Construction of a Machine Learning Model to Estimate Physiological Variables of Speed Skating Athletes Under Hypoxic Training Conditions.
Journal
Journal of strength and conditioning research
ISSN: 1533-4287
Titre abrégé: J Strength Cond Res
Pays: United States
ID NLM: 9415084
Informations de publication
Date de publication:
01 Jul 2023
01 Jul 2023
Historique:
medline:
26
6
2023
pubmed:
9
6
2021
entrez:
8
6
2021
Statut:
ppublish
Résumé
Han, J, Liu, M, Shi, J, and Li, Y. Construction of a machine learning model to estimate physiological variables of speed skating athletes under hypoxic training conditions. J Strength Cond Res 37(7): 1543-1550, 2023-Monitoring changes in athletes' physiological variables is essential to create a safe and effective hypoxic training plan for speed skating athletes. This research aims to develop a machine learning estimation model to estimate physiological variables of athletes under hypoxic training conditions based on their physiological measurements collected at sea level. The research team recruited 64 professional speed skating athletes to participate in a 10-week training program, including 3 weeks of sea-level training, followed by 4 weeks of hypoxic training and then a 3-week sea-level recovery period. We measured several physiological variables that could reflect the athletes' oxygen transport capacity in the first 7 weeks, including red blood cell (RBC) count and hemoglobin (Hb) concentration. The physiological variables were measured once a week and then modeled as a mathematical model to estimate measurements' changes using the maximum likelihood method. The mathematical model was then used to construct a machine learning model. Furthermore, the original data (measured once per week) were used to construct a polynomial model using curve fitting. We calculated and compared the mean absolute error between estimated values of the 2 models and measured values. Our results show that the machine learning model estimated RBC count and Hb concentration accurately. The errors of the estimated values were within 5% of the measured values. Compared with the curve fitting polynomial model, the accuracy of the machine learning model in estimating hypoxic training's physiological variables is higher. This study successfully constructed a machine learning model that used physiological variables measured at the sea level to estimate the physiological variables during hypoxic training.
Identifiants
pubmed: 34100790
doi: 10.1519/JSC.0000000000004058
pii: 00124278-202307000-00027
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1543-1550Informations de copyright
Copyright © 2023 National Strength and Conditioning Association.
Références
Chen D, Meng QH. Health status detection for patients in physiological monitoring. Conf Proc IEEE Eng Med Biol Soc 4: 4921–4924, 2011.
Dostal J, Stasek J, Kockova R, et al. Cardiac etiology of exercise induced hypoxemia within elite athletes. Med Sci Sports Exerc 51: 3176, 2019.
Hamlin MJ, Hellemans J. Effect of intermittent normobaric hypoxic exposure at rest on haematological, physiological, and performance parameters in multi-sport athletes. J Sports Sci 25: 431–441, 2007.
Holliss BA, Burden R, Jones AM, et al. Eight weeks of intermittent hypoxic training improves submaximal physiological variables in highly trained runners. J J Strength Cond Res 28: 2195–2203, 2014.
Horvat T, Job J. The use of machine learning in sport outcome prediction: A review[J]. Wiley Interdiscip Rev Data Mining Knowledge Discov 10: 1–28, 2020.
Humberstone-Gough CE, Saunders PU, Bonetti DL, et al. Comparison of live high: Train low altitude and intermittent hypoxic exposure. J Sports Ence Med 12: 394–401, 2013.
Hoffmann JJML, van den Broek NMA, Curvers J. Reference intervals of extended erythrocyte and reticulocyte parameters. Clin Chem Lab Med 50: 941–948, 2012.
Hoffman HJ, Johnson RE. Pseudo-likelihood estimation of multivariate normal parameters in the presence of left-censored data. J Agric Biol Environ Stat 20: 156–171, 2015.
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 9: 1735–1780, 1997.
Jacobs RA, Rasmussen P, Siebenmann C, et al. Determinants of time trial performance and maximal incremental exercise in highly trained endurance athletes. J Appl Physiol 111: 1422–1430, 2011.
Khodaee M, Grothe HL, Seyfert JH, et al. Athletes at high altitude. Sports Health 8: 126–132, 2016.
Lecun Y, Bengio Y, Hinton GE, et al. Deep learning. Nature 521: 436–444, 2015.
Link RM, Bernhard S, Brendan C, et al. Maximum-likelihood estimation of xylem vessel length distributions. J Theor Biol 455: 329–341, 2018.
Little MA, Gael V, Sohrab S, et al. Using and understanding cross-validation strategies. Perspectives on Saeb et al. GigaScience 6: 1–6, 2017.
Millet GP, Brocherie F. Hypoxic training is beneficial in elite athletes. J Med Sci Sports Exerc 52: 515–518, 2020.
Matthew WH, Billaut F, Aughey RJ. Live-high train-low improves repeated time-trial and Yo-Yo IR2 performance in sub-elite team-sport athletes. J Science Medicine Sport 20: 190–195, 2017.
Park HY, Hwang HJ, Park JH, et al. The effects of altitude/hypoxic training on oxygen delivery capacity of the blood and aerobic exercise capacity in elite athletes—a meta-analysis. J Exerc Nutr Biochem 20: 15–22, 2016.
Pottgiesser T, Garvican LA, Martin DT, et al. Short-term hematological effects upon completion of a four-week simulated altitude camp. Int J Sports Physiol Perform 7: 79–83, 2012.
Powers SK, Williams JH. Exercise-induced hypoxaemia in highly trained athletes. Sports Med 4: 46–53, 1987.
Pottgiesser T, Ahlgrim C, Ruthardt S, et al. Hemoglobin mass after 21 days of conventional altitude training at 1816 m. J Ence Med Sport 12: 673–675, 2010.
Pla R, Brocherie F, Le Garrec S, et al. Effectiveness of the hypoxic exercise test to predict altitude illness and performance at moderate altitude in high-level swimmers. Physiol Rep 8: e14390, 2020.
Roy RJ. Uncertainty, sensitivity, convergence, and rounding in performing and reporting least-squares fits. J Mol Spectrosc 191: 223–231, 1998.
Sareban M, Schiefer LM, Macholz F, et al. Endurance athletes are at increased risk for early acute mountain sickness at 3450 m. Med Sci Sports Exerc 52: 1109–1115, 2020.
Siebenmann C, Robach P, Lundby C. Regulation of blood volume in lowlanders exposed to high altitude. J Appl Physiol 123: 957–966, 2017.
Siebenmann C, Cathomen A, Hug M, et al. Hemoglobin mass and intravascular volume kinetics during and after exposure to 3454 m altitude. J Appl Physiol 119: 1194–1201, 2015.
Van Thienen R, Hespel P. Enhanced muscular oxygen extraction in athletes exaggerates hypoxemia during exercise in hypoxia. J Appl Physiol 120: 351–361, 2016.
Wehrlin JP, Marti B, Hallén J. Hemoglobin mass and aerobic performance at moderate altitude in elite athletes. Adv Exp Med Biol 903: 357–374, 2016.
Wilber RL. Application of altitude/hypoxic training by elite athletes. Med Sci Sports Exerc 39: 1610–1624, 2007.
Warburton DER, Gledhill N, Quinney HA. Blood volume, aerobic power, and endurance performance: Potential ergogenic effect of volume loading. Clin J Sport Med 10: 59–66, 2000.
Wilber RL. Current trends in altitude training. Sports Med 31: 249–265, 2001.
Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring: A survey. Mech Syst Signal Process 115: 213–237, 2016.