{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:18Z","timestamp":1785545058623,"version":"3.56.0"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n \n Low peak oxygen consumption (V\u0307O\n 2<\/jats:sub>\n )\n \n is associated with higher cardiovascular and all-cause mortality, while improvements in peak V\u0307O\n 2<\/jats:sub>\n reduce this risk. Although early detection allows timely intervention, practical screening tools remain lacking. As electrocardiograms (ECGs) reflect both cardiac and age-related changes, they may offer a viable screening approach.\n <\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n \n This study aimed to detect low peak V\u0307O\n 2<\/jats:sub>\n using resting 12-lead ECGs analyzed by a trained neural network.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n The low peak V\u0307O\n 2<\/jats:sub>\n estimation model was developed using data from 965 individuals (n=540, 56% with cardiac or pulmonary disorders) mainly at Chang Gung Memorial Hospital, Linkou, and validated in an independent cohort of 242 individuals (n=194, 80% with cardiac disorders) at the Keelung branch. Resting ECGs were recorded immediately before cardiopulmonary exercise testing. Low peak V\u0307O\n 2<\/jats:sub>\n was defined as a peak V\u0307O\n 2<\/jats:sub>\n of <14 mL\/kg\/min.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The mean peak V\u0307O\n 2<\/jats:sub>\n was 17.5 (SD 6.1) and 15.4 (SD 3.9) mL\/kg\/min in the training and validation datasets, with 27% (261\/965) and 38% (92\/242) classified as low peak V\u0307O\n 2<\/jats:sub>\n , respectively. Wavelet analysis improved model accuracy, underscoring its value for feature extraction. Three input models were compared: (1) individual characteristics (IC; age, sex, BMI, resting heart rate, and heart rate variability), (2) ECG alone, and (3) ECG plus IC. ECG alone outperformed IC, and combining both yielded the highest accuracy. For low peak V\u0307O\n 2<\/jats:sub>\n prediction, ECG plus IC achieved mean area under the curve, precision, and recall values of 0.89, 0.72, and 0.72 in cross-validation, and 0.87, 0.67, and 0.61 in external validation.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n \n An artificial intelligence\u2013driven ECG-based algorithm showed strong potential for screening low peak V\u0307O\n 2<\/jats:sub>\n , enabling early identification of individuals with low peak V\u0307O\n 2<\/jats:sub>\n and facilitating timely clinical intervention.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/81105","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:41:21Z","timestamp":1781199681000},"page":"e81105-e81105","source":"Crossref","is-referenced-by-count":0,"title":["AI-Powered Resting 12-Lead Electrocardiogram Algorithm for Predicting Low Peak Oxygen Consumption: Development and Validation Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6816-8836","authenticated-orcid":false,"given":"Shu-Chun","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8702-0391","authenticated-orcid":false,"given":"Tieh-Cheng","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0590-7977","authenticated-orcid":false,"given":"Michelle","family":"Liou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6286-4494","authenticated-orcid":false,"given":"Yu-Chieh","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3637-201X","authenticated-orcid":false,"given":"Sing-Ya","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3133-127X","authenticated-orcid":false,"given":"Guan-Yi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2532-9043","authenticated-orcid":false,"given":"Hong-Ren","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"issue":"11","key":"R1","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1056\/NEJMoa011858","article-title":"Exercise capacity and mortality among men referred for exercise testing","volume":"346","author":"Myers","journal-title":"N Engl J Med"},{"issue":"16","key":"R2","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1016\/j.ehj.2004.06.013","article-title":"The predictive value of cardiorespiratory fitness for cardiovascular events in men with various risk profiles: a prospective population-based cohort study","volume":"25","author":"Laukkanen","journal-title":"Eur Heart J"},{"issue":"17","key":"R3","doi-asserted-by":"publisher","first-page":"2395","DOI":"10.1001\/jama.262.17.2395","article-title":"Physical fitness and all-cause mortality. A prospective study of healthy men and women","volume":"262","author":"Blair","journal-title":"JAMA"},{"issue":"24","key":"R4","doi-asserted-by":"publisher","first-page":"e653","DOI":"10.1161\/CIR.0000000000000461","article-title":"Importance of assessing cardiorespiratory fitness in clinical practice: a case for fitness as a clinical vital sign: a scientific statement from the American Heart Association","volume":"134","author":"Ross","journal-title":"Circulation"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1093\/eurjcn\/zvad044","article-title":"Trainability for cardiopulmonary fitness is low in patients with peripheral artery disease","volume":"23","author":"Huang","journal-title":"Eur J Cardiovasc Nurs"},{"issue":"3","key":"R6","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.123.031162","article-title":"High-intensity interval training is associated with improved 10-year survival by mediating left ventricular remodeling in patients with heart failure with reduced and mid-range ejection fraction","volume":"13","author":"Hsu","journal-title":"J Am Heart Assoc"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.ijcard.2011.11.086","article-title":"Aerobic interval training improves oxygen uptake efficiency by enhancing cerebral and muscular hemodynamics in patients with heart failure","volume":"167","author":"Fu","journal-title":"Int J Cardiol"},{"issue":"4 Suppl","key":"R8","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1177\/1359786810382057","article-title":"Mortality trends in the general population: the importance of cardiorespiratory fitness","volume":"24","author":"Lee","journal-title":"J Psychopharmacol"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1245\/s10434-025-18499-9","article-title":"Predictive value of preoperative cardiopulmonary exercise testing for complications and mortality after esophagectomy: a meta-analysis","volume":"33","author":"Tseng","journal-title":"Ann Surg Oncol"},{"issue":"Supplement_1","key":"R10","doi-asserted-by":"publisher","first-page":"S74","DOI":"10.1513\/AnnalsATS.201610-780FR","article-title":"Cardiopulmonary exercise testing and surgery","volume":"14","author":"Older","journal-title":"Ann Am Thorac Soc"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0002-9149(81)90081-3","article-title":"Effect of aging on the electrocardiogram","volume":"48","author":"Bachman","journal-title":"Am J Cardiol"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1053\/pcad.2001.24683","article-title":"An evidence-based review of the resting electrocardiogram as a screening technique for heart disease","volume":"44","author":"Ashley","journal-title":"Prog Cardiovasc Dis"},{"issue":"5","key":"R13","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1038\/s41591-021-01335-4","article-title":"Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial","volume":"27","author":"Yao","journal-title":"Nat Med"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41591-018-0240-2","article-title":"Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram","volume":"25","author":"Attia","journal-title":"Nat Med"},{"issue":"3","key":"R15","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12030455","article-title":"Artificial intelligence-enabled electrocardiography predicts left ventricular dysfunction and future cardiovascular outcomes: a retrospective analysis","volume":"12","author":"Chen","journal-title":"J Pers Med"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1378\/chest.125.4.1561","article-title":"The clinical value of the ECG in noncardiac conditions","volume":"125","author":"Van Mieghem","journal-title":"Chest"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","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","journal-title":"Eur J Prev Cardiol"},{"issue":"8","key":"R18","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.jchf.2016.03.022","article-title":"Cardiopulmonary exercise testing in heart failure","volume":"4","author":"Malhotra","journal-title":"JACC Heart Fail"},{"issue":"22","key":"R19","doi-asserted-by":"publisher","first-page":"e77","DOI":"10.1016\/j.jacc.2014.07.944","article-title":"2014 ACC\/AHA guideline on perioperative cardiovascular evaluation and management of patients undergoing noncardiac surgery: a report of the American College of Cardiology\/American Heart Association Task Force on practice guidelines","volume":"64","author":"Fleisher","journal-title":"J Am Coll Cardiol"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1161\/01.cir.83.3.778","article-title":"Value of peak exercise oxygen consumption for optimal timing of cardiac transplantation in ambulatory patients with heart failure","volume":"83","author":"Mancini","journal-title":"Circulation"},{"issue":"5","key":"R21","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1249\/MSS.0000000000002846","article-title":"Stepper-based training improves monocyte-platelet aggregation and thrombin generation in nonambulatory hemiplegic patients","volume":"54","author":"Huang","journal-title":"Med Sci Sports Exerc"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.04.012","article-title":"Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network","volume":"405","author":"Acharya","journal-title":"Inf Sci"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2018.04.005","article-title":"Deep learning for healthcare applications based on physiological signals: a review","volume":"161","author":"Faust","journal-title":"Comput Methods Programs Biomed"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.03.016","article-title":"A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification","volume":"96","author":"Yildirim","journal-title":"Comput Biol Med"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3390\/electronics9010121","article-title":"An automatic diagnosis of arrhythmias using a combination of CNN and LSTM technology","volume":"9","author":"Zheng","journal-title":"Electronics"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1253598","article-title":"Prediction for blood lactate during exercise using an artificial intelligence-enabled electrocardiogram: a feasibility study","volume":"14","author":"Huang","journal-title":"Front Physiol"},{"issue":"5","key":"R27","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1109\/18.57199","article-title":"The wavelet transform, time-frequency localization and signal analysis","volume":"36","author":"Daubechies","journal-title":"IEEE Trans Inform Theory"},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Ledig C Theis L Huszar F et al. Photo-realistic single image super-resolution using a generative adversarial network. Presented at: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Jul 21-26, 2017; Honolulu, HI. [doi: 10.1109\/CVPR.2017.19]","DOI":"10.1109\/CVPR.2017.19"},{"issue":"10","key":"R29","doi-asserted-by":"publisher","first-page":"2464","DOI":"10.1109\/78.157290","article-title":"The discrete wavelet transform: wedding the a trous and Mallat algorithms","volume":"40","author":"Shensa","journal-title":"IEEE Trans Signal Process"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1137\/1031129","article-title":"Continuous and discrete wavelet transforms","volume":"31","author":"Heil","journal-title":"SIAM Rev"},{"issue":"5","key":"R31","doi-asserted-by":"publisher","first-page":"R155","DOI":"10.1088\/0967-3334\/26\/5\/R01","article-title":"Wavelet transforms and the ECG: a review","volume":"26","author":"Addison","journal-title":"Physiol Meas"},{"issue":"2","key":"R32","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1006\/acha.1996.0015","article-title":"The lifting scheme: a custom-design construction of biorthogonal wavelets","volume":"3","author":"Sweldens","journal-title":"Appl Comput Harmon Anal"},{"issue":"2","key":"R33","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/18.119724","article-title":"Fast algorithms for discrete and continuous wavelet transforms","volume":"38","author":"Rioul","journal-title":"IEEE Trans Inform Theory"},{"issue":"5","key":"R34","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","journal-title":"Ann Statist"},{"key":"R35","doi-asserted-by":"crossref","unstructured":"Son J Jung I Park K Han B . Tracking-by-segmentation with online gradient boosting decision tree. In: ICCV \u201915: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). IEEE Computer Society; 2015. [doi: 10.1109\/ICCV.2015.350]","DOI":"10.1109\/ICCV.2015.350"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"Chawla","journal-title":"JAIR"},{"issue":"9","key":"R37","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"Garcia","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"R38","doi-asserted-by":"publisher","DOI":"10.3390\/s21030951","article-title":"A hybrid deep CNN model for abnormal arrhythmia detection based on cardiac ECG signal","volume":"21","author":"Ullah","journal-title":"Sensors (Basel)"},{"key":"R39","unstructured":"Kohavi R . A study of cross-validation and bootstrap for accuracy estimation and model selection. In: IJCAI\u201995: Proceedings of the 14th International Joint Conference on Artificial Intelligence - Volume 2. Morgan Kaufmann Publishers; 1995."},{"issue":"3","key":"R40","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TBME.2015.2468589","article-title":"Real-time patient-specific ECG classification by 1-D convolutional neural networks","volume":"63","author":"Kiranyaz","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"R41","doi-asserted-by":"publisher","first-page":"57","DOI":"10.54254\/2755-2721\/95\/2024BJ0057","article-title":"ECG signal classification based on DWT denoising and XGBoost","volume":"95","author":"Yu","journal-title":"Appl Comput Eng"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00817-1","article-title":"Advanced machine learning techniques for cardiovascular disease early detection and diagnosis","volume":"10","author":"Baghdadi","journal-title":"J Big Data"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e81105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:26:34Z","timestamp":1785536794000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e81105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/81105","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]},"article-number":"v14i11e81105"}}