{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T14:17:56Z","timestamp":1791901076095,"version":"4.3.4"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T00:00:00Z","timestamp":1702252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008732","name":"Uehara Memorial Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008732","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>Exercise intolerance is a clinical feature of patients with heart failure (HF). Cardiopulmonary exercise testing (CPET) is the first-line examination for assessing exercise capacity in patients with HF. However, the need for extensive experience in assessing anaerobic threshold (AT) and the potential risk associated with the excessive exercise load when measuring peak oxygen uptake (peak VO2) limit the utility of CPET. This study aimed to use deep-learning approaches to identify AT in real time during testing (defined as real-time AT) and to predict peak VO2 at real-time AT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>This study included the time-series data of CPET recorded at the Department of Cardiovascular Medicine, Kyushu University Hospital. Two deep neural network models were developed to: (i) estimate the AT probability using breath-by-breath data and (ii) predict peak VO2 using the data at the real-time AT. The eligible CPET contained 1472 records of 1053 participants aged 18\u201390 years and 20% were used for model evaluation. The developed model identified real-time AT with 0.82 for correlation coefficient (Corr) and 1.20\u2005mL\/kg\/min for mean absolute error (MAE), and the corresponding AT time with 0.86 for Corr and 0.66\u2005min for MAE. The peak VO2 prediction model achieved 0.87 for Corr and 2.25\u2005mL\/kg\/min for MAE.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Deep-learning models for real-time CPET analysis can accurately identify AT and predict peak VO2. The developed models can be a competent assistant system to assess a patient\u2019s condition in real time, expanding CPET utility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/eurjpc\/zwad375","type":"journal-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T03:38:59Z","timestamp":1702006739000},"page":"448-457","source":"Crossref","is-referenced-by-count":19,"title":["Development of deep-learning models for real-time anaerobic threshold and peak VO2 prediction during cardiopulmonary exercise testing"],"prefix":"10.1093","volume":"31","author":[{"given":"Tatsuya","family":"Watanabe","sequence":"first","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7300-8180","authenticated-orcid":false,"given":"Takeshi","family":"Tohyama","sequence":"additional","affiliation":[{"name":"Centre for Advanced Medical Open Innovation, Kyushu University , 3-1-1 Maidashi, Higashi-ku, Fukuoka-shi , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masataka","family":"Ikeda","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeo","family":"Fujino","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toru","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouji","family":"Matsushima","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junji","family":"Kishimoto","sequence":"additional","affiliation":[{"name":"Centre for Clinical and Translational Research of Kyushu University Hospital , 3-1-1 Maidashi, Higashi-ku, Fukuoka-shi, Fukuoka 812-8582 , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koji","family":"Todaka","sequence":"additional","affiliation":[{"name":"Centre for Advanced Medical Open Innovation, Kyushu University , 3-1-1 Maidashi, Higashi-ku, Fukuoka-shi , Fukuoka 812-8582, Japan"},{"name":"Centre for Clinical and Translational Research of Kyushu University Hospital , 3-1-1 Maidashi, Higashi-ku, Fukuoka-shi, Fukuoka 812-8582 , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shintaro","family":"Kinugawa","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroyuki","family":"Tsutsui","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"School of Medicine and Graduate School, International University of Health and Welfare , 141-11 Sakami, Okawa-shi, Fukuoka 831-0016 , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3387-1550","authenticated-orcid":false,"given":"Tomomi","family":"Ide","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"},{"name":"Division of Cardiovascular Medicine, Research Institute of Angiocardiology, Faculty of Medical Sciences, Kyushu University , 3-1-1 Maidashi, Higashi-ku , Fukuoka 812-8582, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,12,11]]},"reference":[{"key":"2024030501225200900_zwad375-B1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.21037\/amj.2020.03.03","article-title":"Global epidemiology and future trends of heart failure","volume":"5","author":"Lippi","year":"2020","journal-title":"AME Med J"},{"key":"2024030501225200900_zwad375-B2","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.1001\/jamacardio.2019.4187","article-title":"Association between aging of the US population and heart disease mortality from 2011 to 2017","volume":"4","author":"Sidney","year":"2019","journal-title":"JAMA Cardiol"},{"key":"2024030501225200900_zwad375-B3","doi-asserted-by":"crossref","first-page":"S143","DOI":"10.1016\/j.cardfail.2012.08.102","article-title":"Skeletal muscle abnormalities in heart failure","volume":"18","author":"Kinugawa","year":"2012","journal-title":"J Card Fail"},{"key":"2024030501225200900_zwad375-B4","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1016\/j.jacc.2015.11.050","article-title":"Variables measured during cardiopulmonary exercise testing as predictors of mortality in chronic systolic heart failure","volume":"67","author":"Keteyian","year":"2016","journal-title":"J Am Coll Cardiol"},{"key":"2024030501225200900_zwad375-B5","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1253\/circj.72.575","article-title":"Peak VO(2) is more potent than B-type natriuretic peptide as a prognostic parameter in cardiac patients","volume":"72","author":"Kubozono","year":"2008","journal-title":"Circ J"},{"key":"2024030501225200900_zwad375-B6","doi-asserted-by":"crossref","first-page":"4077","DOI":"10.1002\/ehf2.13556","article-title":"Machine learning-based model for predicting 1 year mortality of hospitalized patients with heart failure","volume":"8","author":"Tohyama","year":"2021","journal-title":"ESC Hear Fail"},{"key":"2024030501225200900_zwad375-B7","doi-asserted-by":"crossref","first-page":"e1918962","DOI":"10.1001\/jamanetworkopen.2019.18962","article-title":"Comparison of machine learning methods with traditional models for use of administrative claims with electronic medical records to predict heart failure outcomes","volume":"3","author":"Desai","year":"2020","journal-title":"JAMA Netw Open"},{"key":"2024030501225200900_zwad375-B8","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1016\/j.ahj.2008.07.010","article-title":"A cardiopulmonary exercise testing score for predicting outcomes in patients with heart failure","volume":"156","author":"Myers","year":"2008","journal-title":"Am Heart J"},{"key":"2024030501225200900_zwad375-B9","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1152\/jappl.1973.35.2.236","article-title":"Anaerobic threshold and respiratory gas exchange during exercise","volume":"35","author":"Wasserman","year":"1973","journal-title":"J Appl Physiol"},{"key":"2024030501225200900_zwad375-B10","first-page":"1","article-title":"The anaerobic threshold: definition, physiological significance and identification","volume":"35","author":"Wasserman","year":"1986","journal-title":"Adv Cardiol"},{"key":"2024030501225200900_zwad375-B11","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1016\/j.jacc.2021.01.030","article-title":"Cardiac rehabilitation for patients with heart failure: JACC expert panel","volume":"77","author":"Bozkurt","year":"2021","journal-title":"J Am Coll Cardiol"},{"key":"2024030501225200900_zwad375-B12","first-page":"1","article-title":"Determination of the anaerobic threshold by gas exchange: biochemical considerations, methodology and physiological effects","volume":"83","author":"Wasserman","year":"1994","journal-title":"Z Kardiol"},{"key":"2024030501225200900_zwad375-B13","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s40248-019-0183-6","article-title":"Interobserver variability of ventilatory anaerobic threshold in asymptomatic volunteers","volume":"14","author":"Kaczmarek","year":"2019","journal-title":"Multidiscip Respir Med"},{"key":"2024030501225200900_zwad375-B14","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.cardfail.2009.08.009","article-title":"The ventilatory anaerobic threshold in heart failure: a multicenter evaluation of reliability","volume":"16","author":"Myers","year":"2010","journal-title":"J Card Fail"},{"key":"2024030501225200900_zwad375-B15","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1161\/CIR.0000000000000101","article-title":"Supervision of exercise testing by nonphysicians: a scientific statement from the American Heart Association","volume":"130","author":"Myers","year":"2014","journal-title":"Circulation"},{"key":"2024030501225200900_zwad375-B16","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1177\/00031348221117024","article-title":"Artificial intelligence and machine learning in surgery","volume":"89","author":"Rajesh","year":"2023","journal-title":"Am Surg"},{"key":"2024030501225200900_zwad375-B17","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"2024030501225200900_zwad375-B18","doi-asserted-by":"crossref","first-page":"e235","DOI":"10.1016\/S2589-7500(22)00017-6","article-title":"Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study","volume":"4","author":"Ruamviboonsuk","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2024030501225200900_zwad375-B19","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1152\/japplphysiol.00752.2015","article-title":"A machine-learning approach for computation of fractional flow reserve from coronary computed tomography","volume":"121","author":"Itu","year":"2016","journal-title":"J Appl Physiol (1985)"},{"key":"2024030501225200900_zwad375-B20","doi-asserted-by":"crossref","first-page":"e011579","DOI":"10.1161\/CIRCEP.122.011579","article-title":"Deep learning of ECG for the prediction of postoperative atrial fibrillation","volume":"16","author":"Tohyama","year":"2023","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2024030501225200900_zwad375-B21","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/S0140-6736(19)31721-0","article-title":"An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction","volume":"394","author":"Attia","year":"2019","journal-title":"Lancet"},{"key":"2024030501225200900_zwad375-B22","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1097\/00149831-200308000-00008","article-title":"A critical appraisal of the prognostic value of the VE\/VCO2 slope in chronic heart failure","volume":"10","author":"Tabet","year":"2003","journal-title":"Eur J Cardiovasc Prev Rehabil"},{"key":"2024030501225200900_zwad375-B23","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1161\/CIR.0b013e3181e52e69","article-title":"Clinician\u2019s guide to cardiopulmonary exercise testing in adults: a scientific statement from the American Heart Association","volume":"122","author":"Balady","year":"2010","journal-title":"Circulation"},{"key":"2024030501225200900_zwad375-B24","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1016\/0002-9149(90)91169-7","article-title":"Validation of a computerized technique for detection of the gas exchange anaerobic threshold in cardiac disease","volume":"66","author":"Dickstein","year":"1990","journal-title":"Am J Cardiol"},{"key":"2024030501225200900_zwad375-B25","doi-asserted-by":"crossref","first-page":"e0275091","DOI":"10.1371\/journal.pone.0275091","article-title":"The motivation for physical activity is a predictor of VO2peak and is a useful parameter when determining the need for cardiac rehabilitation in an elderly cardiac population","volume":"17","author":"Mikkelsen","year":"2022","journal-title":"PLoS One"},{"key":"2024030501225200900_zwad375-B26","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1097\/HJR.0b013e3283361dc5","article-title":"Exercise intolerance in chronic heart failure: mechanisms and therapies. Part I","volume":"17","author":"Piepoli","year":"2010","journal-title":"Eur J Cardiovasc Prev Rehabil"},{"key":"2024030501225200900_zwad375-B27","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1002\/clc.23321","article-title":"Heart failure with preserved ejection fraction: new approaches to diagnosis and management","volume":"43","author":"Upadhya","year":"2020","journal-title":"Clin Cardiol"},{"key":"2024030501225200900_zwad375-B28","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s41746-020-00348-6","article-title":"Feasibility of the deep learning method for estimating the ventilatory threshold with electrocardiography data","volume":"3","author":"Miura","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2024030501225200900_zwad375-B29","doi-asserted-by":"crossref","first-page":"e006612","DOI":"10.1161\/JAHA.117.006612","article-title":"Real-time analysis of the heart rate variability during incremental exercise for the detection of the ventilatory threshold","volume":"7","author":"Shiraishi","year":"2018","journal-title":"J Am Heart Assoc"},{"key":"2024030501225200900_zwad375-B30","doi-asserted-by":"crossref","first-page":"e18025","DOI":"10.2196\/18025","article-title":"Barriers to and facilitators of technology in cardiac rehabilitation and self-management: systematic qualitative grounded theory review","volume":"22","author":"Tadas","year":"2020","journal-title":"J Med Internet Res"}],"container-title":["European Journal of Preventive Cardiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/eurjpc\/advance-article-pdf\/doi\/10.1093\/eurjpc\/zwad375\/54726241\/zwad375.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/eurjpc\/article-pdf\/31\/4\/448\/56831770\/zwad375.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/eurjpc\/article-pdf\/31\/4\/448\/56831770\/zwad375.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,4]],"date-time":"2024-03-04T20:23:22Z","timestamp":1709583802000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/eurjpc\/article\/31\/4\/448\/7469081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,11]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,12,11]]},"published-print":{"date-parts":[[2024,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/eurjpc\/zwad375","relation":{},"ISSN":["2047-4873","2047-4881"],"issn-type":[{"value":"2047-4873","type":"print"},{"value":"2047-4881","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,3]]},"published":{"date-parts":[[2023,12,11]]}}}