Cardiorespiratory fitness estimation in free-living using wearable sensors
Abstract
Objective In this paper we propose artificial intelligence methods to estimate cardiorespiratory fitness (CRF) in free-living using wearable sensor data.Methods Our methods rely on a computational framework able to contextualize heart rate (HR) in free-living, and use context-specific HR as predictor of CRF without need for laboratory tests. In particular, we propose three estimation steps. Initially, we recognize activity primitives using accelerometer and location data. Using topic models, we group activity primitives and derive activities composites. We subsequently rank activity composites, and analyze the relation between ranked activity composites and CRF across individuals. Finally, HR data in specific activity primitives and composites is used as predictor in a hierarchical Bayesian regression model to estimate CRF level from the participant's habitual behavior in free-living.Results We show that by combining activity primitives and activity composites the proposed framework can adapt to the user and context, and outperforms other CRF estimation models, reducing estimation error between 10.3% and 22.6% on a study population of 46 participants.Conclusions Our investigation showed that HR can be contextualized in free-living using activity primitives and activity composites and robust CRF estimation in free-living is feasible.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Despite some promising studies which attempt to infer VO2max from data collected during free-living conditions, these mostly stem from small-scale cohorts with less than 50 participants and use contextual data from treadmill activity, which again limits their application in real-world contexts.
“Despite some promising studies which attempt to infer VO2max from data collected during free-living conditions, these mostly stem from small-scale cohorts with less than 50 participants and use contextual data from treadmill activity, which again limits their application in real-world contexts [150].”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [150]
Cites
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337 · see citing works
Activity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · see citing works
Mining interesting locations and travel sequences from GPS trajectories
Zheng, Y., Zhang, L., Xie, X., & Ma, W. (2009) · International World Wide Web Conference (WWW) · doi:10.1145/1526709.1526816 · Cited by 1,957 · see citing works
Blair, S. N. (1996) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.1996.03540030039029 · Cited by 1,819 · see citing works
Åstrand, P. O., & Ryhming, I. (1954) · Journal of Applied Physiology · doi:10.1152/jappl.1954.7.2.218 · Cited by 1,558 · see citing works
Wei, M. (1999) · JAMA · doi:10.1001/jama.282.16.1547 · Cited by 1,168 · see citing works
Smart wearable systems: Current status and future challenges
Chan, M., Estève, D., Fourniols, J.-Y., Escriba, C., & Campo, E. (2012) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2012.09.003 · Cited by 953 · see citing works
Bouten, C. V. C., Koekkoek, K. K., Verduin, M., Kodde, R., & Janssen, J. J. (1997) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.554760 · Cited by 911 · see citing works
Proceedings of the 19th international conference on World wide web
(2010) · doi:10.1145/1772690 · Cited by 907 · see citing works
Variability of Aerobic Performance in the Laboratory and Its Physiologic Correlates
Kuipers, H., VERSTAPPEN, F. T. J., KEIZER, H. A., Geurten, P., & van Kranenburg, G. (1985) · International Journal of Sports Medicine · doi:10.1055/s-2008-1025839 · Cited by 884 · see citing works
How to assess physical activity? How to assess physical fitness?
Vanhees, L., Lefevre, J., Philippaerts, R., Martens, M., Huygens, W., Troosters, T., & Beunen, G. (2005) · European Journal of Cardiovascular Prevention & Rehabilitation · doi:10.1097/01.hjr.0000161551.73095.9c · Cited by 658 · see citing works
Prediction of functional aerobic capacity without exercise testing
Jackson, A. S., Blair, S. N., Mahar, M. T., Wier, L. T., Ross, R., & STUTEVILLE, J. E. (1990) · Medicine & Science in Sports & Exercise · doi:10.1249/00005768-199012000-00021 · Cited by 643 · see citing works
Submaximal Exercise Testing: Clinical Application and Interpretation
Noonan, V., & Dean, E. (2000) · Physical Therapy · doi:10.1093/ptj/80.8.782 · Cited by 637 · see citing works
Review: Mortality trends in the general population: the importance of cardiorespiratory fitness
Lee, D.-C., Artero, E. G., Sui, X., & Blair, S. N. (2010) · Journal of Psychopharmacology · doi:10.1177/1359786810382057 · Cited by 628 · see citing works
Discovery of activity patterns using topic models
Huynh, T., Fritz, M., & Schiele, B. (2008) · Ubiquitous Computing · doi:10.1145/1409635.1409638 · Cited by 505 · see citing works
Bennett, C. C., & Hauser, K. (2013) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2012.12.003 · Cited by 378 · see citing works
Westerterp, K. R., Wouters, L., & Lichtenbelt, W. D. V. M. (1995) · Obesity Research · doi:10.1002/j.1550-8528.1995.tb00007.x · Cited by 328 · see citing works
Proceedings of the 11th international conference on Ubiquitous computing
(2009) · doi:10.1145/1620545 · Cited by 309 · see citing works
Estimation of V?O2max from the ratio between HRmax and HRrest ? the Heart Rate Ratio Method
Uth, N., S�rensen, H., Overgaard, K., & Pedersen, P. K. (2003) · European Journal of Applied Physiology · doi:10.1007/s00421-003-0988-y · Cited by 231 · see citing works
Thorsen, L., Skovlund, E., Strømme, S. B., Hornslien, K., Dahl, A. A., & Fosså, S. D. (2005) · Journal of Clinical Oncology · doi:10.1200/jco.2005.04.106 · Cited by 221 · see citing works
Estimating V˙O2peak from a Nonexercise Prediction Model: The HUNT Study, Norway
NES, B. M., JANSZKY, I., VATTEN, L. J., NILSEN, T. I. L., ASPENES, S. T., & WISLØFF, U. (2011) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0b013e31821d3f6f · Cited by 219 · see citing works
Bonomi, A. G., Plasqui, G., Goris, A. H. C., & Westerterp, K. R. (2009) · Journal of Applied Physiology · doi:10.1152/japplphysiol.00150.2009 · Cited by 195 · see citing works
Refined Two-Regression Model for the ActiGraph Accelerometer
Crouter, S. E., Kuffel, E. E., Haas, J. D., Frongillo, E. A., & Bassett, D. R. (2010) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0b013e3181c37458 · Cited by 176 · see citing works
MOPET: A context-aware and user-adaptive wearable system for fitness training
Buttussi, F., & Chittaro, L. (2008) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2007.11.004 · Cited by 172 · see citing works
Loimaala, A., Huikuri, H. V., Oja, P., Pasanen, M. E., & VUORI, I. M. (2000) · Journal of Applied Physiology · doi:10.1152/jappl.2000.89.5.1825 · Cited by 164 · see citing works
Marshall, S. J., & Ramirez, E. R. (2011) · American Journal of Lifestyle Medicine · doi:10.1177/1559827610395487 · Cited by 142 · see citing works
MEDIC: Medical embedded device for individualized care
Wu, W. H., Bui, A. A. T., Batalin, M. A., Au, L. K., Binney, J., & Kaiser, W. J. (2008) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2007.11.006 · Cited by 139 · see citing works
Sartor, F., Vernillo, G., de Morree, H. M., Bonomi, A. G., Torre, A. L., Kubis, H., & Veicsteinas, A. (2013) · Sports Medicine · doi:10.1007/s40279-013-0068-3 · Cited by 136 · see citing works
Using machine learning for real-time activity recognition and estimation of energy expenditure
Tapia, M., & Emmanuel, E. (2008) · Cited by 127 · see citing works
Altini, M., Penders, J., Vullers, R. J. M., & Amft, O. (2014) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2313039 · Cited by 118 · see citing works
Self-citationRuiz, J. R., Ramírez-Lechuga, J., Ortega, F. B., Castro‐Piñero, J., Benítez, J. M., Araúzo-Azofra, A., Sánchez‐Muñoz, C., Sjöstróm, M., Castillo, M. J., Gutiérrez, Á., et al. (2008) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2008.06.004 · Cited by 106 · see citing works
Accelerometry and Heart Rate as a Measure of Physical Fitness: Proof of Concept
PLASQUI, G., & WESTERTERP, K. R. (2005) · Medicine & Science in Sports & Exercise · doi:10.1249/01.mss.0000161805.61893.c0 · Cited by 56 · see citing works
Energy expenditure estimation using wearable sensors
Altini, M., Penders, J., & Amft, O. (2012) · Wireless Health · doi:10.1145/2448096.2448097 · Cited by 50 · see citing works
Self-citationPrediction of VO2max with daily step counts for Japanese adult women
Cao, Z., Miyatake, N., Higuchi, M., Ishikawa‐Takata, K., Miyachi, M., & Tabata, I. (2008) · European Journal of Applied Physiology · doi:10.1007/s00421-008-0902-8 · Cited by 49 · see citing works
Vathsangam, H., Emken, A., Schroeder, E. T., Spruijt‐Metz, D., & Sukhatme, G. S. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2159840 · Cited by 46 · see citing works
Accelerometry and Heart Rate as a Measure of Physical Fitness
Plasqui, G., & Westerterp, K. R. (2006) · Medicine & Science in Sports & Exercise · doi:10.1249/01.mss.0000228942.55152.84 · Cited by 43 · see citing works
Discovery of activity composites using topic models: An analysis of unsupervised methods
Seiter, J., Amft, O., Rossi, M., & Tröster, G. (2014) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2014.05.007 · Cited by 36 · see citing works
Self-citationValidity of Using Heart Rate as a Predictor of Oxygen Consumption in Dance
Redding, E., Wyon, M. A., Shearman, J. P., & Doggart, L. (2004) · Journal of Dance Medicine & Science · doi:10.1177/1089313x0400800301 · Cited by 33 · see citing works
Recognition of User Activity Sequences Using Distributed Event Detection
Amft, O., Lombriser, C., Stiefmeier, T., & Tröster, G. (2007) · Springer eBooks · doi:10.1007/978-3-540-75696-5_8 · Cited by 31 · see citing works
Self-citationTönis, T. M., Gorter, K. J., Vollenbroek-Hutten, M. M. R., & Hermens, H. J. (2012) · PubMed · Cited by 21 · see citing works
(2007) · Lecture notes in computer science · doi:10.1007/978-3-540-75696-5 · Cited by 14 · see citing works
Altini, M., Casale, P., Penders, J., & Amft, O. (2015) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2015.06.008 · Cited by 13 · see citing works
Self-citationPersonalization of Energy Expenditure Estimation in Free Living Using Topic Models
Altini, M., Casale, P., Penders, J., & Amft, O. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2418256 · Cited by 12 · see citing works
Self-citationVALIDITY OF THE POLAR M52 HEART RATE MONITOR IN PREDICTING VO2MAX
Crumpton, S., Williford, H. N., O'Mailia, S., OLSON, M. S., & Woollen, L. E. (2003) · Medicine & Science in Sports & Exercise · doi:10.1097/00005768-200305001-01078 · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Cannière, H. D., Corradi, F., Smeets, C. J. P. P., Schoutteten, M., Varon, C., Hoof, C. A. V., Huffel, S. V., Groenendaal, W., & Vandervoort, P. M. (2020) · Sensors · doi:10.3390/s20123601 · Cited by 66 · see citing works
Privacy Risk Awareness in Wearables and the Internet of Things
Psychoula, I., Chen, L., & Amft, O. (2020) · IEEE Pervasive Computing · doi:10.1109/mprv.2020.2997616 · Cited by 47 · see citing works
Self-citationUse of artificial intelligence in precision nutrition and fitness
Lopes, M. H. B. D. M., Ferreira, D. D., Ferreira, A. C. B. H., da Silva, G. R., Caetano, A. S., & Braz, V. N. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-817133-2.00020-3 · Cited by 50 · see citing works
Silvera‐Tawil, D., Hussain, M. S., & Li, J. (2019) · Smart Health · doi:10.1016/j.smhl.2019.100100 · Cited by 35 · see citing works
Wearable Sensors as a Preoperative Assessment Tool: A Review
Syversen, A., Dosis, A., Jayne, D. G., & Zhang, Z. (2024) · Sensors · doi:10.3390/s24020482 · Cited by 33 · see citing works
Human-centred artificial intelligence for mobile health sensing: challenges and opportunities
Dang, T., Spathis, D., Ghosh, A., & Mascolo, C. (2023) · Royal Society Open Science · doi:10.1098/rsos.230806 · Cited by 30 · see citing works
Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments
Spathis, D., Perez-Pozuelo, I., Gonzales, T. I., Wu, Y., Brage, S., Wareham, N., & Mascolo, C. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00719-1 · Cited by 30 · see citing works
Jahfari, A. N., Tax, D. M. J., Reinders, M. J. T., & van der Bilt, I. (2021) · JMIR Medical Informatics · doi:10.2196/29434 · Cited by 34 · see citing works
Guarducci, S., Jayousi, S., Caputo, S., & Mucchi, L. (2025) · Sensors · doi:10.3390/s25020556 · Cited by 29 · see citing works
Cross-Modal Health State Estimation
Nag, N., Pandey, V., Putzel, P., Bhimaraju, H., Krishnan, S., & Jain, R. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3241913 · Cited by 24 · see citing works
Kwon, S. B., Ahn, J. W., Lee, S. M., Lee, J., Lee, D., Hong, J.-Y., Kim, H. C., & Yoon, H. (2019) · JMIR mhealth and uhealth · doi:10.2196/13327 · Cited by 25 · see citing works
Estimation of cardiorespiratory fitness using heart rate and step count data
Neshitov, A., Tyapochkin, K., Kovaleva, M., Dreneva, A., Surkova, E., Smorodnikova, E., & Pravdin, P. (2023) · Scientific Reports · doi:10.1038/s41598-023-43024-x · Cited by 19 · see citing works
Health State EstimationPreprint
Nag, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.09312 · Cited by 19 · see citing works
Altini, M., & Amft, O. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512924 · Cited by 14 · see citing works
Self-citationSzczegielniak, J., Latawiec, K. J., Łuniewski, J., Stanisławski, R., Bogacz, K., Krajczy, M., & Rydel, M. (2018) · PLoS ONE · doi:10.1371/journal.pone.0191875 · Cited by 14 · see citing works
Derungs, A., Schuster‐Amft, C., & Amft, O. (2018) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2018.00057 · Cited by 14 · see citing works
Self-citationAltini, M., Hoof, C. A. V., & Amft, O. (2017) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi.2017.7897252 · Cited by 13 · see citing works
Self-citationCaramaschi, S., Papini, G. B., & Caiani, E. G. (2023) · Applied Sciences · doi:10.3390/app13074175 · Cited by 8 · see citing works
Monitoring Technologies for Precision Health
Rayan, R. Α., & Zafar, I. (2021) · Wiley eBooks · doi:10.1002/9781119761655.ch13 · Cited by 9 · see citing works
Bibliometric Review of the Step Test: A Comprehensive Analysis of Research Trends and Development
Sampaio, T., Marinho, D. A., Bragada, J. A. A., & Morais, J. E. (2024) · Sports Medicine - Open · doi:10.1186/s40798-024-00764-y · Cited by 8 · see citing works
Development of a New Submaximal Walk Test to Predict Maximal Oxygen Consumption in Healthy Adults
Yang, H. I., Cho, W., Lee, D. H., Suh, S., & Jeon, J. Y. (2021) · Sensors · doi:10.3390/s21175726 · Cited by 6 · see citing works
Energy-Expenditure Estimation During Aerobic Training Sessions for Badminton Players
Yan, X., Yang, J., Dai, J., & Tao, K. (2025) · Sensors · doi:10.3390/s25196257 · Cited by 2 · see citing works
Cyclist Performance Classification System based on Submaximal Fitness Test
Sudin, S., Shakaff, A. Y. M., Zakaria, A., Salleh, A. F., Saad, F. S. A., & Abdullah, A. H. (2018) · Journal of Telecommunication Electronic and Computer Engineering (JTEC) · Cited by 2 · see citing works
Dosis, A., Syversen, A., Kowal, M. R., Grant, D., Tiernan, J. P., Wong, D., & Jayne, D. G. (2025) · JMIR mhealth and uhealth · doi:10.2196/69996 · Cited by 1 · see citing works
Wearable Solutions for P-Health at Work : Precise, Pervasive and Preventive
Lu, K. (2018) · KTH Publication Database DiVA (KTH Royal Institute of Technology) · Cited by 1 · see citing works
Schiavone, G., Lamichhane, B., & Hoof, C. A. V. (2017) · BioMed Research International · doi:10.1155/2017/4593956
Modeling collegiate student-athlete sport performance via self-report measures
Gordon, C. P. (2017) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
AIM in Wearable and Implantable Computing
Baronetto, A., & Amft, O. (2021) · Springer eBooks · doi:10.1007/978-3-030-58080-3_299-1
Self-citationAIM in Wearable and Implantable Computing
Baronetto, A., & Amft, O. (2022) · Springer eBooks · doi:10.1007/978-3-030-64573-1_299
Self-citationMulti-domain Estimation of Health-Related Physical Fitness from SmartwatchesPreprint
Beltrame, T., Lie, M., Alves, G. T., Costa, V. T. D. M., Filho, A. C. B., Góis, M. D. O., Chikui, E. K., de Oliveira, J. L., Pinto, P. R., Angeloni, M. D. A., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4725158/v1
Dosis, A., Syversen, A., Kowal, M. R., Grant, D., Tiernan, J. P., Wong, D., & Jayne, D. G. (2024) · doi:10.2196/preprints.69996
Sampaio, T., Marinho, D. A., Bragada, J. A. A., & Morais, J. E. (2024) · Figshare · doi:10.6084/m9.figshare.26943918
Vascular waveform analysis using Bayesian pulse deconvolution
Ruth, P. S., DeBenedetti, T., O'Brien, L., Landay, J. A., Coleman, T. P., & Fox, E. B. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-03213-0
Huang, X., Chen, D., Cai, Y., Chen, Z., Xie, D., Peng, C., & Li, Y. (2026) · Medicine Advances · doi:10.1002/med4.70082
- Authors
- Altini, M., Casale, P., Penders, J., & Amft, O.
- Affiliations
- Eindhoven University of Technology (NL)
- Imec the Netherlands (NL)
- University of Passau (DE)
- Corresponding author
- Altini, Marco
- Venue
- Artificial Intelligence in Medicine
- Publisher
- Elsevier BV
- Published
- 2016-03
- Volume
- 68
- Pages
- 37-46
- ISSN
- 0933-3657 (ISSN-L)
- OpenAlex
- W2284544053
- Cited by
- 34
- References
- 44
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 5 · 2023: 3 · 2022: 2 · 2021: 4 · 2020: 4 · 2019: 2 · 2018: 6 · 2017: 3
- FWCI
- 2.49
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Artificial Intelligence in Medicine (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Health Sciences › Medicine › Physiology › Physical Activity and Health
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Keywords
- wearable sensors, heart rate, activity recognition, topic modeling, Bayesian hierarchical model, accelerometer, location data, habitual behavior
- MeSH terms
- Cardiorespiratory Fitness, Adult, Artificial Intelligence, Female, Humans, Male, Biosensing Techniques, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
