.03.113","article-title":"Low amplitude ECG and QRS fragmentation in provocable coved-type ST-segment elevation on surface ECG are strong predictors of a continuum between arrhythmogenic cardiomypathy and Brugada syndrome","volume":"214","author":"Peters","year":"2016","journal-title":"Int J Cardiol"},{"key":"2025081710000801000_8.1.e001505.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2012.12.023"},{"key":"2025081710000801000_8.1.e001505.29","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehl205"},{"key":"2025081710000801000_8.1.e001505.30","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2020.00953","article-title":"Temporal variability in electrocardiographic indices in subjects with Brugada patterns","volume":"11","author":"Lee","year":"2020","journal-title":"Front Physiol"},{"key":"2025081710000801000_8.1.e001505.31","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-8167.2008.01282.x"},{"key":"2025081710000801000_8.1.e001505.32","first-page":"1900-1910","article-title":"Non-invasive assessment of the arrhythmogenic substrate in Brugada syndrome using signal-averaged electrocardiogram: clinical implications from a prospective clinical trial","volume":"21","author":"Ciconte","year":"2019","journal-title":"Europace"},{"key":"2025081710000801000_8.1.e001505.33","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1016\/j.hrthm.2017.02.026","article-title":"Twelve-lead ambulatory electrocardiographic monitoring in Brugada syndrome: potential diagnostic and prognostic implications","volume":"14","author":"Gray","year":"2017","journal-title":"Heart Rhythm"},{"key":"2025081710000801000_8.1.e001505.34","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2025081710000801000_8.1.e001505.35","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS169"},{"key":"2025081710000801000_8.1.e001505.36","doi-asserted-by":"crossref","DOI":"10.1186\/s12874-019-0863-0","article-title":"Clinical risk prediction with random forests for survival, longitudinal, and multivariate (RF-SLAM) data analysis","volume":"20","author":"Wongvibulsin","year":"2019","journal-title":"BMC Med Res Methodol"},{"key":"2025081710000801000_8.1.e001505.37","doi-asserted-by":"crossref","unstructured":"Tse G , Lee S , Zhou J . Territory-wide Chinese cohort of congenital long QT syndrome: random survival forest and COX analyses. Front Cardiovasc Med 2021.","DOI":"10.3389\/fcvm.2021.608592"},{"key":"2025081710000801000_8.1.e001505.38","doi-asserted-by":"crossref","DOI":"10.1186\/s12864-019-6293-x","article-title":"Investigating the role of super-enhancer RNAs underlying embryonic stem cell differentiation","volume":"20","author":"Chang","year":"2019","journal-title":"BMC Genomics"},{"key":"2025081710000801000_8.1.e001505.39","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCHEARTFAILURE.118.005765","article-title":"Targeted DNA methylation profiling of human cardiac tissue reveals novel epigenetic traits and gene deregulation across different heart failure patient subtypes","volume":"12","author":"Glezeva","year":"2019","journal-title":"Circ Heart Fail"},{"key":"2025081710000801000_8.1.e001505.40","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-019-14253-4","article-title":"Non-Invasive characterization of human bone marrow stimulation and reconstitution by cell-free messenger RNA sequencing","volume":"11","author":"Ibarra","year":"2020","journal-title":"Nat Commun"},{"key":"2025081710000801000_8.1.e001505.41","article-title":"Identification of important risk factors for all-cause mortality of acquired long QT syndrome patients using random survival forests and non-negative matrix factorization","author":"Chen","year":"2020","journal-title":"Heart Rhythm"},{"key":"2025081710000801000_8.1.e001505.42","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.119.012714","article-title":"Incorporating latent variables using Nonnegative matrix factorization improves risk stratification in Brugada syndrome","volume":"9","author":"Tse","year":"2020","journal-title":"J Am Heart Assoc"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2020-001505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T17:00:21Z","timestamp":1755450021000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2020-001505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,2,5]]},"published-print":{"date-parts":[[2021,2]]}},"alternative-id":["10.1136\/openhrt-2020-001505"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2020-001505","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}