{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T18:34:10Z","timestamp":1772217250966,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T00:00:00Z","timestamp":1669939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T00:00:00Z","timestamp":1669939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N509620\/1"],"award-info":[{"award-number":["EP\/N509620\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Cardiorespiratory fitness is an established predictor of metabolic disease and mortality. Fitness is directly measured as maximal oxygen consumption (VO<jats:sub>2<\/jats:sub><jats:italic>m<\/jats:italic><jats:italic>a<\/jats:italic><jats:italic>x<\/jats:italic>), or indirectly assessed using heart rate responses to standard exercise tests. However, such testing is costly and burdensome because it requires specialized equipment such as treadmills and oxygen masks, limiting its utility. Modern wearables capture dynamic real-world data which could improve fitness prediction. In this work, we design algorithms and models that convert raw wearable sensor data into cardiorespiratory fitness estimates. We validate these estimates\u2019 ability to capture fitness profiles in free-living conditions using the Fenland Study (N=11,059), along with its longitudinal cohort (<jats:italic>N<\/jats:italic>\u2009=\u20092675), and a third external cohort using the UK Biobank Validation Study (<jats:italic>N<\/jats:italic>\u2009=\u2009181) who underwent maximal VO<jats:sub>2<\/jats:sub><jats:italic>m<\/jats:italic><jats:italic>a<\/jats:italic><jats:italic>x<\/jats:italic>testing, the gold standard measurement of fitness. Our results show that the combination of wearables and other biomarkers as inputs to neural networks yields a strong correlation to ground truth in a holdout sample (<jats:italic>r<\/jats:italic>\u2009=\u20090.82, 95CI 0.80\u20130.83), outperforming other approaches and models and detects fitness change over time (e.g., after 7 years). We also show how the model\u2019s latent space can be used for fitness-aware patient subtyping paving the way to scalable interventions and personalized trial recruitment. These results demonstrate the value of wearables for fitness estimation that today can be measured only with laboratory tests.<\/jats:p>","DOI":"10.1038\/s41746-022-00719-1","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T12:00:50Z","timestamp":1669982450000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9761-951X","authenticated-orcid":false,"given":"Dimitris","family":"Spathis","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1150-2754","authenticated-orcid":false,"given":"Ignacio","family":"Perez-Pozuelo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0085-8771","authenticated-orcid":false,"given":"Tomas I.","family":"Gonzales","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Soren","family":"Brage","sequence":"additional","affiliation":[]},{"given":"Nicholas","family":"Wareham","sequence":"additional","affiliation":[]},{"given":"Cecilia","family":"Mascolo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,2]]},"reference":[{"key":"719_CR1","doi-asserted-by":"publisher","first-page":"e183605","DOI":"10.1001\/jamanetworkopen.2018.3605","volume":"1","author":"K Mandsager","year":"2018","unstructured":"Mandsager, K. et al. Association of cardiorespiratory fitness with long-term mortality among adults undergoing exercise treadmill testing. JAMA Netw. Open 1, e183605\u2013e183605 (2018).","journal-title":"JAMA Netw. Open"},{"key":"719_CR2","unstructured":"Swain, D. P., Brawner, C. A., of Sports Medicine, A. C. et al. ACSM\u2019s Resource Manual for Guidelines for Exercise Testing and Prescription (Wolters Kluwer Health\/Lippincott Williams & Wilkins, 2014)."},{"key":"719_CR3","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1249\/MSS.0b013e3181af238d","volume":"42","author":"Z-B Cao","year":"2010","unstructured":"Cao, Z.-B. et al. Predicting VO2max with an objectively measured physical activity in Japanese women. Med. Sci. Sports Exerc. 42, 179\u2013186 (2010).","journal-title":"Med. Sci. Sports Exerc."},{"key":"719_CR4","doi-asserted-by":"crossref","unstructured":"Gonzales, T. I. et al. Resting heart rate as a biomarker for tracking change in cardiorespiratory fitness of UK adults: the fenland study. medRxiv (2020).","DOI":"10.1101\/2020.07.01.20144154"},{"key":"719_CR5","doi-asserted-by":"crossref","unstructured":"Gonzales, T. I. et al. Estimating maximal oxygen consumption from heart rate response to submaximal ramped treadmill test. medRxiv (2020).","DOI":"10.1101\/2020.02.18.20024489"},{"key":"719_CR6","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1249\/MSS.0b013e31821d3f6f","volume":"43","author":"BM Nes","year":"2011","unstructured":"Nes, B. M. et al. Estimating VO2 peak from a nonexercise prediction model: the hunt study, norway. Med. Sci. Sports Exerc. 43, 2024\u20132030 (2011).","journal-title":"Med. Sci. Sports Exerc."},{"key":"719_CR7","doi-asserted-by":"crossref","unstructured":"Spathis, D., Perez-Pozuelo, I., Brage, S., Wareham, N. J. & Mascolo, C. Self-supervised transfer learning of physiological representations from free-living wearable data. In Proceedings of the Conference on Health, Inference, and Learning, 69\u201378 (2021).","DOI":"10.1145\/3450439.3451863"},{"key":"719_CR8","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1038\/s41591-021-01339-0","volume":"27","author":"J Dunn","year":"2021","unstructured":"Dunn, J. et al. Wearable sensors enable personalized predictions of clinical laboratory measurements. Nature medicine 27, 1105\u20131112 (2021).","journal-title":"Nature medicine"},{"key":"719_CR9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/jpm7020003","volume":"7","author":"A Shcherbina","year":"2017","unstructured":"Shcherbina, A. et al. Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort. J. Person. Med. 7, 3 (2017).","journal-title":"J. Person. Med."},{"key":"719_CR10","doi-asserted-by":"publisher","first-page":"3037","DOI":"10.3390\/ijerph16173037","volume":"16","author":"S Passler","year":"2019","unstructured":"Passler, S., Bohrer, J., Bl\u00f6chinger, L. & Senner, V. Validity of wrist-worn activity trackers for estimating vo2max and energy expenditure. Int. J. Environ. Res. Public Health 16, 3037 (2019).","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"719_CR11","doi-asserted-by":"crossref","first-page":"393","DOI":"10.70252\/BDAY8376","volume":"12","author":"KD Cooper","year":"2019","unstructured":"Cooper, K. D. & Shafer, A. B. Validity and reliability of the polar a300\u2019s fitness test feature to predict vo2max. Int. J. Exerc. Sci. 12, 393 (2019).","journal-title":"Int. J. Exerc. Sci."},{"key":"719_CR12","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.artmed.2016.02.002","volume":"68","author":"M Altini","year":"2016","unstructured":"Altini, M., Casale, P., Penders, J. & Amft, O. Cardiorespiratory fitness estimation in free-living using wearable sensors. Artif. Intell. Med. 68, 37\u201346 (2016).","journal-title":"Artif. Intell. Med."},{"key":"719_CR13","doi-asserted-by":"publisher","first-page":"e38570","DOI":"10.2196\/38570","volume":"6","author":"J Helgerud","year":"2022","unstructured":"Helgerud, J., Haglo, H. & Hoff, J. et al. Prediction of vo2max from submaximal exercise using the smartphone application myworkout go: Validation study of a digital health method. JMIR Cardio 6, e38570 (2022).","journal-title":"JMIR Cardio"},{"key":"719_CR14","doi-asserted-by":"publisher","first-page":"i34","DOI":"10.1093\/bja\/aex393","volume":"119","author":"K Richardson","year":"2017","unstructured":"Richardson, K., Levett, D., Jack, S. & Grocott, M. Fit for surgery? perspectives on preoperative exercise testing and training. Br. J. Anaesth. 119, i34\u2013i43 (2017).","journal-title":"Br. J. Anaesth."},{"key":"719_CR15","doi-asserted-by":"crossref","unstructured":"Leon-Ferre, R., Ruddy, K. J., Staff, N. P. & Loprinzi, C. L. Fit for chemo: Nerves may thank you. J. Natl Cancer Inst. 109 (2017).","DOI":"10.1093\/jnci\/djw208"},{"key":"719_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12966-019-0882-6","volume":"16","author":"T Lindsay","year":"2019","unstructured":"Lindsay, T. et al. Descriptive epidemiology of physical activity energy expenditure in uk adults (the fenland study). Int. J. Behav. Nutr. Phys. Activity 16, 1\u201313 (2019).","journal-title":"Int. J. Behav. Nutr. Phys. Activity"},{"key":"719_CR17","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s00421-003-0988-y","volume":"91","author":"N Uth","year":"2004","unstructured":"Uth, N., S\u00f8rensen, H., Overgaard, K. & Pedersen, P. K. Estimation of vo2max from the ratio between hrmax and hrrest\u2013the heart rate ratio method. Eur. J. Appl. Physiol. 91, 111\u2013115 (2004).","journal-title":"Eur. J. Appl. Physiol."},{"key":"719_CR18","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/S0735-1097(00)01054-8","volume":"37","author":"H Tanaka","year":"2001","unstructured":"Tanaka, H., Monahan, K. D. & Seals, D. R. Age-predicted maximal heart rate revisited. J. Am. Coll. Cardiol. 37, 153\u2013156 (2001).","journal-title":"J. Am. Coll. Cardiol."},{"key":"719_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-019-2680-1","volume":"20","author":"HA Gaspar","year":"2019","unstructured":"Gaspar, H. A. & Breen, G. Probabilistic ancestry maps: a method to assess and visualize population substructures in genetics. BMC Bioinform. 20, 1\u201311 (2019).","journal-title":"BMC Bioinform."},{"key":"719_CR20","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1093\/annonc\/mdu250","volume":"26","author":"D Schmid","year":"2015","unstructured":"Schmid, D. & Leitzmann, M. Cardiorespiratory fitness as predictor of cancer mortality: a systematic review and meta-analysis. Ann. Oncol. 26, 272\u2013278 (2015).","journal-title":"Ann. Oncol."},{"key":"719_CR21","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.ypmed.2016.10.011","volume":"93","author":"FB Schuch","year":"2016","unstructured":"Schuch, F. B. et al. Are lower levels of cardiorespiratory fitness associated with incident depression? a systematic review of prospective cohort studies. Prev. Med. 93, 159\u2013165 (2016).","journal-title":"Prev. Med."},{"key":"719_CR22","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1016\/j.ehj.2004.06.013","volume":"25","author":"JA Laukkanen","year":"2004","unstructured":"Laukkanen, J. A., Kurl, S., Salonen, R., Rauramaa, R. & Salonen, J. T. The predictive value of cardiorespiratory fitness for cardiovascular events in men with various risk profiles: a prospective population-based cohort study. Eur. Heart J. 25, 1428\u20131437 (2004).","journal-title":"Eur. Heart J."},{"key":"719_CR23","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.2337\/dc12-0712","volume":"36","author":"JM Jakicic","year":"2013","unstructured":"Jakicic, J. M. et al. Four-year change in cardiorespiratory fitness and influence on glycemic control in adults with type 2 diabetes in a randomized trial: the look ahead trial. Diabetes Care 36, 1297\u20131303 (2013).","journal-title":"Diabetes Care"},{"key":"719_CR24","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.atherosclerosis.2021.06.904","volume":"330","author":"S Qui","year":"2021","unstructured":"Qui, S., Cai, X., Sun, Z., Wu, T. & Schumann, U. Is estimated cardiorespiratory fitness an effective predictor for cardiovascular and all-cause mortality? a meta-analysis. Atherosclerosis 330, 22\u201328 (2021).","journal-title":"Atherosclerosis"},{"key":"719_CR25","unstructured":"Apple. Using apple watch to estimate cardio fitness with vo2 max (2021). https:\/\/www.apple.com\/healthcare\/docs\/site\/Using_Apple_Watch_to_Estimate_Cardio_Fitness_with_VO2_max.pdf. [Online; posted 2021, note = https:\/\/www.apple.com\/healthcare\/docs\/site\/Using_Apple_Watch_to_Estimate_Cardio_Fitness_with_VO2_max.pdf]."},{"key":"719_CR26","unstructured":"Lipton, Z., Wang, Y.-X. & Smola, A. Detecting and correcting for label shift with black box predictors. In Proceedings of International conference on machine learning, 3122\u20133130 (PMLR, 2018)."},{"key":"719_CR27","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1038\/sj.ejcn.1602118","volume":"59","author":"S Brage","year":"2005","unstructured":"Brage, S., Brage, N., Franks, P. W., Ekelund, U. & Wareham, N. J. Reliability and validity of the combined heart rate and movement sensor actiheart. Eur. J. Clin. Nutr. 59, 561\u2013570 (2005).","journal-title":"Eur. J. Clin. Nutr."},{"key":"719_CR28","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1152\/japplphysiol.00092.2006","volume":"103","author":"S Brage","year":"2007","unstructured":"Brage, S. et al. Hierarchy of individual calibration levels for heart rate and accelerometry to measure physical activity. J. Appl. Physiol. 103, 682\u2013692 (2007).","journal-title":"J. Appl. Physiol."},{"key":"719_CR29","doi-asserted-by":"crossref","unstructured":"Gonzales, T. I. et al. Descriptive epidemiology of cardiorespiratory fitness in UK adults: The fenland study. medRxiv (2022).","DOI":"10.1101\/2022.03.01.22271683"},{"key":"719_CR30","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.jpsychires.2016.10.005","volume":"84","author":"M Faurholt-Jepsen","year":"2017","unstructured":"Faurholt-Jepsen, M., Brage, S., Kessing, L. V. & Munkholm, K. State-related differences in heart rate variability in bipolar disorder. J. Psychiatr. Res. 84, 169\u2013173 (2017).","journal-title":"J. Psychiatr. Res."},{"key":"719_CR31","doi-asserted-by":"publisher","first-page":"e0167472","DOI":"10.1371\/journal.pone.0167472","volume":"11","author":"T White","year":"2016","unstructured":"White, T., Westgate, K., Wareham, N. J. & Brage, S. Estimation of physical activity energy expenditure during free-living from wrist accelerometry in uk adults. PLoS One 11, e0167472 (2016).","journal-title":"PLoS One"},{"key":"719_CR32","unstructured":"Yosinski, J., Clune, J., Nguyen, A., Fuchs, T. & Lipson, H. Understanding neural networks through deep visualization. In Proceedings of ICML Workshop on Deep Learning (2015)."},{"key":"719_CR33","unstructured":"Van der Maaten, L. & Hinton, G. Visualizing data using t-sne. J. Mach. Learn. Res. 9 (2008)."},{"key":"719_CR34","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.23915\/distill.00002","volume":"1","author":"M Wattenberg","year":"2016","unstructured":"Wattenberg, M., Vi\u00e9gas, F. & Johnson, I. How to use t-sne effectively. Distill 1, e2 (2016).","journal-title":"Distill"},{"key":"719_CR35","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1038\/s41562-017-0189-z","volume":"2","author":"DJ Benjamin","year":"2018","unstructured":"Benjamin, D. J. et al. Redefine statistical significance. Nat. Hum. Behav. 2, 6\u201310 (2018).","journal-title":"Nat. Hum. Behav."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00719-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00719-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00719-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T20:52:33Z","timestamp":1728507153000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-022-00719-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,2]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["719"],"URL":"https:\/\/doi.org\/10.1038\/s41746-022-00719-1","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,2]]},"assertion":[{"value":"26 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"176"}}