{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:12:45Z","timestamp":1788876765334,"version":"build-2803163510"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>\n                      This study developed and evaluated a machine learning model for predicting oxygen uptake (VO\n                      <jats:sub>2<\/jats:sub>\n                      ) in dragon boat athletes using wearable signals and compared performance across signal combinations and device groups.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Twelve male collegiate dragon boat athletes completed nine tests grouped into six task types (T1\u2013T6): 200-, 500-, and 1000-m all-out paddling tests; an incremental test; a five-stage constant-load test; and four supramaximal-intensity tests pooled as T6. Heart rate, respiratory rate, device-derived minute ventilation, and muscle-oxygenation signals were collected. Fifteen signal combinations (G1\u2013G15) and six device groups (A\u2013F) were evaluated using a multilayer perceptron model. Performance was assessed using mean absolute error (MAE) and root mean square error (RMSE), with mean absolute percentage error (MAPE) also reported.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      G13\u2013G15 showed comparable performance, with no significant differences. G14 yielded the lowest MAE and MAPE (2.21 mL\u00b7kg\n                      <jats:sup>\u22121<\/jats:sup>\n                      \u00b7min\n                      <jats:sup>\u22121<\/jats:sup>\n                      and 9.48%), whereas G13 yielded the lowest RMSE (3.19 mL\u00b7kg\n                      <jats:sup>\u22121<\/jats:sup>\n                      \u00b7min\n                      <jats:sup>\u22121<\/jats:sup>\n                      ). No significant differences were observed among signal combinations within Groups A, C, D, E, or F. Group F showed the lowest MAPE but did not differ significantly from Group B, whereas Group C showed significantly higher MAPE than Groups B, D, E, and F. Performance did not differ significantly across exercise tasks. During the 1000-m test, predicted and measured VO\n                      <jats:sub>2<\/jats:sub>\n                      were strongly correlated for G15 (\n                      <jats:italic>r<\/jats:italic>\n                      \u00a0=\u00a00.88), with a mean prediction error of 0.44 mL\u00b7kg\n                      <jats:sup>\u22121<\/jats:sup>\n                      \u00b7min\n                      <jats:sup>\u22121<\/jats:sup>\n                      and descriptive 95% limits of agreement from \u22126.32 to 7.20 mL\u00b7kg\n                      <jats:sup>\u22121<\/jats:sup>\n                      \u00b7min\n                      <jats:sup>\u22121<\/jats:sup>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      Cardiorespiratory signals provided useful information for wearable-based VO\n                      <jats:sub>2<\/jats:sub>\n                      prediction, whereas the contribution of muscle-oxygenation signals depended on the input configuration. G13\u2013G15 should be regarded as comparably performing configurations, and bilateral muscle-oxygenation monitoring was not consistently superior to unilateral monitoring. Multimodal wearable signals show potential for non-invasive VO\n                      <jats:sub>2<\/jats:sub>\n                      monitoring in dragon boat athletes, although larger samples and independent validation are required.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1740055","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:03:38Z","timestamp":1788876218000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prediction of oxygen uptake in dragon boat athletes using machine learning and multimodal physiological signals"],"prefix":"10.3389","volume":"17","author":[{"given":"Yongji","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Physical Education, North China University of Water Resources and Electric Power","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qing","sequence":"additional","affiliation":[{"name":"Key Laboratory of Exercise and Physical Fitness, Ministry of Education, Beijing Sport University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Cui","sequence":"additional","affiliation":[{"name":"The School of Management and Economics, North China University of Water Resources and Electric Power","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinshi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Physical Education, North China University of Water Resources and Electric Power","place":["Zhengzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiabei","family":"Yu","sequence":"additional","affiliation":[{"name":"Competitive Sports Research Office 4, Beijing Research Institute of Sports Science","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"517","DOI":"10.2165\/00007256-200333070-00004","article-title":"Heart rate monitoring: applications and limitations","volume":"33","author":"Achten","year":"2003","journal-title":"Sports Med."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10161956","article-title":"A short review on the machine learning-guided oxygen uptake prediction for sport science applications","volume":"10","author":"Alzamer","year":"2021","journal-title":"Electronics"},{"key":"B3","doi-asserted-by":"publisher","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":"Amelard","year":"2021","journal-title":"NPJ Digit. Med."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2022.100863","article-title":"Recent advances in machine learning for maximal oxygen uptake (VO2max) prediction: a review","volume":"28","author":"Ashfaq","year":"2022","journal-title":"Inf. Med. Unlocked"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0237010","article-title":"The effect of an airflow restriction mask (ARM) on metabolic, ventilatory, and electromyographic responses to continuous cycling exercise","volume":"15","author":"Barbieri","year":"2020","journal-title":"PloS One"},{"key":"B6","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1097\/00005768-200001000-00012","article-title":"Limiting factors for maximum oxygen uptake and determinants of endurance performance","volume":"32","author":"Bassett","year":"2000","journal-title":"Med. Sci. Sports Exerc."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/srep45738","article-title":"Prediction of oxygen uptake dynamics by machine learning analysis of wearable sensors during activities of daily living","volume":"7","author":"Beltrame","year":"2017","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.14814\/phy2.14814","article-title":"Current limits for flowmeter resistance in metabolic carts can negatively affect exercise performance","volume":"9","author":"Beltrami","year":"2021","journal-title":"Physiol. Rep."},{"key":"B9","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-020-0226-6","article-title":"Investigating sources of inaccuracy in wearable optical heart rate sensors","volume":"3","author":"Bent","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1055\/s-0030-1253375","article-title":"Predicting MAOD using only a supramaximal exhaustive test","volume":"31","author":"Bertuzzi","year":"2010","journal-title":"Int. J. Sports Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical methods for assessing agreement between two methods of clinical measurement","volume":"1","author":"Bland","year":"1986","journal-title":"Lancet."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1578","DOI":"10.1080\/001401300750004005","article-title":"The relationship between heart rate and oxygen uptake during non-steady state exercise","volume":"43","author":"Bot","year":"2000","journal-title":"Ergonomics."},{"key":"B13","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s00421-020-04514-2","article-title":"Reliability and validity of the COSMED K5 portable metabolic system during walking","volume":"121","author":"DeBlois","year":"2021","journal-title":"Eur. J. Appl. Physiol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1249\/mss.0000000000001284","article-title":"Variable accuracy of wearable heart rate monitors during aerobic exercise","volume":"49","author":"Gillinov","year":"2017","journal-title":"Med. Sci. Sports Exerc."},{"key":"B15","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1519\/JSC.0b013e318252f612","article-title":"Physiological and physical characteristics of elite dragon boat paddlers","volume":"27","author":"Ho","year":"2013","journal-title":"J. Strength Cond. Res."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11030091","article-title":"Machine learning for human activity recognition: state-of-the-art techniques and emerging trends","volume":"11","author":"Hossen","year":"2025","journal-title":"J. Imaging."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/bios15040208","article-title":"Machine learning-based VO2 estimation using a wearable multiwavelength photoplethysmography device","volume":"15","author":"Hsiao","year":"2025","journal-title":"Biosensors."},{"key":"B18","doi-asserted-by":"publisher","first-page":"713","DOI":"10.5114\/biolsport.2021.103571","article-title":"The use of muscle near-infrared spectroscopy (NIRS) to assess the aerobic training loads of world-class rowers","volume":"38","author":"Klusiewicz","year":"2021","journal-title":"Biol. Sport."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3390\/s24165412","article-title":"Combined impact of heart rate sensor placements with respiratory rate and minute ventilation on oxygen uptake prediction","volume":"24","author":"Lu","year":"2024","journal-title":"Sensors."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10020254","article-title":"Are activity wrist-worn devices accurate for determining heart rate during intense exercise","volume":"10","author":"Mart\u00edn-Escudero","year":"2023","journal-title":"Bioengineering."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3390\/s23052472","article-title":"Using a contemporary portable metabolic gas exchange system for assessing energy expenditure: a validity and reliability study","volume":"23","author":"McClung","year":"2023","journal-title":"Sensors."},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.5040\/9781492595618","volume-title":"Monitoring Training and Performance in Athletes","author":"McGuigan","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/s22218238","article-title":"Muscle oxygenation measured with near-infrared spectroscopy following different intermittent training protocols in a world-class kayaker\u2014a case study","volume":"22","author":"Paulauskas","year":"2022","journal-title":"Sensors."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fspor.2022.864825","article-title":"Muscle oxygenation unlocks the secrets of physiological responses to exercise: time to exploit it in the training monitoring","volume":"4","author":"Perrey","year":"2022","journal-title":"Front. Sports Act. Living."},{"key":"B25","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/s40279-017-0820-1","article-title":"Muscle oximetry in sports science: a systematic review","volume":"48","author":"Perrey","year":"2018","journal-title":"Sports Med."},{"key":"B26","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1007\/s40279-023-01987-x","article-title":"Muscle oximetry in sports science: an updated systematic review","volume":"54","author":"Perrey","year":"2024","journal-title":"Sports Med."},{"key":"B27","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/978-3-642-35289-8_5","article-title":"Early stopping \u2014 but when","volume-title":"Neural Networks: Tricks of the Trade: Second Edition","author":"Prechelt","year":"2012"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.2196\/67110","article-title":"Wrist-worn and arm-worn wearables for monitoring heart rate during sedentary and light-to-vigorous physical activities: Device validation study","volume":"9","author":"Schweizer","year":"2025","journal-title":"JMIR Cardio."},{"key":"B29","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s00421-024-05593-1","article-title":"Profiles of muscle-specific oxygenation responses and thresholds during graded cycling incremental test","volume":"125","author":"Sendra-P\u00e9rez","year":"2025","journal-title":"Eur. J. Appl. Physiol."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0319760","article-title":"Estimating oxygen uptake in simulated team sports using machine learning models and wearable sensor data: a pilot study","volume":"20","author":"Sheridan","year":"2025","journal-title":"PloS One"},{"key":"B31","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1136\/bjsm.29.1.13","article-title":"Physical and physiological profiles of Malaysian dragon boat rowers","volume":"29","author":"Singh","year":"1995","journal-title":"Br. J. Sports Med."},{"key":"B32","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1038\/s41746-022-00719-1","article-title":"Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments","volume":"5","author":"Spathis","year":"2022","journal-title":"NPJ Digit. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1007\/s00421-021-04666-9","article-title":"A heat and moisture-exchanging mask impairs self-paced maximal running performance in a sub-zero environment","volume":"121","author":"Tutt","year":"2021","journal-title":"Eur. J. Appl. Physiol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.neuroimage.2016.10.038","article-title":"Assessing and tuning brain decoders: cross-validation, caveats, and guidelines","volume":"145","author":"Varoquaux","year":"2017","journal-title":"NeuroImage."},{"key":"B35","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1001\/jamacardio.2016.3340","article-title":"Accuracy of wrist-worn heart rate monitors","volume":"2","author":"Wang","year":"2017","journal-title":"JAMA Cardiol."},{"key":"B36","doi-asserted-by":"publisher","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":"Wang","year":"2022","journal-title":"Front. Physiol."},{"key":"B37","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1142\/9789811270611_0005","article-title":"Feasibility of using an armband optical heart rate sensor in naturalistic environment","volume":"28","author":"Yu","year":"2023","journal-title":"Pac. Symp. Biocomput."},{"key":"B38","doi-asserted-by":"publisher","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":"Zignoli","year":"2020","journal-title":"PloS One"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1740055\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T14:03:40Z","timestamp":1788876220000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1740055\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":38,"alternative-id":["10.3389\/fphys.2026.1740055"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1740055","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"article-number":"1740055"}}