Paperdoi:10.3389/fbioe.2026.1939545

Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture

Venue listedDated Oct 30, 2026Added Nov 16, 2026

  • MB

Authors: Maura Seynaeve; Kilian Hendrickx; Benedicte Vanwanseele; Toon de Beukelaar

Frontiers in Bioengineering and Biotechnology 14:1939545 (2026); PMID 43032678; PMC13761331

TL;DR

21 recreational runners ran on a treadmill after a normal night and after a night of total sleep deprivation (randomised crossover), wearing a trunk IMU while also tracked by lab motion capture. Within-subject classifiers spotted the sleep-deprived run above chance (best 84% wearable, 81% motion capture), but between-subject models without a personal baseline stayed near 50%.

Abstract

Sleep deprivation is associated with impaired endurance performance and an increased risk of running-related injury. Previous research has identified alterations in running biomechanics following a single night of sleep deprivation under laboratory conditions. However, whether these biomechanical changes can be detected using wearable technology remains unknown. Twenty-one recreationally active runners completed submaximal treadmill running under both normal sleep and total sleep deprivation conditions in a randomized crossover design. Biomechanical features were extracted simultaneously using a full-body motion capture system and a trunk-mounted wearable sensor. Five machine learning classifiers were evaluated in two classification tasks: a within-subject task using paired recordings from the same individual, and a between-subject task performed without individual baseline data. Within-subject classification exceeded chance level (label-permutation testing,

p

0.05

) for most models and both measurement systems, with best accuracies of 84% for the wearable sensor (Logistic Regression) and 81% for the motion capture system (Random Forest). These findings indicate that sleep deprivation produces a systematic and individually consistent biomechanical signature during running. In contrast, between-subject classification failed across nearly all models and systems, with accuracies remaining close to chance level (˜50%), suggesting that inter-individual variability obscures the sleep-deprivation signal in the absence of personalized baseline data. Both systems converged on temporal organization, loading-related variables, and stride-to-stride variability as the most discriminative feature domains. Contrary to expectations, the laboratory motion capture system did not outperform the wearable sensor. Together, these findings suggest that individualized, baseline-referenced monitoring may be important for detecting sleep-deprivation-related changes in running gait, and suggest that a single trunk-mounted wearable sensor may provide a practical solution for real-world monitoring when paired recordings are available.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

StressSleep stagingActivity recognition

Signals

Keywords

FatigueT FatigueFatigue Sub Job CSleep DeprivationRunning GaitTrunk IMURuneasiWithin Subject

How it works

How Method works: Setup → Method → TargetSetup: Signals (accel, imu). Method: Method. Target: Stress; Sleep staging; Activity recognition.SetupSignals: accel, imuxyzSignalsaccel, imuMethodMethodTargetStressStressSleep stagingSleep stagingActivity recognitionActivity recognition

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Seynaeve, M., Hendrickx, K., Vanwanseele, B., & de Beukelaar, T. (2026). Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture. Frontiers in Bioengineering and Biotechnology, 14, 1939545. https://doi.org/10.3389/fbioe.2026.1939545
Seynaeve, Maura, Kilian Hendrickx, Benedicte Vanwanseele, and Toon de Beukelaar. 2026. "Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture." Frontiers in Bioengineering and Biotechnology 14: 1939545. https://doi.org/10.3389/fbioe.2026.1939545.
Seynaeve, M., Hendrickx, K., Vanwanseele, B. and de Beukelaar, T. (2026) 'Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture', Frontiers in Bioengineering and Biotechnology, 14, p. 1939545. doi: 10.3389/fbioe.2026.1939545.
Seynaeve, Maura, et al. "Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture." Frontiers in Bioengineering and Biotechnology, vol. 14, 2026, p. 1939545. https://doi.org/10.3389/fbioe.2026.1939545.
M. Seynaeve, K. Hendrickx, B. Vanwanseele, and T. de Beukelaar, "Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture," Frontiers in Bioengineering and Biotechnology, vol. 14, p. 1939545, 2026, doi: 10.3389/fbioe.2026.1939545.
@article{seynaeve2026detecting,
  title         = {{Detecting sleep deprivation from running biomechanics using machine learning classification: a comparison between wearable and laboratory motion capture}},
  author        = {Seynaeve, Maura and Hendrickx, Kilian and Vanwanseele, Benedicte and de Beukelaar, Toon},
  year          = {2026},
  journal       = {Frontiers in Bioengineering and Biotechnology},
  volume        = {14},
  pages         = {1939545},
  doi           = {10.3389/fbioe.2026.1939545}
}

Added to the ChatPPG research hub