{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:52:30Z","timestamp":1792788750338,"version":"4.5.0"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T00:00:00Z","timestamp":1745193600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100021525","name":"Insight SFI Research Centre for Data Analytics","doi-asserted-by":"publisher","award":["SFI\/12\/RC\/2289_P2"],"award-info":[{"award-number":["SFI\/12\/RC\/2289_P2"]}],"id":[{"id":"10.13039\/501100021525","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SFI Centre for Research Training in Artificial Intelligence","award":["SFI\/18\/CRT\/6223"],"award-info":[{"award-number":["SFI\/18\/CRT\/6223"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"\n Accurate assessment of training status in team sports is crucial for optimising performance and reducing injury risk. This pilot study investigates the feasibility of using machine learning (ML) models to estimate oxygen uptake (VO\n 2<\/jats:sub>\n ) with wearable sensors during team sports activities. Six healthy male team sports athletes participated in the study. Data were collected using inertial measurement units (IMU), heart rate monitors, and breathing rate sensors during incremental fitness tests. The performance of different ML models, including multiple linear regression (MLR), XGBoost, and deep learning models (LSTM, CNN, MLP), was compared using raw and engineered features from IMU data. Results indicate that while LSTM models with raw IMU data provided the most accurate predictions (RMSE: 4.976, MAE: 3.698\n \n \n \n \n \n mL<\/mml:mtext>\n <\/mml:mstyle>\n \n \u22c5<\/mml:mo>\n \n \n \n \n kg<\/mml:mtext>\n <\/mml:mstyle>\n <\/mml:mrow>\n \n \u2212<\/mml:mo>\n 1<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n \n \u22c5<\/mml:mo>\n \n \n \n \n min<\/mml:mtext>\n <\/mml:mstyle>\n <\/mml:mrow>\n \n \u2212<\/mml:mo>\n 1<\/mml:mn>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n ), MLR models remained competitive, especially with engineered features. Multi-sensor configurations, particularly those including sensors on the torso and limbs, enhanced prediction accuracy. The findings demonstrate the potential of ML models to monitor VO\n 2<\/jats:sub>\n noninvasively in real-time, offering valuable insights into the internal physiological demand during team sports activities.\n <\/jats:p>","DOI":"10.1371\/journal.pone.0319760","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T13:51:29Z","timestamp":1745243489000},"page":"e0319760","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["Estimating oxygen uptake in simulated team sports using machine learning models and wearable sensor data: A pilot study"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3687-1943","authenticated-orcid":true,"given":"Dermot","family":"Sheridan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arne","family":"Jaspers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinh","family":"Viet Cuong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Op De Be\u00e9ck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niall M.","family":"Moyna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6933-4960","authenticated-orcid":true,"given":"Toon T.","family":"de Beukelaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1329-2570","authenticated-orcid":true,"given":"Mark","family":"Roantree","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,21]]},"reference":[{"issue":"9","key":"pone.0319760.ref001","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1007\/s40279-023-01833-0","article-title":"understanding training load as exposure and dose","volume":"53","author":"FM Impellizzeri","year":"2023","journal-title":"Sports Med"},{"issue":"2","key":"pone.0319760.ref002","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1123\/ijspp.2018-0935","article-title":"Internal and external training load: 15 years on","volume":"14","author":"FM Impellizzeri","year":"2019","journal-title":"Int J Sports Physiol Perform"},{"issue":"1","key":"pone.0319760.ref003","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/MPUL.2016.2627240","article-title":"Wearable devices for sports: new integrated technologies allow coaches, physicians, and trainers to better understand the physical demands of athletes in real time","volume":"8","author":"DR Seshadri","year":"2017","journal-title":"IEEE Pulse"},{"key":"pone.0319760.ref004","doi-asserted-by":"crossref","DOI":"10.3389\/fphys.2018.00639","article-title":"Heart rate monitoring in team sports: A conceptual framework for contextualizing heart rate measures for training and recovery prescription","volume":"9","author":"C Schneider","year":"2018","journal-title":"Front Physiol."},{"key":"pone.0319760.ref005","doi-asserted-by":"crossref","first-page":"612","DOI":"10.3389\/fnins.2017.00612","article-title":"Session-RPE method for training load monitoring: validity, ecological usefulness, and influencing factors","volume":"11","author":"M Haddad","year":"2017","journal-title":"Front Neurosci"},{"key":"pone.0319760.ref006"},{"issue":"8","key":"pone.0319760.ref007","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1055\/a-0592-7219","article-title":"Metabolic power in team sports - part 2: aerobic and anaerobic energy yields","volume":"39","author":"C Osgnach","year":"2018","journal-title":"Int J Sports Med"},{"issue":"1","key":"pone.0319760.ref008","doi-asserted-by":"crossref","first-page":"163","DOI":"10.5114\/biolsport.2024.129479","article-title":"Do players with superior physiological attributes outwork their less-conditioned counterparts? A study in Gaelic football","volume":"41","author":"LS Daly","year":"2024","journal-title":"Biol Sport"},{"issue":"2","key":"pone.0319760.ref009","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1007\/s11332-016-0278-9","article-title":"VO2Max and VO2AT: athletic performance and field role of elite soccer players","volume":"12","author":"D Manari","year":"2016","journal-title":"Sport Sci Health"},{"issue":"9","key":"pone.0319760.ref010","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1123\/ijspp.2016-0363","article-title":"Impaired player-coach perceptions of exertion and recovery during match congestion","volume":"12","author":"SH Doeven","year":"2017","journal-title":"Int J Sports Physiol Perform"},{"issue":"10","key":"pone.0319760.ref011","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1123\/ijspp.2018-0026","article-title":"Monitoring players\u2019 readiness using predicted heart-rate responses to soccer drills","volume":"13","author":"M Lacome","year":"2018","journal-title":"Int J Sports Physiol Perform"},{"issue":"2","key":"pone.0319760.ref012","doi-asserted-by":"crossref","first-page":"827","DOI":"10.3390\/s23020827","article-title":"Relationships between external, wearable sensor-based, and internal parameters: a systematic review","volume":"23","author":"J Helwig","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"12","key":"pone.0319760.ref013","doi-asserted-by":"crossref","first-page":"2533","DOI":"10.1007\/s40279-017-0772-5","article-title":"Activity demands during multi-directional team sports: a systematic review","volume":"47","author":"JB Taylor","year":"2017","journal-title":"Sports Med"},{"issue":"20","key":"pone.0319760.ref014","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1080\/02640414.2014.965190","article-title":"Using accelerometry to quantify deceleration during a high-intensity soccer turning manoeuvre","volume":"32","author":"NJ Nedergaard","year":"2014","journal-title":"J Sports Sci"},{"issue":"11","key":"pone.0319760.ref015","doi-asserted-by":"crossref","first-page":"5073","DOI":"10.3390\/s23115073","article-title":"Performance of different accelerometry-based metrics to estimate oxygen consumption during track and treadmill locomotion over a wide intensity range","volume":"23","author":"H V\u00e4h\u00e4-Ypy\u00e4","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"24","key":"pone.0319760.ref016","doi-asserted-by":"crossref","first-page":"5101","DOI":"10.3390\/ijerph16245101","article-title":"Accelerometry-based external load indicators in sport: too many options, same practical outcome?","volume":"16","author":"CD G\u00f3mez-Carmona","year":"2019","journal-title":"Int J Environ Res Public Health"},{"key":"pone.0319760.ref017","doi-asserted-by":"crossref","first-page":"1302911","DOI":"10.3389\/fbioe.2023.1302911","article-title":"Identification of runner fatigue stages based on inertial sensors and deep learning","volume":"11","author":"P Chang","year":"2023","journal-title":"Front Bioeng Biotechnol"},{"issue":"2","key":"pone.0319760.ref018","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/s11332-019-00557-x","article-title":"State-of-the art concepts and future directions in modelling oxygen consumption and lactate concentration in cycling exercise","volume":"15","author":"A Zignoli","year":"2019","journal-title":"Sport Sci Health"},{"issue":"7","key":"pone.0319760.ref019","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/JBHI.2019.2958879","article-title":"Deep learning for fall risk assessment with inertial sensors: utilizing domain knowledge in spatio-temporal gait parameters","volume":"24","author":"C Tunca","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"pone.0319760.ref020","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41746-021-00531-3","article-title":"Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities","volume":"4","author":"R Amelard","year":"2021","journal-title":"NPJ Digit Med"},{"issue":"6","key":"pone.0319760.ref021","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1152\/japplphysiol.00148.2023","article-title":"Prediction of oxygen uptake kinetics during heavy-intensity cycling exercise by machine learning analysis","volume":"134","author":"ET Hedge","year":"2023","journal-title":"J Appl Physiol (1985)"},{"key":"pone.0319760.ref022","doi-asserted-by":"crossref","first-page":"897412","DOI":"10.3389\/fphys.2022.897412","article-title":"Enhancing instantaneous oxygen uptake estimation by non-linear model using cardio-pulmonary physiological and motion signals","volume":"13","author":"Z Wang","year":"2022","journal-title":"Front Physiol"},{"issue":"4","key":"pone.0319760.ref023","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.3390\/s23042249","article-title":"Surrogate Modelling for oxygen uptake prediction using LSTM neural network","volume":"23","author":"P Davidson","year":"2023","journal-title":"Sensors (Basel)"},{"issue":"3","key":"pone.0319760.ref024","doi-asserted-by":"crossref","first-page":"e0229466","DOI":"10.1371\/journal.pone.0229466","article-title":"Estimating an individual\u2019s oxygen uptake during cycling exercise with a recurrent neural network trained from easy-to-obtain inputs: A pilot study","volume":"15","author":"A Zignoli","year":"2020","journal-title":"PLoS One"},{"key":"pone.0319760.ref025","doi-asserted-by":"crossref","first-page":"868","DOI":"10.3389\/fphys.2018.00868","article-title":"Is Oxygen uptake measurement enough to estimate energy expenditure during high-intensity intermittent exercise? Quantification of anaerobic contribution by different methods","volume":"9","author":"VLG Panissa","year":"2018","journal-title":"Front Physiol"},{"issue":"4","key":"pone.0319760.ref026","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1080\/02701367.2019.1643446","article-title":"Lactate equivalent for maximal lactate steady state determination in soccer","volume":"90","author":"I Garcia-Tabar","year":"2019","journal-title":"Res Q Exerc Sport"},{"issue":"4","key":"pone.0319760.ref027","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1080\/02640419608727717","article-title":"A 1% treadmill grade most accurately reflects the energetic cost of outdoor running","volume":"14","author":"AM Jones","year":"1996","journal-title":"J Sports Sci"},{"issue":"15","key":"pone.0319760.ref028","doi-asserted-by":"crossref","first-page":"3975","DOI":"10.1016\/j.jbiomech.2015.09.015","article-title":"Classification of team sport activities using a single wearable tracking device","volume":"48","author":"DWT Wundersitz","year":"2015","journal-title":"J Biomech"},{"key":"pone.0319760.ref029","doi-asserted-by":"crossref","first-page":"1764","DOI":"10.3389\/fphys.2018.01764","article-title":"Accuracy and precision of the COSMED K5 portable analyser","volume":"9","author":"I Perez-Suarez","year":"2018","journal-title":"Front Physiol"},{"issue":"4","key":"pone.0319760.ref030","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1080\/1091367X.2011.615671","article-title":"Reliability and validity of the ZephyrTM BioHarnessTM to measure respiratory responses to exercise","volume":"15","author":"J Hailstone","year":"2011","journal-title":"Meas Phys Educ Exerc Sci"},{"issue":"2","key":"pone.0319760.ref031","doi-asserted-by":"crossref","first-page":"95","DOI":"10.2165\/11319670-000000000-00000","article-title":"Recommendations for improved data processing from expired gas analysis indirect calorimetry","volume":"40","author":"RA Robergs","year":"2010","journal-title":"Sports Med"},{"key":"pone.0319760.ref032"},{"key":"pone.0319760.ref033","first-page":"785","article-title":"XGBoost","author":"T Chen","year":"2016"},{"issue":"2","key":"pone.0319760.ref034","doi-asserted-by":"crossref","first-page":"67","DOI":"10.3390\/hydrology8020067","article-title":"A multilayer perceptron model for stochastic synthesis","volume":"8","author":"E Rozos","year":"2021","journal-title":"Hydrology"},{"issue":"8","key":"pone.0319760.ref035","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"pone.0319760.ref036"},{"key":"pone.0319760.ref037","article-title":"Deep learning with kernel flow regularization for time series forecasting","author":"M Shirdel","year":"2021","journal-title":"arXiv"},{"issue":"8","key":"pone.0319760.ref038","doi-asserted-by":"crossref","first-page":"2340","DOI":"10.1519\/JSC.0000000000002057","article-title":"Validity of heart rate-based indices to measure training load and intensity in elite football players","volume":"32","author":"P Silva","year":"2018","journal-title":"J Strength Cond Res"},{"issue":"6","key":"pone.0319760.ref039","doi-asserted-by":"crossref","first-page":"e0199509","DOI":"10.1371\/journal.pone.0199509","article-title":"Data fusion of body-worn accelerometers and heart rate to predict VO2max during submaximal running","volume":"13","author":"A De Brabandere","year":"2018","journal-title":"PLoS One"},{"key":"pone.0319760.ref040"},{"issue":"7","key":"pone.0319760.ref041","doi-asserted-by":"crossref","first-page":"517","DOI":"10.2165\/00007256-200333070-00004","article-title":"Heart rate monitoring: applications and limitations","volume":"33","author":"J Achten","year":"2003","journal-title":"Sports Med"},{"issue":"2","key":"pone.0319760.ref042","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/JBHI.2015.2390493","article-title":"Estimating oxygen uptake during nonsteady-state activities and transitions using wearable sensors","volume":"20","author":"M Altini","year":"2016","journal-title":"IEEE J Biomed Health Inform"},{"issue":"5","key":"pone.0319760.ref043","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1123\/ijspp.2023-0444","article-title":"Predicting soccer players\u2019 fitness status through a machine-learning approach","volume":"19","author":"M Mandorino","year":"2024","journal-title":"Int J Sports Physiol Perform"},{"issue":"4","key":"pone.0319760.ref044","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1249\/01.MSS.0000058441.94520.32","article-title":"The yo-yo intermittent recovery test: physiological response, reliability, and validity","volume":"35","author":"P Krustrup","year":"2003","journal-title":"Med Sci Sports Exerc"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T13:51:39Z","timestamp":1745243499000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319760"}},"subtitle":[],"editor":[{"given":"Noman","family":"Naseer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,21]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0319760","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,21]]}}}