{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:02:14Z","timestamp":1773154934395,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T00:00:00Z","timestamp":1681344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM139967"],"award-info":[{"award-number":["R01GM139967"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-21-1-2036"],"award-info":[{"award-number":["N00014-21-1-2036"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-22-1-2325"],"award-info":[{"award-number":["N00014-22-1-2325"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation Graduate Research Fellowship","award":["DGE-2039655"],"award-info":[{"award-number":["DGE-2039655"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To design and validate a novel deep generative model for seismocardiogram (SCG) dataset augmentation. SCG is a noninvasively acquired cardiomechanical signal used in a wide range of cardivascular monitoring tasks; however, these approaches are limited due to the scarcity of SCG data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>A deep generative model based on transformer neural networks is proposed to enable SCG dataset augmentation with control over features such as aortic opening (AO), aortic closing (AC), and participant-specific morphology. We compared the generated SCG beats to real human beats using various distribution distance metrics, notably Sliced-Wasserstein Distance (SWD). The benefits of dataset augmentation using the proposed model for other machine learning tasks were also explored.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Experimental results showed smaller distribution distances for all metrics between the synthetically generated set of SCG and a test set of human SCG, compared to distances from an animal dataset (1.14\u00d7 SWD), Gaussian noise (2.5\u00d7 SWD), or other comparison sets of data. The input and output features also showed minimal error (95% limits of agreement for pre-ejection period [PEP] and left ventricular ejection time [LVET] timings are 0.03\u2009\u00b1\u20093.81\u00a0ms and \u22120.28\u2009\u00b1\u20096.08\u00a0ms, respectively). Experimental results for data augmentation for a PEP estimation task showed 3.3% accuracy improvement on an average for every 10% augmentation (ratio of synthetic data to real data).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The model is thus able to generate physiologically diverse, realistic SCG signals with precise control over AO and AC features. This will uniquely enable dataset augmentation for SCG processing and machine learning to overcome data scarcity.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocad067","type":"journal-article","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T18:37:52Z","timestamp":1681411072000},"page":"1266-1273","source":"Crossref","is-referenced-by-count":7,"title":["Synthetic seismocardiogram generation using a transformer-based neural network"],"prefix":"10.1093","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5124-684X","authenticated-orcid":false,"given":"Mohammad","family":"Nikbakht","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, Georgia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4698-2823","authenticated-orcid":false,"given":"Asim H","family":"Gazi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, Georgia, USA"}]},{"given":"Jonathan","family":"Zia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, Georgia, USA"}]},{"given":"Sungtae","family":"An","sequence":"additional","affiliation":[{"name":"Department of Interactive Computing, Georgia Institute of Technology , Atlanta, Georgia, USA"}]},{"given":"David J","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, Georgia, USA"}]},{"given":"Omer T","family":"Inan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Georgia Institute of Technology , Atlanta, Georgia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8366-4811","authenticated-orcid":false,"given":"Rishikesan","family":"Kamaleswaran","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Emory University School of Medicine , Atlanta, Georgia, USA"}]}],"member":"286","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"issue":"4","key":"2024041301133631300_ocad067-B1","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1109\/JBHI.2014.2361732","article-title":"Ballistocardiography and seismocardiography: a review of recent advances","volume":"19","author":"Inan","year":"2015","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"2024041301133631300_ocad067-B2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-33675-6","article-title":"Definition of fiducial points in the normal seismocardiogram","volume":"8","author":"S\u00f8rensen","year":"2018","journal-title":"Sci Rep"},{"issue":"1","key":"2024041301133631300_ocad067-B3","doi-asserted-by":"crossref","first-page":"e004313","DOI":"10.1161\/CIRCHEARTFAILURE.117.004313","article-title":"Novel wearable seismocardiography and machine learning algorithms can assess clinical status of heart failure patients","volume":"11","author":"Inan","year":"2018","journal-title":"Circ Heart Fail"},{"issue":"19","key":"2024041301133631300_ocad067-B4","doi-asserted-by":"crossref","first-page":"8522","DOI":"10.1109\/JSEN.2018.2872651","article-title":"Fusing near-infrared spectroscopy with wearable hemodynamic measurements improves classification of mental stress","volume":"19","author":"Gurel","year":"2019","journal-title":"IEEE Sens J"},{"key":"2024041301133631300_ocad067-B5","first-page":"1061","author":"Gurel"},{"key":"2024041301133631300_ocad067-B6","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1109\/EMBC46164.2021.9630415","author":"Gazi","year":"2021"},{"key":"2024041301133631300_ocad067-B7","author":"Ganti"},{"issue":"8","key":"2024041301133631300_ocad067-B8","doi-asserted-by":"crossref","first-page":"e27466","DOI":"10.2196\/27466","article-title":"Enabling wearable pulse transit time-based blood pressure estimation for medically underserved areas and health equity: comprehensive evaluation study","volume":"9","author":"Ganti","year":"2021","journal-title":"JMIR Mhealth Uhealth"},{"key":"2024041301133631300_ocad067-B9","doi-asserted-by":"publisher","first-page":"3344","DOI":"10.1109\/CVPRW50498.2020.00394","author":"Jaipuria","year":"2020"},{"issue":"18","key":"2024041301133631300_ocad067-B10","doi-asserted-by":"crossref","first-page":"20398","DOI":"10.1109\/JSEN.2021.3095176","article-title":"AdaptNet: human activity recognition via bilateral domain adaptation using semi-supervised deep translation networks","volume":"21","author":"An","year":"2021","journal-title":"IEEE Sensors J"},{"key":"2024041301133631300_ocad067-B11","doi-asserted-by":"publisher","first-page":"3774","DOI":"10.1109\/ICCV.2017.405","author":"Zheng","year":"2017"},{"issue":"5","key":"2024041301133631300_ocad067-B12","doi-asserted-by":"crossref","first-page":"056021","DOI":"10.1088\/1741-2552\/abb580","article-title":"Data augmentation for enhancing EEG-based emotion recognition with deep generative models","volume":"17","author":"Luo","year":"2020","journal-title":"J Neural Eng"},{"issue":"1","key":"2024041301133631300_ocad067-B13","first-page":"1","article-title":"Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network","volume":"9","author":"Zhu","year":"2019","journal-title":"Sci Rep"},{"key":"2024041301133631300_ocad067-B14","author":"Delaney","year":"2019"},{"issue":"12","key":"2024041301133631300_ocad067-B15","doi-asserted-by":"crossref","first-page":"441","DOI":"10.3390\/biology9120441","article-title":"Synsiggan: generative adversarial networks for synthetic biomedical signal generation","volume":"9","author":"Hazra","year":"2020","journal-title":"Biology"},{"issue":"11","key":"2024041301133631300_ocad067-B16","doi-asserted-by":"crossref","first-page":"3226","DOI":"10.1109\/JBHI.2020.2979608","article-title":"Plethaugment: GAN-based PPG augmentation for medical diagnosis in low-resource settings","volume":"24","author":"Kiyasseh","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"issue":"7","key":"2024041301133631300_ocad067-B17","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1109\/JBHI.2020.2980979","article-title":"Modeling consistent dynamics of cardiogenic vibrations in low-dimensional subspace","volume":"24","author":"Zia","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"2024041301133631300_ocad067-B18","doi-asserted-by":"crossref","first-page":"1296","DOI":"10.1109\/JBHI.2019.2931872","article-title":"A globalized model for mapping wearable seismocardiogram signals to whole-body ballistocardiogram signals based on deep learning","volume":"24","author":"Hersek","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"2024041301133631300_ocad067-B19","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"issue":"10","key":"2024041301133631300_ocad067-B20","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1056\/NEJMra022700","article-title":"Use of the electrocardiogram in acute myocardial infarction","volume":"348","author":"Zimetbaum","year":"2003","journal-title":"N Engl J Med"},{"issue":"3","key":"2024041301133631300_ocad067-B21","doi-asserted-by":"crossref","first-page":"R1","DOI":"10.1088\/0967-3334\/28\/3\/R01","article-title":"Photoplethysmography and its application in clinical physiological measurement","volume":"28","author":"Allen","year":"2007","journal-title":"Physiol Meas"},{"issue":"6","key":"2024041301133631300_ocad067-B22","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1109\/JBHI.2019.2895775","article-title":"Performance analysis of gyroscope and accelerometer sensors for seismocardiography-based wearable pre-ejection period estimation","volume":"23","author":"Shandhi","year":"2019","journal-title":"IEEE J Biomed Health Inform"},{"issue":"12","key":"2024041301133631300_ocad067-B23","doi-asserted-by":"crossref","first-page":"3805","DOI":"10.1109\/JSEN.2017.2701349","article-title":"Automatic detection of seismocardiogram sensor misplacement for robust pre-ejection period estimation in unsupervised settings","volume":"17","author":"Ashouri","year":"2017","journal-title":"IEEE Sensors J"},{"issue":"12","key":"2024041301133631300_ocad067-B24","doi-asserted-by":"crossref","first-page":"521","DOI":"10.3390\/bios11120521","article-title":"Enabling continuous wearable reflectance pulse oximetry at the sternum","volume":"11","author":"Chan","year":"2021","journal-title":"Biosensors"},{"issue":"30","key":"2024041301133631300_ocad067-B25","doi-asserted-by":"crossref","first-page":"eabb1708","DOI":"10.1126\/sciadv.abb1708","article-title":"Enabling the assessment of trauma-induced hemorrhage via smart wearable systems","volume":"6","author":"Zia","year":"2020","journal-title":"Sci Adv"},{"issue":"4","key":"2024041301133631300_ocad067-B26","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1109\/JBHI.2019.2931348","article-title":"A unified framework for quality indexing and classification of seismocardiogram signals","volume":"24","author":"Zia","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"2024041301133631300_ocad067-B27","doi-asserted-by":"publisher","author":"Karita","DOI":"10.1109\/ASRU46091.2019.9003750"},{"issue":"1","key":"2024041301133631300_ocad067-B28","doi-asserted-by":"crossref","first-page":"6706","DOI":"10.1609\/aaai.v33i01.33016706","article-title":"Neural speech synthesis with transformer network","volume":"33","author":"Li","year":"2019","journal-title":"AAAI"},{"issue":"1","key":"2024041301133631300_ocad067-B29","doi-asserted-by":"crossref","first-page":"64","DOI":"10.3390\/vibration2010005","article-title":"Recent advances in seismocardiography","volume":"2","author":"Taebi","year":"2019","journal-title":"Vibration"},{"key":"2024041301133631300_ocad067-B30","author":"Liang","year":"2022"},{"key":"2024041301133631300_ocad067-B31","author":"Hartmann","year":"2018"},{"key":"2024041301133631300_ocad067-B32","author":"Weng","year":"2019"},{"issue":"4","key":"2024041301133631300_ocad067-B33","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.1109\/JSEN.2017.2787628","article-title":"Universal pre-ejection period estimation using seismocardiography: quantifying the effects of sensor placement and regression algorithms","volume":"18","author":"Ashouri","year":"2018","journal-title":"IEEE Sens J"},{"key":"2024041301133631300_ocad067-B34","doi-asserted-by":"publisher","author":"Nikbakht","DOI":"10.1109\/SENSORS52175.2022.9967101"},{"key":"2024041301133631300_ocad067-B35","author":"Liu","year":"2014"},{"key":"2024041301133631300_ocad067-B36","doi-asserted-by":"publisher","author":"Rethage","DOI":"10.1109\/ICASSP.2018.8462417"},{"issue":"44","key":"2024041301133631300_ocad067-B37","doi-asserted-by":"crossref","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proc Natl Acad Sci USA"},{"issue":"1","key":"2024041301133631300_ocad067-B38","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/TBME.2021.3090376","article-title":"Reducing the impact of external vibrations on fiducial point detection in seismocardiogram signals","volume":"69","author":"Lin","year":"2022","journal-title":"IEEE Trans Biomed Eng"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/7\/1266\/50634375\/ocad067.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/7\/1266\/50634375\/ocad067.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T01:14:05Z","timestamp":1712970845000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/30\/7\/1266\/7117772"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,13]]},"references-count":38,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,4,13]]},"published-print":{"date-parts":[[2023,6,20]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocad067","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,7,1]]},"published":{"date-parts":[[2023,4,13]]}}}