Key result
Models estimating cardiorespiratory fitness from continuous free-living wearable data showed good agreement with measured values.
Why the study?
Current cardiorespiratory fitness assessment methods may discriminate against frail individuals challenged by maximal cardiopulmonary exercise testing, whereas wearable data may offer a more accurate representation.
Can continuous free-living wearable data accurately estimate cardiorespiratory fitness?
Systematic Review (n=31,072)
Can continuous free-living wearable data accurately estimate cardiorespiratory fitness?
Models using continuous free-living wearable data show good agreement with measured cardiorespiratory fitness, though high heterogeneity and lack of external validation limit current clinical implementation.
Answers are grounded in this paper and cite their sources.
Supports wearable CRF estimation without exercise testing; extends validation but heterogeneity and validation gaps limit routine use.
BACKGROUND Current methods of cardiorespiratory fitness (CRF) assessment may discriminate against frail individuals who are challenged to perform a maximal cardiopulmonary exercise test. CRF estimations from free-living wearable data, captured over extended time periods may offer a more accurate representation. OBJECTIVE This study aimed to review current evidence behind this novel concept and assess the accuracy of estimation models. METHODS Following PRISMA guidelines we systematically searched four databases (MEDLINE, EMBASE, Scopus and arXiv) for studies reporting the development of models to estimate CRF from continuous free-living wearable data. Studies conducted under controlled laboratory conditions were excluded. Performance metrics were combined in a meta-correlation analysis using a random effects model. RESULTS Of 1848 articles screened, 18 met the eligibility criteria with a total of 31072 participants. Weighted mean age was 46.9 ±1.46 years. Multiple computational techniques were used, with eight studies employing more advanced machine learning models. The meta-correlation analysis revealed a pooled overall estimate of 0.83 with a 95%CI [0.77; 0.88]. The I2 test indicated high heterogeneity at 97%. Risk of bias assessment found most concerns in the data analysis domain with studies often lacking clarity around the data handling process. CONCLUSIONS Good agreement between CRF predictions and measured values was noted. Yet no definite conclusions can be drawn for clinical implementation, due to high heterogeneity among the included studies and lack of external validation. Nonetheless, continuous data streams appear a valuable resource that could lead to a step change in how we measure and monitor CRF. CLINICALTRIAL PROSPERO (CRD42024593878)
No takes yet. Share an insight, caveat, or question.
Dosis et al. (2024) conducted a systematic review in Cardiorespiratory fitness (n=31,072). Cardiorespiratory fitness estimation from continuous free-living wearable data vs. Measured cardiorespiratory fitness values was evaluated on Meta-correlation between predicted and measured cardiorespiratory fitness (pooled overall estimate 0.83, 95% CI 0.77-0.88). Models estimating cardiorespiratory fitness from continuous free-living wearable data showed good agreement with measured values.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: