Key result
Wearable-derived HRV and pulse arrival time detect physical fatigue with ~88% accuracy.
Why the study?
Existing physical fatigue assessment methods lack personalized, continuous, real-time monitoring capabilities using wearable cardiovascular sensors.
Can a novel physical fatigue assessment method utilizing heart rate variability and pulse arrival time accurately classify fatigue states in healthy subjects?
Observational (n=16)
No
Can a novel physical fatigue assessment method utilizing heart rate variability and pulse arrival time accurately classify fatigue states in healthy subjects?
Effect estimate: Accuracy 0.875 for PAT, 0.813 for SDNN
A novel wearable sensor-based method utilizing heart rate variability and pulse arrival time shows promising accuracy in classifying physical fatigue states.
Supports feasibility of pulse arrival time-based ML for fatigue classification; leaves open clinical validation.
This paper proposes a novel method for physical fatigue assessment that can be applied in wearable systems, by utilizing a set of real-time measurable cardiovascular parameters. Daylength measurements, including a morning test set, physical exercise during the day, and an afternoon test set were conducted on 16 healthy subjects (8 female and 8 male). To analyze cardiovascular parameters for physical fatigue assessment, electrocardiography, pulse wave and blood pressure were measured during the test sets. The fatigue assessment questionnaire score, reaction time, countermovement jump height and hand grip strength were also measured and used as reference parameters. This study demonstrates that (i) the compiled test battery can selectively assess the rested vs. physically-fatigued states; (ii) the obtained linear support-vector machine, trained using the heart rate variability based parameter (F-score 0.842, accuracy 0.813) and pulse arrival time based parameter (F-score 0.875, accuracy 0.875) shows a promising ability to classify between the physically mildly fatigued and significantly fatigued states. Despite the somewhat limited study group size, the results of the study are unique and provide a significant advancement on the existing physical fatigue assessment methods towards a personalized and continuous real-time fatigue monitoring system with wearable sensors.
No takes yet. Share an insight, caveat, or question.
Allik et al. (2022) conducted an observational in Physical fatigue (n=16). Physical exercise-induced fatigue vs. Rested state (morning measurements) was evaluated on Classification accuracy between mildly and significantly fatigued states (Accuracy 0.875 for PAT, 0.813 for SDNN). A linear support-vector machine trained using heart rate variability (SDNN) and pulse arrival time (PAT) demonstrated high accuracy (up to 87.5%) in classifying between mildly and significantly physically fatigued states.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: