{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T18:06:30Z","timestamp":1779473190063,"version":"3.53.1"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102008"],"award-info":[{"award-number":["62102008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172018"],"award-info":[{"award-number":["62172018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund","award":["CCF-Tencent RAGR20250108"],"award-info":[{"award-number":["CCF-Tencent RAGR20250108"]}]},{"name":"CCF-Zhipu Large Model Innovation Fund","award":["CCF-Zhipu202414"],"award-info":[{"award-number":["CCF-Zhipu202414"]}]},{"name":"PKU-OPPO Fund","award":["BO202301"],"award-info":[{"award-number":["BO202301"]}]},{"name":"PKU-OPPO Fund","award":["BO202303"],"award-info":[{"award-number":["BO202303"]}]},{"name":"Research Project of Peking University in the State Key Laboratory of Vascular Homeostasis and Remodeling","award":["2025-SKLVHR-YCTS-02"],"award-info":[{"award-number":["2025-SKLVHR-YCTS-02"]}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Twelve-lead electrocardiograms (ECGs) are the clinical gold standard for cardiac diagnosis, offering comprehensive spatial coverage of the heart necessary for detecting conditions such as myocardial infarction (MI). However, their lack of portability limits continuous and large-scale deployment. In contrast, three-lead ECG systems are widely used in wearable devices due to their simplicity and mobility, but they often fail to capture pathologies localized in unmeasured regions. To bridge this gap, we propose WearECG, a Variational Autoencoder (VAE) method that reconstructs 12-lead ECGs from three leads (II, V1, V5). Our model includes architectural improvements to better capture temporal and spatial dependencies in ECG signals. We evaluate generation quality using MSE, MAE, and Fr\u00e9chet Inception Distance (FID), and assess clinical validity via a Turing test with expert cardiologists. To further validate the diagnostic utility, we fine-tune ECGFounder\u2014a large-scale pretrained ECG model\u2014on a multi-label classification task involving over 40 cardiac conditions, including 6 different myocardial infarction locations using both real and generated signals. Experiments on the MIMIC and PTB-XL datasets show that our method produces physiologically realistic and diagnostically informative signals, with robust performance in downstream tasks. This work demonstrates the potential of generative modeling for ECG reconstruction and its implications for scalable, low-cost cardiac screening.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001335","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:37:13Z","timestamp":1779471433000},"page":"e0001335","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reconstructing 12-lead ECG from 3-lead ECG using variational autoencoder to improve cardiac disease detection of wearable ECG devices"],"prefix":"10.1371","volume":"5","author":[{"given":"Xinyan","family":"Guan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongfan","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiarui","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4041-3083","authenticated-orcid":true,"given":"Deyun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shijia","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanyu","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7521-5127","authenticated-orcid":true,"given":"Shenda","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"issue":"1","key":"pdig.0001335.ref001","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1056\/NEJMra035098","article-title":"Cardiovascular disease","volume":"349","author":"EG Nabel","year":"2003","journal-title":"N Engl J Med"},{"key":"pdig.0001335.ref002","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1016\/S0140-6736(18)32203-7","article-title":"Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980\u20132017: a systematic analysis for the global burden of disease study 2017","volume":"392","author":"GA Roth","year":"2018","journal-title":"Lancet"},{"issue":"4","key":"pdig.0001335.ref003","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1016\/j.amjcard.2013.04.017","article-title":"Diagnostic utility of a novel leadless arrhythmia monitoring device","volume":"112","author":"MP Turakhia","year":"2013","journal-title":"Am J Cardiol"},{"issue":"6","key":"pdig.0001335.ref004","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1109\/JBHI.2020.2980454","article-title":"Non-standardized patch-based ECG lead together with deep learning based algorithm for automatic screening of atrial fibrillation","volume":"24","author":"D Lai","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"pdig.0001335.ref005","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.ijcard.2021.03.015","article-title":"Enhanced detection of cardiac arrhythmias utilizing 14-day continuous ECG patch monitoring","volume":"332","author":"C-M Liu","year":"2021","journal-title":"Int J Cardiol"},{"issue":"5","key":"pdig.0001335.ref006","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1001\/jamacardio.2018.0136","article-title":"Passive detection of atrial fibrillation using a commercially available smartwatch","volume":"3","author":"GH Tison","year":"2018","journal-title":"JAMA Cardiol"},{"key":"pdig.0001335.ref007","doi-asserted-by":"crossref","first-page":"2381","DOI":"10.1016\/j.jacc.2018.03.003","article-title":"Smartwatch algorithm for automated detection of atrial fibrillation","volume":"71","author":"JM Bumgarner","year":"2018","journal-title":"J Am Coll Cardiol"},{"issue":"20","key":"pdig.0001335.ref008","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":"MV Perez","year":"2019","journal-title":"N Engl J Med"},{"issue":"6","key":"pdig.0001335.ref009","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1109\/TBCAS.2016.2519523","article-title":"Wearable noncontact armband for mobile ECG monitoring system","volume":"10","author":"VP Rachim","year":"2016","journal-title":"IEEE Trans Biomed Circuits Syst"},{"issue":"9","key":"pdig.0001335.ref010","doi-asserted-by":"crossref","first-page":"11046","DOI":"10.1109\/JSEN.2021.3059997","article-title":"Influence of armband form factors on wearable ECG monitoring performance","volume":"21","author":"BM Li","year":"2021","journal-title":"IEEE Sensors J"},{"issue":"12","key":"pdig.0001335.ref011","doi-asserted-by":"crossref","first-page":"3464","DOI":"10.1109\/TBME.2020.2987759","article-title":"Wearable armband device for daily life electrocardiogram monitoring","volume":"67","author":"J Lazaro","year":"2020","journal-title":"IEEE Trans Biomed Eng"},{"key":"pdig.0001335.ref012","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1054\/jelc.2000.20296","article-title":"Minimal lead sets for reconstruction of 12-lead electrocardiograms","author":"SP Nelwan","year":"2000","journal-title":"J Electrocardiol"},{"issue":"2","key":"pdig.0001335.ref013","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.jelectrocard.2015.12.008","article-title":"Frank vectorcardiographic system from standard 12 lead ECG: an effort to enhance cardiovascular diagnosis","volume":"49","author":"S Maheshwari","year":"2016","journal-title":"J Electrocardiol"},{"issue":"3","key":"pdig.0001335.ref014","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1109\/JBHI.2015.2415519","article-title":"Reconstruction of precordial lead electrocardiogram from limb leads using the state-space model","volume":"20","author":"J Lee","year":"2016","journal-title":"IEEE J Biomed Health Inform"},{"issue":"10","key":"pdig.0001335.ref015","article-title":"A lightweight piecewise linear synthesis method for standard 12-lead ECG signals based on adaptive region segmentation","volume":"13","author":"H Zhu","year":"2018","journal-title":"PLoS One"},{"issue":"2","key":"pdig.0001335.ref016","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1109\/JBHI.2013.2294561","article-title":"Patient-specific 12-lead ECG reconstruction from sparse electrodes using independent component analysis","volume":"18","author":"GR Tsouri","year":"2014","journal-title":"IEEE J Biomed Health Inform"},{"key":"pdig.0001335.ref017","first-page":"1","article-title":"Classification of ECG Using Ensemble of Residual CNNs with Attention Mechanism.","author":"P Nejedly","year":"2021","journal-title":"2021 Computing in Cardiology (CinC)"},{"key":"pdig.0001335.ref018","first-page":"1","article-title":"A Novel Single Lead to 12-Lead ECG Reconstruction Methodology Using Convolutional Neural Networks and LSTM.","author":"V Gundlapalle","year":"2022","journal-title":"2022 IEEE 13th Latin America Symposium on Circuits and System (LASCAS)"},{"key":"pdig.0001335.ref019","first-page":"1","article-title":"Single-Lead to Multi-Lead Electrocardiogram Reconstruction Using a Modified Attention U-Net Framework.","author":"A Garg","year":"2023","journal-title":"2023 International Joint Conference on Neural Networks (IJCNN)"},{"key":"pdig.0001335.ref020","doi-asserted-by":"crossref","DOI":"10.1038\/s44325-024-00036-4","volume-title":"Multi-channel masked autoencoder and comprehensive evaluations for reconstructing 12-lead ECG from arbitrary single-lead ECG","author":"J Chen","year":"2024"},{"issue":"5","key":"pdig.0001335.ref021","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1109\/JBHI.2019.2936583","article-title":"Synthesis of electrocardiogram V-lead signals from limb-lead measurement using R-peak aligned generative adversarial network","volume":"24","author":"J Lee","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"pdig.0001335.ref022","doi-asserted-by":"crossref","first-page":"106858","DOI":"10.1016\/j.cmpb.2022.106858","article-title":"Multiple electrocardiogram generator with single-lead electrocardiogram","volume":"221","author":"H-C Seo","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"pdig.0001335.ref023","first-page":"184","article-title":"Twelve-lead ecg reconstruction from single-lead signals using generative adversarial networks.","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"MY Joo","year":"2023"},{"issue":"1","key":"pdig.0001335.ref024","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1038\/s41746-024-01193-7","article-title":"AI-enhanced reconstruction of the 12-lead electrocardiogram via 3-leads with accurate clinical assessment","volume":"7","author":"F Mason","year":"2024","journal-title":"NPJ Digit Med"},{"key":"pdig.0001335.ref025","article-title":"An electrocardiogram foundation model built on over 10 million recordings with external evaluation across multiple domains","volume":"2","author":"J Li","year":"2025","journal-title":"NEJM AI"},{"key":"pdig.0001335.ref026","unstructured":"Gow B, Pollard T, Nathanson LA, Johnson A, Moody B, Fernandes C, et al. Mimic-iv-ecg: Diagnostic electrocardiogram matched subset (version 1.0). 2023. https:\/\/physionet.org\/content\/mimic-iv-ecg\/1.0\/"},{"issue":"5","key":"pdig.0001335.ref027","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1161\/01.CIR.13.5.737","article-title":"An accurate, clinically practical system for spatial vectorcardiography","volume":"13","author":"E Frank","year":"1956","journal-title":"Circulation"},{"key":"pdig.0001335.ref028","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1136\/hrt.8.3.157","article-title":"Heart-vector and leads","volume":"8","author":"HC Burger","year":"1946","journal-title":"Br Heart J"},{"key":"pdig.0001335.ref029","author":"DP Kingma","year":"2022"},{"key":"pdig.0001335.ref030","first-page":"1","article-title":"Classification of myocardial infarction with multi-lead ecg signals using deep learning","volume":"59","author":"Y Liu","year":"2020","journal-title":"J Electrocardiol"},{"key":"pdig.0001335.ref031","first-page":"1","article-title":"Classification of conduction blocks using deep learning on multi-lead ecg signals","volume":"60","author":"X Li","year":"2021","journal-title":"J Electrocardiol"},{"key":"pdig.0001335.ref032","first-page":"1","article-title":"Detection of arrhythmia heartbeats from ecg signal using wavelet transform-based cnn model","volume":"2023","author":"A Shukla","year":"2023","journal-title":"Springer Proc Complexity"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:37:20Z","timestamp":1779471440000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001335"}},"subtitle":[],"editor":[{"given":"Chenxi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":32,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001335","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}