{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T01:45:42Z","timestamp":1789609542035,"version":"build-2803163510"},"reference-count":46,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T00:00:00Z","timestamp":1695254400000},"content-version":"unspecified","delay-in-days":20,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Biofourmis Inc."}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2023,8,3]]},"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Computer-assisted interpretation of single-lead ECG is the preliminary method for clinicians to flag and further evaluate an arrhythmia of clinical importance for acutely ill patients. Critical scrutiny of novel detection algorithms is lacking, particularly in external real-world data sets. This study\u2019s objective was to evaluate a hybrid machine learning model\u2019s ability to classify eight arrhythmias from a single-lead ECG signal from acutely ill patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This cross-sectional external retrospective evaluation of a previously trained hybrid machine learning model against an ECG reading team in the setting of home hospital care (acute care delivered at home substituting for traditional hospital care) draws from patients admitted at two hospitals in Boston, Massachusetts, USA between 12 June 2017 and 23 November 2019. We calculated classifier statistics for each arrhythmia, all arrhythmias and strips where the model identified normal sinus rhythm.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The model analysed 2 680 162\u2009min of single-lead ECG data from 423 patients and identified 691\u2009478 arrhythmias. Patients had a mean age of 70 years (SD, 18), 60% were female and 45% were white. For any arrhythmia, the model had a sensitivity of 98%, a specificity of 100%, an accuracy of 98%, a positive predictive value of 100%, a negative predictive value of 93% and an F\n                      <jats:sub>1<\/jats:sub>\n                      Score of 99%. Performance was best for pause (F\n                      <jats:sub>1<\/jats:sub>\n                      Score, 99%) and worst for paroxysmal supraventricular tachycardia (F\n                      <jats:sub>1<\/jats:sub>\n                      Score, 92%). The model\u2019s false positive rate for any arrhythmia was 0.2%, ranging from 0.4% for pause to 7.2% for paroxysmal supraventricular tachycardia. The false negative rate for any arrhythmia was 1.9%.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>A hybrid machine learning model was effective at classifying common cardiac arrhythmias from a single-lead ECG in real-world data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/openhrt-2022-002228","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T23:15:28Z","timestamp":1695251728000},"page":"e002228","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":9,"title":["Single-lead arrhythmia detection through machine learning: cross-sectional evaluation of a novel algorithm using real-world data"],"prefix":"10.1136","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9941-2133","authenticated-orcid":false,"given":"Henry","family":"Mitchell","sequence":"first","affiliation":[{"name":"Divison of General Internal Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Rosario","sequence":"additional","affiliation":[{"name":"Divison of General Internal Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carme","family":"Hernandez","sequence":"additional","affiliation":[{"name":"Divison of General Internal Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA"},{"name":"University of Barcelona, Barcelona, Catalunya, Spain"},{"name":"Hospital Clinic, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stuart R","family":"Lipsitz","sequence":"additional","affiliation":[{"name":"Divison of General Internal Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA"},{"name":"Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4337-9896","authenticated-orcid":false,"given":"David M","family":"Levine","sequence":"additional","affiliation":[{"name":"Divison of General Internal Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA"},{"name":"Harvard Medical School, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,9,20]]},"reference":[{"key":"2025081710130394000_10.2.e002228.1","first-page":"174","article-title":"Einthoven\u2019s string Galvanometer: the first electrocardiograph","volume":"35","author":"Rivera-Ruiz","year":"2008","journal-title":"Tex Heart Inst J"},{"key":"2025081710130394000_10.2.e002228.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jelectrocard.2007.03.008"},{"key":"2025081710130394000_10.2.e002228.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2005.02.007"},{"key":"2025081710130394000_10.2.e002228.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jelectrocard.2005.01.008"},{"key":"2025081710130394000_10.2.e002228.5","doi-asserted-by":"crossref","first-page":"012001","DOI":"10.1088\/1361-6501\/aaf2b7","article-title":"Critical review of electrocardiography measurement systems and technology","volume":"30","author":"Kalra","year":"2019","journal-title":"Meas Sci Technol"},{"key":"2025081710130394000_10.2.e002228.6","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1016\/j.hlc.2017.10.005","article-title":"The role of Holter monitoring in the diagnosis of early repolarisation pattern","volume":"27","author":"Ji","year":"2018","journal-title":"Heart Lung Circ"},{"key":"2025081710130394000_10.2.e002228.7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2025081710130394000_10.2.e002228.8","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1001\/jamacardio.2021.2746","article-title":"Performance of a convolutional neural network and explainability technique for 12-lead electrocardiogram interpretation","volume":"6","author":"Hughes","year":"2021","journal-title":"JAMA Cardiol"},{"key":"2025081710130394000_10.2.e002228.9","doi-asserted-by":"crossref","first-page":"e348","DOI":"10.1016\/S2589-7500(20)30107-2","article-title":"Automatic multilabel electrocardiogram diagnosis of heart rhythm or conduction abnormalities with deep learning: a cohort study","volume":"2","author":"Zhu","year":"2020","journal-title":"Lancet Digit Health"},{"key":"2025081710130394000_10.2.e002228.10","doi-asserted-by":"crossref","first-page":"2227","DOI":"10.1038\/s41467-020-16172-1","article-title":"Author correction: automatic diagnosis of the 12-lead ECG using a deep neural network","volume":"11","author":"Ribeiro","year":"2020","journal-title":"Nat Commun"},{"key":"2025081710130394000_10.2.e002228.11","doi-asserted-by":"crossref","first-page":"12818","DOI":"10.1038\/s41598-021-92172-5","article-title":"A new deep learning algorithm of 12-lead electrocardiogram for identifying atrial fibrillation during sinus rhythm","volume":"11","author":"Baek","year":"2021","journal-title":"Sci Rep"},{"key":"2025081710130394000_10.2.e002228.12","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2021.102373","article-title":"Interpretable deep learning for automatic diagnosis of 12-lead electrocardiogram","volume":"24","author":"Zhang","year":"2021","journal-title":"iScience"},{"key":"2025081710130394000_10.2.e002228.13","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6579\/aaaa9d","article-title":"A robust deep convolutional neural network for the classification of abnormal cardiac rhythm using single lead electrocardiograms of variable length","volume":"39","author":"Kamaleswaran","year":"2018","journal-title":"Physiol Meas"},{"key":"2025081710130394000_10.2.e002228.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.08.022"},{"key":"2025081710130394000_10.2.e002228.15","doi-asserted-by":"crossref","first-page":"146","DOI":"10.15420\/aer.2020.26","article-title":"Big data and artificial intelligence: opportunities and threats in electrophysiology","volume":"9","author":"van de Leur","year":"2020","journal-title":"Arrhythm Electrophysiol Rev"},{"key":"2025081710130394000_10.2.e002228.16","doi-asserted-by":"crossref","DOI":"10.1038\/s41591-019-0359-9","article-title":"Publisher correction: cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat Med"},{"key":"2025081710130394000_10.2.e002228.17","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1145\/212094.212114","article-title":"Overfitting and undercomputing in machine learning","volume":"27","author":"Dietterich","year":"1995","journal-title":"ACM Comput Surv"},{"key":"2025081710130394000_10.2.e002228.18","doi-asserted-by":"crossref","first-page":"105948","DOI":"10.1016\/j.cmpb.2021.105948","article-title":"Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm","volume":"202","author":"Dias","year":"2021","journal-title":"Comput Methods Programs Biomed"},{"key":"2025081710130394000_10.2.e002228.19","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.ins.2021.06.022","article-title":"Automated arrhythmia detection with homeomorphically irreducible tree technique using more than 10,000 individual subject ECG records","volume":"575","author":"Baygin","year":"2021","journal-title":"Information Sciences"},{"key":"2025081710130394000_10.2.e002228.20","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s13246-020-00965-1","article-title":"Automated detection of arrhythmia from electrocardiogram signal based on new convolutional encoded features with bidirectional long short-term memory network classifier","volume":"44","author":"Pandey","year":"2021","journal-title":"Phys Eng Sci Med"},{"key":"2025081710130394000_10.2.e002228.21","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1007\/s00521-016-2472-8","article-title":"Robust automated cardiac arrhythmia detection in ECG beat signals","volume":"29","author":"de Albuquerque","year":"2018","journal-title":"Neural Comput & Applic"},{"key":"2025081710130394000_10.2.e002228.22","doi-asserted-by":"crossref","DOI":"10.1002\/emp2.12517","article-title":"Home hospital as a disposition for older adults from the emergency department: benefits and opportunities","volume":"2","author":"Ouchi","year":"2021","journal-title":"J Am Coll Emerg Physicians Open"},{"key":"2025081710130394000_10.2.e002228.23","doi-asserted-by":"publisher","DOI":"10.7326\/M19-0600"},{"key":"2025081710130394000_10.2.e002228.24","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-018-4307-z"},{"key":"2025081710130394000_10.2.e002228.25","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-020-06416-7"},{"key":"2025081710130394000_10.2.e002228.26","doi-asserted-by":"publisher","DOI":"10.1136\/bmjinnov-2020-000592"},{"key":"2025081710130394000_10.2.e002228.27","doi-asserted-by":"crossref","first-page":"3644","DOI":"10.1007\/s11606-021-07052-5","article-title":"Acute care at home during the COVID-19 pandemic surge in Boston","volume":"36","author":"Levine","year":"2021","journal-title":"J Gen Intern Med"},{"key":"2025081710130394000_10.2.e002228.28","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-143-11-200512060-00008"},{"key":"2025081710130394000_10.2.e002228.29","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1001\/jamainternmed.2018.2562","article-title":"Association of a bundled hospital-at-home and 30-day postacute transitional care program with clinical outcomes and patient experiences","volume":"178","author":"Federman","year":"2018","journal-title":"JAMA Intern Med"},{"key":"2025081710130394000_10.2.e002228.30","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2021.14920","article-title":"Association of costs and days at home with transfer hospital in home","volume":"4","author":"Cai","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2025081710130394000_10.2.e002228.31","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/j.bbe.2017.06.001","article-title":"Denoising of ECG signal by non-local estimation of approximation coefficients in DWT","volume":"37","author":"Singh","year":"2017","journal-title":"Biocybernetics and Biomedical Engineering"},{"key":"2025081710130394000_10.2.e002228.32","unstructured":"Strasser F , Muma M , Zoubir AM . Motion artifact removal in ECG signals using multi-resolution thresholding. European Signal Processing Conference; 2012:899\u2013903"},{"key":"2025081710130394000_10.2.e002228.33","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.1985.325532"},{"key":"2025081710130394000_10.2.e002228.34","unstructured":"Rajput KS , Wibowo S , Hao C , et al . On arrhythmia detection by deep learning and multidimensional representation; 2019."},{"key":"2025081710130394000_10.2.e002228.35","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2003.821031"},{"key":"2025081710130394000_10.2.e002228.36","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2006.884644"},{"key":"2025081710130394000_10.2.e002228.37","doi-asserted-by":"crossref","first-page":"3130527","DOI":"10.1155\/2019\/3130527","article-title":"An improved sliding window area method for T wave detection","volume":"2019","author":"Shang","year":"2019","journal-title":"Comput Math Methods Med"},{"key":"2025081710130394000_10.2.e002228.38","doi-asserted-by":"crossref","first-page":"5751","DOI":"10.1016\/j.eswa.2010.02.033","article-title":"A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification","volume":"37","author":"Khorrami","year":"2010","journal-title":"Expert Syst Appl"},{"key":"2025081710130394000_10.2.e002228.39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijcsea.2012.2101","article-title":"Classification of ECG arrhythmias using discrete wavelet transform and neural networks","volume":"2","author":"Sarkaleh","year":"2012","journal-title":"IJCSEA"},{"key":"2025081710130394000_10.2.e002228.40","doi-asserted-by":"crossref","unstructured":"Mallat SG . A theory for Multiresolution signal decomposition: the Wavelet representation. In: Heil C , Walnut DF , eds. Fundamental Papers in Wavelet Theory. Princeton University Press, 2006: 494\u2013513. doi:10.1515\/9781400827268","DOI":"10.1515\/9781400827268.494"},{"key":"2025081710130394000_10.2.e002228.41","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00561.2010"},{"key":"2025081710130394000_10.2.e002228.42","doi-asserted-by":"crossref","unstructured":"Noseworthy PA , Attia ZI , Brewer LC , et al . Assessing and mitigating bias in medical artificial intelligence. Circ: Arrhythmia and Electrophysiology 2020;13. doi:10.1161\/CIRCEP.119.007988","DOI":"10.1161\/CIRCEP.119.007988"},{"key":"2025081710130394000_10.2.e002228.43","unstructured":"Sitzman DA , Mikko Kaski M , Ian Rowlandson M , et al . EK-pro: the choice for quality ECG arrhythmia monitoring; 2015."},{"key":"2025081710130394000_10.2.e002228.44","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/s13246-020-00863-6","article-title":"Cloud-based ECG monitoring using event-driven ECG acquisition and machine learning techniques","volume":"43","author":"Mian Qaisar","year":"2020","journal-title":"Phys Eng Sci Med"},{"key":"2025081710130394000_10.2.e002228.45","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0184352","article-title":"The development and validation of an easy to use automatic QT-interval algorithm","volume":"12","author":"Hermans","year":"2017","journal-title":"PLoS ONE"},{"key":"2025081710130394000_10.2.e002228.46","doi-asserted-by":"crossref","first-page":"iii113","DOI":"10.1093\/europace\/euy243","article-title":"Support vector machine-based assessment of the T-wave morphology improves long QT syndrome diagnosis","volume":"20","author":"Hermans","year":"2018","journal-title":"Europace"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2022-002228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T17:13:15Z","timestamp":1755450795000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2022-002228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":46,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,9,20]]},"published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10.1136\/openhrt-2022-002228"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2022-002228","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}