Preprint / Version 2

Predicting daily recovery during long-term endurance training using machine learning analysis

##article.authors##

  • Jeffrey Rothschild Sports Performance Research Institute New Zealand https://orcid.org/0000-0003-0014-5878
  • Tom Stewart Sports Performance Research Institute New Zealand
  • Andrew Kilding Sports Performance Research Institute New Zealand
  • Daniel Plews Sports Performance Research Institute New Zealand

DOI:

https://doi.org/10.51224/SRXIV.191

Keywords:

training load monitoring, Cycling, Running, Triathlon, Sports Nutrition, sleep, HRV

Abstract

Purpose: The aim of this study was to determine if machine learning models could predict the perceived morning recovery status (AM PRS), training feeling during exercise (exercise TF), and daily change in heart rate variability (HRV change) of endurance athletes based on training, dietary intake, sleep, HRV, and subjective wellbeing measures.

 

Methods: Self-selected nutrition intake, exercise training, sleep habits, HRV, and subjective wellbeing of 40 endurance athletes was monitored daily for 12 weeks (3,325 days of tracking). Global and individualized models were constructed using nine machine learning techniques and combined into an ensemble model at the group level, and with a single best algorithm chosen for individualized models. Model performance was compared with a baseline intercept-only model.

 

Results: Prediction error (root mean square error [RMSE]) was lower than baseline for the group models (12.1 vs. 17.5, 13.1 vs. 14.7, and 0.25 vs. 0.30 for AM PRS, exercise TF, and HRV change, respectively). At the individual level prediction accuracy outperformed the baseline model but varied greatly across participants (RMSE range 5.5 to 23.6, 5.7 to 18.2, and 0.05 to 0.52 for AM PRS, exercise TF, and HRV change, respectively).

 

Conclusion: Daily recovery measures can be predicted based on commonly measured variables, with a small subset of variables providing most of the predictive power. However, at the individual level the key variables may vary, and additional data may be needed to improve prediction accuracy.

References

Bourdon PC, Cardinale M, Murray A, et al. Monitoring Athlete Training Loads: Consensus Statement. Int J Sports Physiol Perform. 2017;12(Suppl 2):S2161-S2170.

Voet JG, Lamberts RP, de Koning JJ, de Jong J, Foster C, van Erp T. Differences in execution and perception of training sessions as experienced by (semi-) professional cyclists and their coach. Eur J Sport Sci. 2021:1-9.

Halson SL. Monitoring training load to understand fatigue in athletes. Sports Med. 2014;44 Suppl 2:S139-147.

Impellizzeri FM, Marcora SM, Coutts AJ. Internal and External Training Load: 15 Years On. Int J Sports Physiol Perform. 2019;14(2):270-273.

Clemente FM, Mendes B, Palao JM, et al. Seasonal player wellness and its longitudinal association with internal training load: study in elite volleyball. J Sports Med Phys Fitness. 2019;59(3):345-351.

Achten J, Halson SL, Moseley L, Rayson MP, Casey A, Jeukendrup AE. Higher dietary carbohydrate content during intensified running training results in better maintenance of performance and mood state. J Appl Physiol (1985). 2004;96(4):1331-1340.

Rothschild J, Kilding AE, Plews DJ. Prevalence and Determinants of Fasted Training in Endurance Athletes: A Survey Analysis. Int J Sport Nutr Exerc Metab. 2020;30(5):345-356.

Van Eetvelde H, Mendonca LD, Ley C, Seil R, Tischer T. Machine learning methods in sport injury prediction and prevention: a systematic review. J Exp Orthop. 2021;8(1):27.

Mezyk E, Unold O. Machine learning approach to model sport training. Comput Human Behav. 2011;27(5):1499-1506.

Perri E, Simonelli C, Rossi A, Trecroci A, Alberti G, Iaia FM. Relationship Between Wellness Index and Internal Training Load in Soccer: Application of a Machine Learning Model. Int J Sports Physiol Perform. 2021;16(5):695-703.

Morgenstern JD, Rosella LC, Costa AP, de Souza RJ, Anderson LN. Perspective: Big Data and Machine Learning Could Help Advance Nutritional Epidemiology. Adv Nutr. 2021;12(3):621-631.

Rothschild JA, Morton JP, Stewart T, Kilding AE, Plews DJ. The quantification of daily carbohydrate periodization among endurance athletes during 12 weeks of self-selected training: presentation of a novel Carbohydrate Periodization Index. medRxiv. 2022.

Foster C, Boullosa D, McGuigan M, et al. 25 Years of Session Rating of Perceived Exertion: Historical Perspective and Development. Int J Sports Physiol Perform. 2021;16(5):612-621.

Clemente FM, Rabbani A, Araujo JP. Ratings of perceived recovery and exertion in elite youth soccer players: Interchangeability of 10-point and 100-point scales. Physiol Behav. 2019;210:112641.

Laurent CM, Green JM, Bishop PA, et al. A practical approach to monitoring recovery: development of a perceived recovery status scale. J Strength Cond Res. 2011;25(3):620-628.

Plews DJ, Laursen PB, Stanley J, Kilding AE, Buchheit M. Training adaptation and heart rate variability in elite endurance athletes: opening the door to effective monitoring. Sports Med. 2013;43(9):773-781.

Mishica C, Kyrolainen H, Hynynen E, Nummela A, Holmberg HC, Linnamo V. Evaluation of nocturnal vs. morning measures of heart rate indices in young athletes. PLoS One. 2022;17(1):e0262333.

Chinoy ED, Cuellar JA, Huwa KE, et al. Performance of seven consumer sleep-tracking devices compared with polysomnography. Sleep. 2021;44(5).

Roberts DM, Schade MM, Mathew GM, Gartenberg D, Buxton OM. Detecting sleep using heart rate and motion data from multisensor consumer-grade wearables, relative to wrist actigraphy and polysomnography. Sleep. 2020;43(7).

Miller DJ, Lastella M, Scanlan AT, et al. A validation study of the WHOOP strap against polysomnography to assess sleep. J Sports Sci. 2020;38(22):2631-2636.

Zaffaroni A, Coffey S, Dodd S, et al. Sleep Staging Monitoring Based on Sonar Smartphone Technology. Annu Int Conf IEEE Eng Med Biol Soc. 2019;2019:2230-2233.

Saw AE, Main LC, Gastin PB. Monitoring the athlete training response: subjective self-reported measures trump commonly used objective measures: a systematic review. Br J Sports Med. 2016;50(5):281-291.

Haddad M, Stylianides G, Djaoui L, Dellal A, Chamari K. Session-RPE Method for Training Load Monitoring: Validity, Ecological Usefulness, and Influencing Factors. Front Neurosci. 2017;11:612.

Rothschild J, Kilding AE, Stewart T, Plews DJ. Factors influencing substrate oxidation during submaximal cycling: a modelling analysis. Sports Med. 2022;In Press.

Plews DJ, Laursen PB, Kilding AE, Buchheit M. Evaluating training adaptation with heart-rate measures: a methodological comparison. Int J Sports Physiol Perform. 2013;8(6):688-691.

Sawczuk T, Jones B, Scantlebury S, Till K. Influence of Perceptions of Sleep on Well-Being in Youth Athletes. J Strength Cond Res. 2021;35(4):1066-1073.

Kuhn M, Johnson K. Applied predictive modeling. Vol 26: Springer; 2013.

James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning : with applications in R. New York: Springer; 2021.

Truda G. Quantified Sleep: Machine learning techniques for observational n-of-1 studies. arXiv preprint arXiv:2105.06811. 2021.

Gudivada VN, Rao D, Raghavan VV. Big data driven natural language processing research and applications. Handbook of Statistics. Vol 33: Elsevier; 2015:203-238.

Kapoor S, Narayanan A. Leakage and the Reproducibility Crisis in ML-based Science. arXiv preprint arXiv:2207.07048. 2022.

Yang P, Hwa Yang Y, B Zhou B, Y Zomaya A. A review of ensemble methods in bioinformatics. Current Bioinformatics. 2010;5(4):296-308.

Biecek P, Burzykowski T. Explanatory model analysis: Explore, explain and examine predictive models. Chapman and Hall/CRC; 2021.

Greenwell BM, Boehmke BC, Gray B. Variable Importance Plots-An Introduction to the vip Package. R J. 2020;12(1):343.

Altini M, Plews D. What is behind changes in resting heart rate and heart rate variability? A large-scale analysis of longitudinal measurements acquired in free-living. Sensors. 2021;21(23):7932.

Shmueli G. To explain or to predict? Statist Sci. 2010;25(3):289-310.

Kinnunen H, Rantanen A, Kentta T, Koskimaki H. Feasible assessment of recovery and cardiovascular health: accuracy of nocturnal HR and HRV assessed via ring PPG in comparison to medical grade ECG. Physiol Meas. 2020;41(4):04NT01.

Plews DJ, Scott B, Altini M, Wood M, Kilding AE, Laursen PB. Comparison of Heart-Rate-Variability Recording With Smartphone Photoplethysmography, Polar H7 Chest Strap, and Electrocardiography. Int J Sports Physiol Perform. 2017;12(10):1324-1328.

Champagne CM, Bray GA, Kurtz AA, et al. Energy intake and energy expenditure: a controlled study comparing dietitians and non-dietitians. J Am Diet Assoc. 2002;102(10):1428-1432.

Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY, Van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 2019;110:12-22.

Downloads

Posted

2022-09-02 — Updated on 2022-09-02

Versions