1
|
Schuth G, Szigeti G, Dobreff G, Pašić A, Gabbett T, Szilas A, Pavlik G. Football Movement Profile-Based Creatine-Kinase Prediction Performs Similarly to Global Positioning System-Derived Machine Learning Models in National-Team Soccer Players. Int J Sports Physiol Perform 2024; 19:874-881. [PMID: 38917990 DOI: 10.1123/ijspp.2024-0077] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2024] [Revised: 04/30/2024] [Accepted: 05/04/2024] [Indexed: 06/27/2024]
Abstract
PURPOSE The relationship between external load and creatine-kinase (CK) response at the team/position or individual level using Global Positioning Systems (GPS) has been studied. This study aimed to compare GPS-derived and Football Movement Profile (FMP) -derived CK-prediction models for national-team soccer players. The second aim was to compare the performance of general and individualized CK prediction models. METHODS Four hundred forty-four national-team soccer players (under 15 [U15] to senior) were monitored during training sessions and matches using GPS. CK was measured every morning from whole blood. The players had 19.3 (18.1) individual GPS-CK pairs, resulting in a total of 8570 data points. Machine learning models were built using (1) GPS-derived or (2) FMP-based parameters or (3) the combination of the 2 to predict the following days' CK value. The performance of general and individual-specific prediction models was compared. The performance of the models was described by R2 and the root-mean-square error (RMSE, in units per liter for CK values). RESULTS The FMP model (R2 = .60, RMSE = 144.6 U/L) performed similarly to the GPS-based model (R2 = .62, RMSE = 141.2 U/L) and the combination of the 2 (R2 = .62, RMSE = 140.3 U/L). The prediction power of the general model was better on average (R2 = .57 vs R2 = .37) and for 73% of the players than the individualized model. CONCLUSIONS The results suggest that FMP-based CK-prediction models perform similarly to those based on GPS-derived metrics. General machine learning models' prediction power was higher than those of the individual-specific models. These findings can be used to monitor postmatch recovery strategies and to optimize weekly training periodization.
Collapse
Affiliation(s)
- Gabor Schuth
- Department of Sport Medicine and Sport Science, Hungarian Football Federation, Budapest, Hungary
- Department of Health Sciences and Sport Medicine, Hungarian University of Sports Science, Budapest, Hungary
| | - György Szigeti
- Department of Sport Medicine and Sport Science, Hungarian Football Federation, Budapest, Hungary
| | - Gergely Dobreff
- Department of Telecommunications and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary
| | - Alija Pašić
- Department of Telecommunications and Media Informatics, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Budapest, Hungary
| | - Tim Gabbett
- Gabbett Performance Solutions, Brisbane, QLD, Australia
| | - Adam Szilas
- Department of Sport Medicine and Sport Science, Hungarian Football Federation, Budapest, Hungary
| | - Gabor Pavlik
- Department of Health Sciences and Sport Medicine, Hungarian University of Sports Science, Budapest, Hungary
| |
Collapse
|
2
|
Saita Y, Hattori K, Hokari A, Ohyama T, Inoue J, Nishimura T, Nemoto S, Aoyagi S. Plasma myoglobin indicates muscle damage associated with acceleration/deceleration during football. J Sports Med Phys Fitness 2023; 63:1337-1342. [PMID: 37712927 DOI: 10.23736/s0022-4707.23.15203-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/16/2023]
Abstract
BACKGROUND Monitoring muscle damage in athletes assists not only coaches to adjust the training workload but also medical staff to prevent injury. Measuring blood myoglobin concentration can help evaluate muscle damage. The novel portable device utilized in this study allows for easy on-site measurement of myoglobin, providing real-time data on the player's muscle damage. This study investigated the relationship between external load (global positioning system parameters) and internal loads (myoglobin concentration and creatine kinase activity) in 15 male professional football players before and after a match. METHODS Whole blood samples from participants' fingertips were collected before the match (baseline) and at 2, 16, and 40 h after the match. Myoglobin concentrations were measured using the IA-100 compact immunoassay system. Creatine kinase concentrations were measured in a clinical laboratory, and match loads were monitored using a global positioning system device. RESULTS The mean myoglobin concentration was significantly higher at 2 h than at the other time points (P<0.05), and decreased to baseline levels within 16 h post-match. The mean creatine kinase concentration increased after the match but did not reach a significant level. Muscle damage monitored by myoglobin after football match-play was strongly associated with acceleration/deceleration metrics rather than the sprint/high-speed running distance. CONCLUSIONS Our findings indicate that myoglobin is a more sensitive marker of muscle damage than creatine kinase after football match-play. Monitoring myoglobin in athletes can aid in determining their recovery status from the previous training load and help practitioners manage the training load.
Collapse
Affiliation(s)
- Yoshitomo Saita
- Department of Medical, IWAKI Sports Club, Fukushima, Japan -
- Department of Sports and Regenerative Medicine, Juntendo University, Tokyo, Japan -
| | - Kazuhiko Hattori
- Department of Sports and Regenerative Medicine, Juntendo University, Tokyo, Japan
| | - Atsushi Hokari
- Department of Sports and Regenerative Medicine, Juntendo University, Tokyo, Japan
| | | | | | | | | | | |
Collapse
|
3
|
Schuth G, Szigeti G, Dobreff G, Pasic A, Gabbett T, Szilas A, Pavlik G. Individual-Specific Relationship Between External Training and Match Load and Creatine-Kinase Response in Youth National Team Soccer Players. Sports Health 2023; 15:700-709. [PMID: 36314370 PMCID: PMC10467477 DOI: 10.1177/19417381221128822] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/31/2023] Open
Abstract
BACKGROUND Previous studies have examined the relationship between external load and creatine-kinase (CK) response at the team level. This study aimed to build individualized CK prediction models for elite youth national team soccer players. HYPOTHESIS The CK response of youth soccer players can be categorized as being sensitive to micromovements (MM), high-velocity (HV) parameters, or the combination of both, measured during training sessions and matches. STUDY DESIGN Prospective cohort study. LEVEL OF EVIDENCE Level 4. METHODS A total of 25 U16-U17 youth national team soccer players were monitored during training sessions and matches using global positioning system (GPS) units. Individual CK values were measured every morning from whole blood. The data set consisted of 57 ± 17 individual datapoints per player. Individual prediction models were used to examine the relationship between external load and consecutive CK changes. Numerous models were built for each player using MM, HV parameters, or the combination of both. The performance of the models was described by the R2 and the root mean square error (RMSE, U/l for CK values). RESULTS The MM models were superior for 8 players (R2 = 0.68; RMSE = 113 U/l), followed by HV (8 players; R2 = 0.69; RMSE = 88 U/l) and the combined models (2 players; R2 = 0.64; RMSE = 141 U/l). For the remaining 7 players, the R2 of the models was <0.5. The recovery time between efforts was more important in the HV model. CONCLUSION Players could be categorized on sensitivity to MM, HV movements, or the combination of both. CLINICAL RELEVANCE These findings can be used to individualize postmatch recovery strategies and to optimize weekly training periodization to maximize match performance.
Collapse
Affiliation(s)
- Gabor Schuth
- Hungarian Football Federation, Department of Sport Medicine and Sport Science, Budapest, Hungary
- University of Physical Education, Department of Health Sciences and Sport Medicine, Budapest, Hungary
| | - Gyorgy Szigeti
- Hungarian Football Federation, Department of Sport Medicine and Sport Science, Budapest, Hungary
| | - Gergely Dobreff
- Budapest University of Technology and Economics (BME), Department of Telecommunications and Media Informatics
| | - Alija Pasic
- Budapest University of Technology and Economics (BME), Department of Telecommunications and Media Informatics
| | - Tim Gabbett
- Gabbett Performance Solutions, Brisbane, Queensland, Australia
- Centre for Health Research, University of Southern Queensland, Ipswich, Queensland, Australia
- Institute of Health and Wellbeing, Federation University, Ballarat, VIC, Australia
| | - Adam Szilas
- Hungarian Football Federation, Department of Sport Medicine and Sport Science, Budapest, Hungary
| | - Gabor Pavlik
- University of Physical Education, Department of Health Sciences and Sport Medicine, Budapest, Hungary
| |
Collapse
|
4
|
Haller N, Behringer M, Reichel T, Wahl P, Simon P, Krüger K, Zimmer P, Stöggl T. Blood-Based Biomarkers for Managing Workload in Athletes: Considerations and Recommendations for Evidence-Based Use of Established Biomarkers. Sports Med 2023; 53:1315-1333. [PMID: 37204619 PMCID: PMC10197055 DOI: 10.1007/s40279-023-01836-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/09/2023] [Indexed: 05/20/2023]
Abstract
Blood-based biomarkers can provide an objective individualized measure of training load, recovery, and health status in order to reduce injury risk and maximize performance. Despite enormous potentials, especially owing to currently evolving technology, such as point-of-care testing, and advantages, in terms of objectivity and non-interference with the training process, there are several pitfalls in the use and interpretation of biomarkers. Confounding variables such as preanalytical conditions, inter-individual differences, or an individual chronic workload can lead to variance in resting levels. In addition, statistical considerations such as the detection of meaningful minimal changes are often neglected. The lack of generally applicable and individual reference levels further complicates the interpretation of level changes and thus load management via biomarkers. Here, the potentials and pitfalls of blood-based biomarkers are described, followed by an overview of established biomarkers currently used to support workload management. Creatine kinase is discussed in terms of its evidence for workload management to illustrate the limited applicability of established markers for workload management to date. We conclude with recommendations for best practices in the use and interpretation of biomarkers in a sport-specific context.
Collapse
Affiliation(s)
- Nils Haller
- Department of Sports Medicine, Rehabilitation and Disease Prevention, Johannes Gutenberg University of Mainz, Mainz, Germany
- Department of Sport and Exercise Science, University of Salzburg, Schlossallee 49, Salzburg, 5400 Hallein-Rif, Austria
| | - Michael Behringer
- Department of Sports Sciences, Goethe University Frankfurt, Frankfurt am Main, Germany
| | - Thomas Reichel
- Department of Exercise Physiology and Sports Therapy, Institute of Sports Science, Justus-Liebig-University Gießen, Gießen, Germany
| | - Patrick Wahl
- Department of Exercise Physiology, German Sport University Cologne, Cologne, Germany
| | - Perikles Simon
- Department of Sports Medicine, Rehabilitation and Disease Prevention, Johannes Gutenberg University of Mainz, Mainz, Germany
| | - Karsten Krüger
- Department of Exercise Physiology and Sports Therapy, Institute of Sports Science, Justus-Liebig-University Gießen, Gießen, Germany
| | - Philipp Zimmer
- Division of Performance and Health (Sports Medicine), Institute for Sport and Sport Science, TU Dortmund University, Dortmund, Germany
| | - Thomas Stöggl
- Department of Sport and Exercise Science, University of Salzburg, Schlossallee 49, Salzburg, 5400 Hallein-Rif, Austria.
- Red Bull Athlete Performance Center, Salzburg, Austria.
| |
Collapse
|
5
|
Teixeira JE, Branquinho L, Ferraz R, Leal M, Silva AJ, Barbosa TM, Monteiro AM, Forte P. Weekly Training Load across a Standard Microcycle in a Sub-Elite Youth Football Academy: A Comparison between Starters and Non-Starters. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph191811611. [PMID: 36141883 PMCID: PMC9517031 DOI: 10.3390/ijerph191811611] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/20/2022] [Revised: 09/11/2022] [Accepted: 09/13/2022] [Indexed: 05/12/2023]
Abstract
Compensatory training sessions have been highlighted as useful strategies to solve the differential weekly training load between the players' starting status. However, the influence of the players' starting status is still understudied in sub-elite youth football. Thus, the aim of this study was to compare the weekly training load on a standard microcycle in starters and non-starters of a sub-elite youth football academy. The weekly training load of 60 young sub-elite football players was monitored during a 6-week period using an 18 Hz global positioning system (GPS), 1 Hz telemetry heart rate, rating of perceived exertion (RPE), and total quality recovery (TQR). The total distance (TD) covered presented a significant difference between starters and non-starters with a moderate effect (t = -2.38, Δ = -428.03 m, p = 0.018, d = 0.26). Training volume was higher in non-starters than in starter players (TDStarters = 5105.53 ± 1684.22 vs. TDNon-starters = 5533.56 ± 1549.26 m). Significant interactive effects were found between a player's starting status, playing time, and session duration in overall training load variables for within (F = 140.46; η2 = 0.85; p < 0.001) and between-subjects (F = 11.63 to 160.70; η2 = 0.05 to 0.76; p < 0.001). The player's starting status seems to only influence the training volume in sub-elite youth football, unless one considers the covariance of the playing time and session duration. Consequently, coaches should prioritize complementary training to equalize training volume and emphasize similar practice opportunities for non-starters. Future studies should evaluate the gap between training and match load, measuring the impact of recovery and compensatory sessions.
Collapse
Affiliation(s)
- José E. Teixeira
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Departamento de Desporto e Educação Física, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
- Correspondence:
| | - Luís Branquinho
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Department of Sports, Higher Institute of Educational Sciences of the Douro, 4560-708 Penafiel, Portugal
| | - Ricardo Ferraz
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Department of Sports Sciences, University of Beira Interior, 6201-001 Covilhã, Portugal
| | - Miguel Leal
- Department of Sports, Higher Institute of Educational Sciences of the Douro, 4560-708 Penafiel, Portugal
| | - António J. Silva
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Department of Sports, Exercise and Health Sciences, University of Trás-os-Montes e Alto Douro, 5001-801 Vila Real, Portugal
| | - Tiago M. Barbosa
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Departamento de Desporto e Educação Física, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
| | - António M. Monteiro
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Departamento de Desporto e Educação Física, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
| | - Pedro Forte
- Research Centre in Sports Sciences, Health and Human Development, 5001-801 Vila Real, Portugal
- Departamento de Desporto e Educação Física, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
- Department of Sports, Higher Institute of Educational Sciences of the Douro, 4560-708 Penafiel, Portugal
| |
Collapse
|
6
|
Freire LA, de Brito MA, Esteves NS, Tannure M, Slimani M, Znazen H, Bragazzi NL, Brito CJ, Soto DAS, Gonçalves D, Miarka B. Running Performance of High-Level Soccer Player Positions Induces Significant Muscle Damage and Fatigue Up to 24 h Postgame. Front Psychol 2021; 12:708725. [PMID: 34594273 PMCID: PMC8477007 DOI: 10.3389/fpsyg.2021.708725] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Accepted: 08/09/2021] [Indexed: 11/25/2022] Open
Abstract
This study aimed to determine the impact of a soccer game on the creatine kinase (Ck) response and recovery and the specific Global Positioning System (GPS)-accelerometry-derived performance analysis during matches and comparing playing positions. A sample composed of 118 observations of 24 professional soccer teams of the Brazil League Serie A was recruited and classified according to playing positions, i.e., Left/Right Defenders (D = 30, age: 25.2 ± 5.8 years, height: 187 ± 5.5 cm, weight: 80 ± 5.8 kg), Offensive Midfielders (OM = 44, age: 25.1 ± 0.2 years, height: 177 ± 0.3 cm, weight: 73 ± 1.2 kg), Forwards (F = 9, age: 25.1 ± 0.2 years, height: 176.9 ± 4.3 cm, weight: 74.5 ± 2.1 kg), Left/Right Wingers (M = 23, age: 24.5 ± 0.5 years, height: 175 ± 1.1 cm, weight: 74 ± 4.4 kg), and Strikers (S = 12, age: 28 ± 0.2 years, height: 184 ± 1.0 cm, weight: 80 ± 1.4 kg). Blood Ck concentration was measured pre-, immediately post-, and 24 h postgame, and the GPS-accelerometry parameters were assessed during games. Findings demonstrated that Ck concentrations were higher at all postgame moments when compared with pregame, with incomplete recovery markers being identified up to 24 h after the game (range: 402–835 U/L). Moreover, Midfielders (108.6 ± 5.6 m/min) and Forwards (109.1 ± 8.3 m/min) had a higher relative distance vs. other positions (100.9 ± 10.1 m/min). Strikers [8.2 (8.1, 9.05) load/min] and Defenders [8.45 (8, 8.8) load/min] demonstrated lower load/min than Wingers [9.5 (9.2, 9.8) load/min], Midfielders [10.6 (9.9, 11.67) load/min], and Forwards [11 (10.65, 11, 15) load/min]. These results could be used to adopt specific training programs and recovery strategies after match according to the playing positions.
Collapse
Affiliation(s)
- Lucas Albuquerque Freire
- Department of Fights, Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Michele Andrade de Brito
- Department of Fights, Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Natã Sant'anna Esteves
- Department of Fights, Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Márcio Tannure
- Department of Fights, Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Maamer Slimani
- Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health (DINOGMI), Section of Psychiatry, University of Genoa, Genoa, Italy
| | - Hela Znazen
- Department of Physical Education and Sport, College of Education, Taif University, Taif, Saudi Arabia
| | - Nicola Luigi Bragazzi
- Laboratory for Industrial and Applied Mathematics, Department of Mathematics and Statistics, York University, Toronto, ON, Canada
| | - Ciro José Brito
- Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Juiz de Fora, Juiz de Fora, Brazil
| | | | - Daniel Gonçalves
- Department of Fights, Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Bianca Miarka
- Department of Fights, Postgraduate Program in Physical Education, School of Physical Education and Sports, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| |
Collapse
|