Predicting Soccer Players’ Fitness Status Through a Machine-Learning Approach

Click name to view affiliation

Mauro Mandorino Performance and Analytics Department, Parma Calcio 1913, Parma, Italy
Department of Movement, Human and Health Sciences, University of Rome “Foro Italico,” Rome, Italy

Search for other papers by Mauro Mandorino in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-5858-2758 *
,
Jo Clubb Global Performance Insights Ltd, London, United Kingdom

Search for other papers by Jo Clubb in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-6509-7531
, and
Mathieu Lacome Performance and Analytics Department, Parma Calcio 1913, Parma, Italy
Laboratory of Sport, Expertise and Performance (EA 7370), French Institute of Sport (INSEP), Paris, France

Search for other papers by Mathieu Lacome in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-1082-0200
Restricted access

Purpose: The study had 3 purposes: (1) to develop an index using machine-learning techniques to predict the fitness status of soccer players, (2) to explore the index’s validity and its relationship with a submaximal run test (SMFT), and (3) to analyze the impact of weekly training load on the index and SMFT outcomes. Methods: The study involved 50 players from an Italian professional soccer club. External and internal loads were collected during training sessions. Various machine-learning algorithms were assessed for their ability to predict heart-rate responses during the training drills based on external load data. The fitness index, calculated as the difference between actual and predicted heart rates, was correlated with SMFT outcomes. Results: Random forest regression (mean absolute error = 3.8 [0.05]) outperformed the other machine-learning algorithms (extreme gradient boosting and linear regression). Average speed, minutes from the start of the training session, and the work:rest ratio were identified as the most important features. The fitness index displayed a very large correlation (r = .70) with SMFT outcomes, with the highest result observed during possession games and physical conditioning exercises. The study revealed that heart-rate responses from SMFT and the fitness index could diverge throughout the season, suggesting different aspects of fitness. Conclusions: This study introduces an “invisible monitoring” approach to assess soccer player fitness in the training environment. The developed fitness index, in conjunction with traditional fitness tests, provides a comprehensive understanding of player readiness. This research paves the way for practical applications in soccer, enabling personalized training adjustments and injury prevention.

Supplementary Materials

    • Supplementary Table S1 (PDF 384 KB)
  • Collapse
  • Expand
  • 1.

    Halson SL. Monitoring training load to understand fatigue in athletes. Sports Med. 2014;44(2):139147. doi:

  • 2.

    Delaney JA, Duthie GM, Thornton HR, Pyne DB. Quantifying the relationship between internal and external work in team sports: development of a novel training efficiency index. Sci Med Footb. 2018;2(2):149156. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 3.

    Buchheit M, Cholley Y, Lambert P. Psychometric and physiological responses to a preseason competitive camp in the heat with a 6-hour time difference in elite soccer players. Int J Sports Physiol Perform. 2016;11(2):176181. PubMed ID: 26182437 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 4.

    Akubat I, Barrett S, Abt G. Integrating the internal and external training loads in soccer. Int J Sports Physiol Perform. 2014;9(3):457462. PubMed ID: 23475154 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 5.

    Lacome M, Simpson B, Broad N, Buchheit M. Monitoring players’ readiness using predicted heart-rate responses to soccer drills. Int J Sports Physiol Perform. 2018;13(10):12731280. PubMed ID: 29688115 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 6.

    Shushan T, McLaren SJ, Buchheit M, Scott TJ, Barrett S, Lovell R. Submaximal fitness tests in team sports: a theoretical framework for evaluating physiological state. Sports Med. 2022;52(11):26052626. PubMed ID: 35817993 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 7.

    Shushan T, Lovell R, Buchheit M, et al. Submaximal fitness test in team sports: a systematic review and meta-analysis of exercise heart rate measurement properties. Sports Med Open. 2023;9(1):21. PubMed ID: 36964427 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 8.

    Shushan T, Norris D, McLaren SJ, et al. A worldwide survey on the practices and perceptions of submaximal fitness tests in team sports. Int J Sports Physiol Perform. 2023;18(7):765779. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 9.

    Carling C, Lacome M, McCall A, et al. Monitoring of post-match fatigue in professional soccer: welcome to the real world. Sports Med. 2018;48(12):26952702. PubMed ID: 29740792 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 10.

    West SW, Clubb J, Torres-Ronda L, et al. More than a metric: how training load is used in elite sport for athlete management. Int J Sports Med. 2021;42(04):300306. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 11.

    Mandorino M, Figueiredo AJ, Cima G, Tessitore A. Predictive analytic techniques to identify hidden relationships between training load, fatigue and muscle strains in young soccer players. Sports. 2021;10(1):3. PubMed ID: 35050968 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 12.

    Rossi A, Pappalardo L, Cintia P, Iaia FM, Fernández J, Medina D. Effective injury forecasting in soccer with GPS training data and machine learning. PLoS One. 2018;13(7):e0201264. PubMed ID: 30044858 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 13.

    Mandorino M, Figueiredo AJ, Cima G, Tessitore A. Analysis of relationship between training load and recovery status in adult soccer players: a machine learning approach. Int J Comput Sci Sport. 2022;21(2):116. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 14.

    Rossi A, Perri E, Pappalardo L, Cintia P, Iaia FM. Relationship between external and internal workloads in elite soccer players: comparison between rate of perceived exertion and training load. Appl Sci. 2019;9(23):5174. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 15.

    Rico-González M, Pino-Ortega J, Méndez A, Clemente F, Baca A. Machine learning application in soccer: a systematic review. Biol Sport. 2023;40(1):249263. PubMed ID: 36636183 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 16.

    Winter EM, Maughan RJ. Requirements for ethics approvals. J Sports Sci. 2009;27(10):985. doi:

  • 17.

    Helgerud J, Høydal K, Wang E, et al. Aerobic high-intensity intervals improve VO2max more than moderate training. Med Sci Sports Exerc. 2007;39(4):665671. PubMed ID: 17414804 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 18.

    Gómez-Carmona CD, Pino-Ortega J, Sánchez-Ureña B, Ibáñez SJ, Rojas-Valverde D. Accelerometry-based external load indicators in sport: too many options, same practical outcome? Int J Environ Res Public Health. 2019;16(24):5101. PubMed ID: 31847248 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 19.

    Gómez-Carmona CD, Bastida-Castillo A, García-Rubio J, Ibáñez SJ, Pino-Ortega J. Static and dynamic reliability of WIMU PRO™ accelerometers according to anatomical placement. Proc Inst Mech Eng Part P J Sports Eng Technol. 2019;233(2):238248. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 20.

    Muñoz-López A, Granero-Gil P, Pino-Ortega J, De Hoyo M. The validity and reliability of a 5-hz GPS device for quantifying athletes’ sprints and movement demands specific to team sports. J Hum Sport Exerc. 2017;12(1):156166. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 21.

    Gomez-Carmona CD, Bastida-Castillo A, Gonzalez-Custodio A, Olcina G, Pino-Ortega J. Using an inertial device (WIMU PRO) to quantify neuromuscular load in running: reliability, convergent validity, and influence of type of surface and device location. J Strength Cond Res. 2020;34(2):365373. PubMed ID: 31985715 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 22.

    Buchheit M, Simpson BM, Lacome M. Monitoring cardiorespiratory fitness in professional soccer players: is it worth the prick? Int J Sports Physiol Perform. 2020;15(10):14371441. PubMed ID: 33004681 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 23.

    Buchheit M. Monitoring training status with HR measures: do all roads lead to Rome? Front Physiol. 2014;5:73. PubMed ID: 24578692 doi:

  • 24.

    Buchheit M, Simpson MB, Al Haddad H, Bourdon PC, Mendez-Villanueva A. Monitoring changes in physical performance with heart rate measures in young soccer players. Eur J Appl Physiol. 2012;112:711723. PubMed ID: 21656232 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 25.

    Kensert A, Alvarsson J, Norinder U, Spjuth O. Evaluating parameters for ligand-based modeling with random forest on sparse data sets. J Cheminformatics. 2018;10(1):110. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 26.

    Mandorino M, Figueiredo AJ, Cima G, Tessitore A. A data mining approach to predict non-contact injuries in young soccer players. Int J Comput Sci Sport. 2021;20(2):147163. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 27.

    Hopkins W, Marshall S, Batterham A, Hanin J. Progressive statistics for studies in sports medicine and exercise science. Med Sci Sports Exerc. 2009;41(1):3. PubMed ID: 19092709 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 28.

    Keogh EJ, Pazzani MJ. Scaling up dynamic time warping to massive datasets. In: Principles of Data Mining and Knowledge Discovery: Third European Conference, PKDD’99, Prague, Czech Republic, September 15–18, 1999. Proceedings 3. Springer; 1999:111.

    • Search Google Scholar
    • Export Citation
  • 29.

    Cohen J. Statistical Power Analysis for the Behavioral Sciences. Academic Press; 2013.

  • 30.

    Mandorino M, Tessitore A, Coustou S, Riboli A, Lacome M. A new approach to comparing small-sided games and soccer matches demands. Bio Sport. 2024;41(3):1528. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 31.

    Milanez VF, Ramos SP, Okuno NM, Boullosa DA, Nakamura FY. Evidence of a non-linear dose-response relationship between training load and stress markers in elite female futsal players. J Sports Sci Med. 2014;13(1):2229. PubMed ID: 24570601

    • Search Google Scholar
    • Export Citation
  • 32.

    Bache-Mathiesen LK, Andersen TE, Dalen-Lorentsen T, Clarsen B, Fagerland MW. Not straightforward: modelling non-linearity in training load and injury research. BMJ Open Sport Exerc Med. 2021;7(3):e001119. PubMed ID: 34422292 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 33.

    Weaving D, Jones B, Till K, Abt G, Beggs C. The case for adopting a multivariate approach to optimize training load quantification in team sports. Front Physiol. 2017;8:1024. PubMed ID: 29311959 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 34.

    Vallance E, Sutton-Charani N, Imoussaten A, Montmain J, Perrey S. Combining internal and external-training-loads to predict non-contact injuries in soccer. Appl Sci. 2020;10(15):5261. doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 35.

    Weaving D, Jones B, Marshall P, Till K, Abt G. Multiple measures are needed to quantify training loads in professional rugby league. Int J Sports Med. 2017;38(10):735740. PubMed ID: 28783849 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 36.

    Randers MB, Nielsen JJ, Bangsbo J, Krustrup P. Physiological response and activity profile in recreational small‐sided football: no effect of the number of players. Scand J Med Sci Sports. 2014;24:130137. PubMed ID: 24944137 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 37.

    Bredt SGT, Chagas MH, Peixoto GH, Menzel HJ, de Andrade AGP. Understanding player load: meanings and limitations. J Hum Kinet. 2020;71:5. PubMed ID: 32148568

    • Search Google Scholar
    • Export Citation
  • 38.

    Coyle EF, Gonzalez-Alonso J. Cardiovascular drift during prolonged exercise: new perspectives. Exerc Sport Sci Rev. 2001;29(2):8892. PubMed ID: 11337829

    • Search Google Scholar
    • Export Citation
  • 39.

    Zuccarelli L, Porcelli S, Rasica L, Marzorati M, Grassi B. Comparison between slow components of HR and VO2 kinetics: functional significance. Med Sci Sports Exerc. 2018;50(8):16491657. PubMed ID: 29570539 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 40.

    Verheijen R. Football periodisation. World Football Academy; 2014.

  • 41.

    Malone JJ, Di Michele R, Morgans R, Burgess D, Morton JP, Drust B. Seasonal training-load quantification in elite English premier league soccer players. Int J Sports Physiol Perform. 2015;10(4):489497. PubMed ID: 25393111 doi:

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 2337 2337 250
Full Text Views 99 99 3
PDF Downloads 158 158 4