{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T01:25:22Z","timestamp":1771464322333,"version":"3.50.1"},"reference-count":31,"publisher":"BMJ","issue":"10","license":[{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"unspecified","delay-in-days":3,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Beijing Haidian district health development research and Cultivation Plan","award":["HP2023-03-501001"],"award-info":[{"award-number":["HP2023-03-501001"]}]},{"name":"Peking University Third Hospital Eagle Project","award":["BYSYCY2024062"],"award-info":[{"award-number":["BYSYCY2024062"]}]},{"name":"Youth incubation fund of the Peking University Third Hospital of Peking University","award":["BYSYFY2021013"],"award-info":[{"award-number":["BYSYFY2021013"]}]},{"name":"Clinical key project of the Peking University Third Hospital of Peking University","award":["BYSYZD2021008"],"award-info":[{"award-number":["BYSYZD2021008"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,9,12]]},"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate prediction models for peak oxygen uptake (VO\u2082peak) in patients with coronary heart disease (CHD) using submaximal cardiopulmonary exercise testing (CPET) indicators and deep learning methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Retrospective model development and validation study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Cardiac Rehabilitation Centre, Peking University Third Hospital, China.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>A total of 10\u2009538 patients with CHD who underwent CPET between January 2014 and December 2019.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Clinical data and CPET indicators were collected. Multiple machine learning and deep learning models were developed and compared. Model performance was assessed using R\u00b2, mean absolute error (MAE), bias, Bland\u2013Altman analysis and SHapley Additive exPlanations (SHAP) feature importance ranking.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The neural network model achieved the best performance (R\u00b2 = 0.82, MAE=1.55\u2009mL\/kg\/min, bias=0.08). XGBoost was the best-performing traditional machine learning model (R\u00b2 = 0.74). SHAP analysis identified eight top-ranked features, including VO\u2082@AT, OUES, weight, VE\/VCO\u2082 slope, VE\/VCO\u2082@AT, age, gender and HR@AT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The CPET deep learning model shows potential for predicting VO\u2082peak in CHD patients, but further external validation and prospective studies are required before clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-098878","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T01:40:45Z","timestamp":1759714845000},"page":"e098878","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning prediction of peak oxygen uptake in patients with coronary heart disease: a retrospective study"],"prefix":"10.1136","volume":"15","author":[{"given":"Tao","family":"Shen","sequence":"first","affiliation":[{"name":"Department of Cardiology, Peking University Third Hospital, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guomin","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Peking University Third Hospital, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9300-2512","authenticated-orcid":false,"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Peking University Third Hospital, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuan","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Peking University Third Hospital, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2025,10,5]]},"reference":[{"key":"2025120415053970000_15.10.e098878.1","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000000461"},{"key":"2025120415053970000_15.10.e098878.2","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1055\/a-1198-5573","article-title":"Current Insights into Exercise-based Cardiac Rehabilitation in Patients with Coronary Heart Disease and Chronic Heart Failure","volume":"42","author":"Nichols","year":"2021","journal-title":"Int J Sports Med"},{"key":"2025120415053970000_15.10.e098878.3","article-title":"Exercise-based cardiac rehabilitation for coronary heart disease","volume":"11","author":"Dibben","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"key":"2025120415053970000_15.10.e098878.4","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1177\/2047487319871728","article-title":"Prognostic comparison of the FRIEND and Wasserman\/Hansen peak VO2 equations applied to a submaximal walking test in outpatients with cardiovascular disease","volume":"28","author":"Chiaranda","year":"2021","journal-title":"Eur J Prev Cardiol"},{"key":"2025120415053970000_15.10.e098878.5","unstructured":"Liguori G . ACSM\u2019s guidelines for exercise testing and prescription. Am College Sport Med 2018;147\u201351."},{"key":"2025120415053970000_15.10.e098878.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.12.030"},{"key":"2025120415053970000_15.10.e098878.7","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1093\/eurjpc\/zwad375","article-title":"Development of deep-learning models for real-time anaerobic threshold and peak VO2 prediction during cardiopulmonary exercise testing","volume":"31","author":"Watanabe","year":"2024","journal-title":"Eur J Prev Cardiol"},{"key":"2025120415053970000_15.10.e098878.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2023.10.034"},{"key":"2025120415053970000_15.10.e098878.9","first-page":"1","article-title":"Determination of the anaerobic threshold by gas exchange: biochemical considerations, methodology and physiological effects","volume":"83 Suppl 3","author":"Wasserman","year":"1994","journal-title":"Z Kardiol"},{"key":"2025120415053970000_15.10.e098878.10","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/16.10.906"},{"key":"2025120415053970000_15.10.e098878.11","doi-asserted-by":"crossref","DOI":"10.1021\/acs.jcim.0c00029","article-title":"Correction to Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships","volume":"60","author":"Sheridan","year":"2020","journal-title":"J Chem Inf Model"},{"key":"2025120415053970000_15.10.e098878.12","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-47494-x","article-title":"The effects of CPET-guided cardiac rehabilitation on exercise tolerance in older persons with CHD after PCI","volume":"13","author":"Shen","year":"2023","journal-title":"Sci Rep"},{"key":"2025120415053970000_15.10.e098878.13","doi-asserted-by":"publisher","DOI":"10.1161\/CIR.0000000000000406"},{"key":"2025120415053970000_15.10.e098878.14","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1093\/ehjqcco\/qcab032","article-title":"Peak oxygen consumption achieved at the end of cardiac rehabilitation predicts long-term survival in patients with coronary heart disease","volume":"8","author":"Carbone","year":"2022","journal-title":"Eur Heart J Qual Care Clin Outcomes"},{"key":"2025120415053970000_15.10.e098878.15","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1093\/eurheartj\/ehaa605","article-title":"ESC Guidelines on sports cardiology and exercise in patients with cardiovascular disease","volume":"42","author":"Pelliccia","year":"2020","journal-title":"Eur Heart J"},{"key":"2025120415053970000_15.10.e098878.16","doi-asserted-by":"crossref","DOI":"10.3390\/jcm11206061","article-title":"A Machine Learning Model to Predict Cardiovascular Events during Exercise Evaluation in Patients with Coronary Heart Disease","volume":"11","author":"Shen","year":"2022","journal-title":"J Clin Med"},{"key":"2025120415053970000_15.10.e098878.17","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.pcad.2018.10.003","article-title":"Determining Cardiorespiratory Fitness With Precision: Compendium of Findings From the FRIEND Registry","volume":"62","author":"Kaminsky","year":"2019","journal-title":"Prog Cardiovasc Dis"},{"key":"2025120415053970000_15.10.e098878.18","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.121.022336","article-title":"Reference Standards for Cardiorespiratory Fitness by Cardiovascular Disease Category and Testing Modality: Data From FRIEND","volume":"10","author":"Peterman","year":"2021","journal-title":"J Am Heart Assoc"},{"key":"2025120415053970000_15.10.e098878.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.mayocp.2021.08.020"},{"key":"2025120415053970000_15.10.e098878.20","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1097\/HCR.0000000000000722","article-title":"A Nonexercise Prediction of Peak Oxygen Uptake for Patients With Cardiovascular Disease: DATA FROM THE FITNESS REGISTRY AND THE IMPORTANCE OF EXERCISE INTERNATIONAL DATABASE (FRIEND)","volume":"43","author":"Peterman","year":"2023","journal-title":"J Cardiopulm Rehabil Prev"},{"key":"2025120415053970000_15.10.e098878.21","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1093\/eurjpc\/zwad321","article-title":"Deep learned representations of the resting 12-lead electrocardiogram to predict at peak exercise","volume":"31","author":"Khurshid","year":"2024","journal-title":"Eur J Prev Cardiol"},{"key":"2025120415053970000_15.10.e098878.22","doi-asserted-by":"crossref","DOI":"10.2196\/35796","article-title":"Cardiorespiratory Fitness Estimation Based on Heart Rate and Body Acceleration in Adults With Cardiovascular Risk Factors: Validation Study","volume":"6","author":"Rissanen","year":"2022","journal-title":"JMIR Cardio"},{"key":"2025120415053970000_15.10.e098878.23","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1249\/MSS.0000000000002435","article-title":"Accuracy of Exercise-based Equations for Estimating Cardiorespiratory Fitness","volume":"53","author":"Peterman","year":"2021","journal-title":"Med Sci Sports Exerc"},{"key":"2025120415053970000_15.10.e098878.24","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1177\/2047487319881242","article-title":"Comparison of non-exercise cardiorespiratory fitness prediction equations in apparently healthy adults","volume":"28","author":"Peterman","year":"2021","journal-title":"Eur J Prev Cardiol"},{"key":"2025120415053970000_15.10.e098878.25","doi-asserted-by":"publisher","DOI":"10.1113\/JP280980"},{"key":"2025120415053970000_15.10.e098878.26","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1016\/j.chest.2022.05.039","article-title":"Pick Your Threshold: A Comparison Among Different Methods of Anaerobic Threshold Evaluation in Heart Failure Prognostic Assessment","volume":"162","author":"Salvioni","year":"2022","journal-title":"Chest"},{"key":"2025120415053970000_15.10.e098878.27","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.jjcc.2016.01.002","article-title":"Usefulness of anaerobic threshold to peak oxygen uptake ratio to determine the severity and pathophysiological condition of chronic heart failure","volume":"68","author":"Tomono","year":"2016","journal-title":"J Cardiol"},{"key":"2025120415053970000_15.10.e098878.28","doi-asserted-by":"crossref","first-page":"2582","DOI":"10.1002\/ejhf.3334","article-title":"Prognostic utility of cardiopulmonary exercise testing with simultaneous exercise echocardiography in heart failure with preserved ejection fraction","volume":"26","author":"Naito","year":"2024","journal-title":"Eur J Heart Fail"},{"key":"2025120415053970000_15.10.e098878.29","doi-asserted-by":"publisher","DOI":"10.1177\/2047487316643446"},{"key":"2025120415053970000_15.10.e098878.30","article-title":"Oxygen uptake efficiency slope at anaerobic threshold can predict peak VO2 in adult congenital heart disease","volume":"18","author":"FitzMaurice","year":"2024","journal-title":"Int J Cardiol Congenit Heart Dis"},{"key":"2025120415053970000_15.10.e098878.31","doi-asserted-by":"crossref","first-page":"2055","DOI":"10.1002\/ehf2.14754","article-title":"Usefulness of oxygen uptake efficiency slope in a 6 min walk test in chronic heart failure","volume":"11","author":"Kim","year":"2024","journal-title":"ESC Heart Fail"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-098878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T23:07:03Z","timestamp":1764889623000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-098878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,5]]},"published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1136\/bmjopen-2025-098878"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-098878","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}