CoChat
Sign Up
Cited by 30Physical Activity and HealthCardiovascular and exercise physiologyNon-Invasive Vital Sign Monitoring

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments

Open access
Spathis, Dimitris, Perez-Pozuelo, Ignacio, Gonzales, Tomas I., Wu, Yu, Brage, Soren, Wareham, Nicholas, Mascolo, Cecilia·2022·npj Digital Medicine
DOI 10.1038/s41746-022-00719-1PMC PMC9718831
Open this paper in CoChat — free accountOpen PDF

Abstract

Cardiorespiratory fitness is an established predictor of metabolic disease and mortality. Fitness is directly measured as maximal oxygen consumption (VO 2max), 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’ ability to capture fitness profiles in free-living conditions using the Fenland Study (N=11,059), along with its longitudinal cohort (N = 2675), and a third external cohort using the UK Biobank Validation Study (N = 181) who underwent maximal VO 2max 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 (r = 0.82, 95CI 0.80–0.83), outperforming other approaches and models and detects fitness change over time (e.g., after 7 years). We also show how the model’s 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41746-022-00719-1

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • The model detects fitness change over time (e.g. after 7 years).

    “It also detects fitness change over time (e.g. after 7 years).”

    From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [136]

  • A recent large-scale analysis using Fenland Study (N = 11 059), its longitudinal cohort (N = 2675), and UK Biobank Validation Study (N = 181) showed that combination of wearables and other biomarkers as inputs to neural networks yields a strong correlation to ground truth in a holdout sample (r = 0.82, 95% CI: 0.80-0.83).

    “A recent large-scale analysis used data from Fenland Study (N = 11 059), along with its longitudinal cohort (N = 2675), and a third external cohort using the UK Biobank Validation Study (N = 181) who underwent maximal VO2max testing, to 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 (r = 0.82,”

    From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [136]

  • The model's latent space can also be used for fitness-aware patient subtyping paving the way to scalable interventions and personalized trial recruitment.

    “Notably, the model’s latent space can also be used for fitness-aware patient subtyping paving the way to scalable interventions and personalized trial recruitment.”

    From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [136]

  • Large population-scale studies showed that HR responses can predict VO2max.

    “while large population-scale studies showed that these HR responses can predict VO2max [136].”

    From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [136]

  • Apple's CRF feature is publicly validated on 221 participants while non-commercial methods use population-scale data from more than 11 000 participants.

    “For example, Apple’s CRF feature is publicly validated on 221 participants [135] while non-commercial methods use population-scale data from more than 11 000 participants [136].”

    From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [136]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 3

  1. Swain, D. P., Brawner, C. A., of Sports Medicine, A. C. et al. ACSM’s Resource Manual for Guidelines for Exercise Testing and Prescription (Wolters Kluwer Health/Lippincott Williams & Wilkins, 2014).
  2. 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, 3122–3130 (PMLR, 2018).
  3. 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).

Cited by

Sorted by citations

Related

Metadata

Authors
Spathis, D., Perez-Pozuelo, I., Gonzales, T. I., Wu, Y., Brage, S., Wareham, N., & Mascolo, C.
Affiliations
University of Cambridge (GB)
Corresponding author
Spathis, Dimitris
ORCID
Venue
npj Digital Medicine
Publisher
Springer Science and Business Media LLC
Published
2022-12-02
Volume
5
Issue
1
Pages
176-176
ISSN
2398-6352 (ISSN-L)
DOI
10.1038/s41746-022-00719-1
PMC
PMC9718831
OpenAlex
W4311185331
Cited by
30
References
30
Citations by year
2026: 9 · 2025: 13 · 2024: 7 · 2023: 1
FWCI
3.25
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Digital Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
RCUK | Engineering and Physical Sciences Research Council (EP/N509620/1)
Topics
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Physical Activity and Health
  • Health Sciences › Medicine › Physiology (medical) › Cardiovascular and exercise physiology
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
Keywords
cardiorespiratory fitness, VO2max, wearable sensors, fitness prediction, free-living conditions, heart rate, artificial neural networks, patient subtyping, UK Biobank

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