1
|
Dello Iacono A, Datson N, Clubb J, Lacome M, Sullivan A, Shushan T. Data analytics practices and reporting strategies in senior football: insights into athlete health and performance from over 200 practitioners worldwide. SCI MED FOOTBALL 2025:1-16. [PMID: 40084830 DOI: 10.1080/24733938.2025.2476478] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 02/15/2025] [Indexed: 03/16/2025]
Abstract
Despite the rise of data generation in football, the expertise of data analytics within the sport is relatively underdeveloped. To further understand the landscape, a cross-sectional, observational study design was used to survey practitioners in senior, professional, or semi-professional football. Areas of interest included the personnel involved (the 'who'), the data collected (the 'what'), and the analytical techniques employed (the 'how'). A total of 206 practitioners completed an online survey, with representation from all six FIFA confederations. Of the 206 respondents, 86% were male, 13% female, and 1% preferred not to disclose their gender. Respondents were categorised as working in either the performance (73%), data (18%), or medical (9%) department. Heterogeneity was observed in responses across all departments regarding training load metrics, outcome metrics, methodological attributes, and measurement properties. Evidence sources used prior to implementing a new metric varied between departments, with performance (63%) and medical (67%) staff relying on professional industry and/or community, while data staff (57%) utilised more in-house projects. The analytical approach used most frequently was exploratory data analysis (90%), with modelling, forecasting, and predicting the least frequent (54%). Respondents reported using a mix of solutions for data storage, aggregating and analysing, and reporting and visualising data. Spreadsheets were cited as a popular solution for data wrangling and reporting tasks. The findings provide an overview of current data ecosystems and information systems in modern football organisations. These results can be used to improve data analytics service provision in football by helping identify areas for development and progression.
Collapse
Affiliation(s)
- Antonio Dello Iacono
- Sport and Physical Activity Research Institute (SPARI), Division of Sport, Exercise and Health, School of Health and Life Sciences, University of the West of Scotland, Glasgow, UK
| | - Naomi Datson
- Department of Sport and Exercise Sciences, Manchester Metropolitan University Institute of Sport, Manchester, UK
| | - Jo Clubb
- Global Performance Insights Ltd, London, UK
| | - Mathieu Lacome
- Performance & Analytics Department, Parma Calcio 1913, Parma, Italy
- Sport Expertise and Performance Laboratory, French National Institute of Sports (INSEP), Paris, France
| | - Adam Sullivan
- Sport and Human Performance Research Centre, Health Research Institute, University of Limerick, Limerick, Ireland
| | - Tzlil Shushan
- Faculty of Science, Medicine and Health, University of Wollongong, Australia
| |
Collapse
|
2
|
Beato M, Jaward MH, Nassis GP, Figueiredo P, Clemente FM, Krustrup P. An Educational Review on Machine Learning: A SWOT Analysis for Implementing Machine Learning Techniques in Football. Int J Sports Physiol Perform 2025; 20:183-191. [PMID: 39662428 DOI: 10.1123/ijspp.2024-0247] [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: 06/05/2024] [Revised: 09/25/2024] [Accepted: 10/07/2024] [Indexed: 12/13/2024]
Abstract
PURPOSE The abundance of data in football presents both opportunities and challenges for decision making. Consequently, this review has 2 primary objectives: first, to provide practitioners with a concise overview of the characteristics of machine-learning (ML) analysis, and, second, to conduct a strengths, weaknesses, opportunities, and threats (SWOT) analysis regarding the implementation of ML techniques in professional football clubs. This review explains the difference between artificial intelligence and ML and the difference between ML and statistical analysis. Moreover, we summarize and explain the characteristics of ML learning approaches, such as supervised learning, unsupervised learning, and reinforcement learning. Finally, we present an example of a SWOT analysis that suggests some actions to be considered in applying ML techniques by medical and sport science staff working in football. Specifically, 4 dimensions are presented: the use of strengths to create opportunities and make the most of them, the use of strengths to avoid threats, working on weaknesses to take advantage of opportunities, and upgrading weaknesses to avoid threats. CONCLUSION ML analysis can be an invaluable tool for football clubs and sport-science and medical departments due to its ability to analyze vast amounts of data and extract meaningful insights. Moreover, ML can enhance performance by assessing the risk of injury, physiological parameters, and physical fitness, as well as optimizing training, recommending strategies based on opponent analysis, and identifying talent and assessing player suitability.
Collapse
Affiliation(s)
- Marco Beato
- School of Allied Health Sciences, University of Suffolk, Ipswich, United Kingdom
| | - Mohamed Hisham Jaward
- School of School of Technology, Business and Arts, University of Suffolk, Ipswich, United Kingdom
| | - George P Nassis
- Physical Education Department, College of Education, United Arab Emirates University, Al Ain, United Arab Emirates
- Department of Sports Science and Clinical Biomechanics, Sport and Health Sciences Cluster (SHSC), University of Southern Denmark, Odense, Denmark
| | - Pedro Figueiredo
- Physical Education Department, College of Education, United Arab Emirates University, Al Ain, United Arab Emirates
- Research Center in Sports Sciences, Health Sciences and Human Development, CIDESD, Vila Real, Portugal
| | - Filipe Manuel Clemente
- Escola Superior Desporto e Lazer, Instituto Politécnico de Viana do Castelo, Rua Escola Industrial e Comercial de Nun'Álvares, Viana do Castelo, Portugal
- Gdansk University of Physical Education and Sport, Gdańsk, Poland
- Sport Physical Activity and Health Research Innovation and Technology Center (SPRINT), Viana do Castelo, Portugal
| | - Peter Krustrup
- Department of Sports Science and Clinical Biomechanics, Sport and Health Sciences Cluster (SHSC), University of Southern Denmark, Odense, Denmark
- Danish Institute for Advanced Study (DIAS), University of Southern Denmark, Odense, Denmark
| |
Collapse
|
3
|
Wen X, Song F, Yang L, Xu Q. Small-Sided Soccer Games Promote Greater Adaptations on Vertical Jump and Change-of-Direction Deficit and Similar Adaptations in Aerobic Capacity than High-Intensity Interval Training in Females. J Sports Sci Med 2024; 23:445-454. [PMID: 38841638 PMCID: PMC11149063 DOI: 10.52082/jssm.2024.445] [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: 04/01/2024] [Accepted: 05/16/2024] [Indexed: 06/07/2024]
Abstract
The objective of this study was to compare the effectiveness of both small-sided games (SSG) and short interval running-based high-intensity interval training (HIIT) programs over an 8-week period in fostering adaptations in aerobic capacity, change-of-direction abilities, and jumping performances of youth female soccer players. The study involved 48 female youth participants under the age of 19, competing at the regional level, who took part in a randomized controlled trial. Participants were assigned to either the SSG group, the HIIT group, or a control group, which involved regular in-field sessions. Assessments were conducted at baseline and after the 8-week training intervention, measuring aerobic capacity using the 30-15 intermittent fitness test (VIFT), change of direction (COD) using the 5-0-5 test, and jumping performance using the countermovement jump test (CMJ). Time 5 group analysis revealed significant interactions in CMJ (p = 0.005; ηp2= 0.213) and VIFT (p < 0.001; ηp2 = 0.433), although no significant interaction were found in COD deficit (p = 0.246; ηp2 = 0.060). Within-group analysis revealed that SSG significantly improved CMJ (p < 0.001), COD deficit (p < 0.001), and VIFT (p < 0.001). HIIT group also significantly improved CMJ (p = 0.029), COD deficit (p = 0.001), and VIFT (p < 0.001). As conclusion, the study revealed that SSG promoted significantly improvements in VIFT, CMJ and COD deficit, being significantly better than control group, while HIIT was only significantly better than control in VIFT. SSG revealed to be effective approach for favoring key physical attributes of female soccer players, being an interesting and recommended training approach to increase the ecology of the training practice, while favoring physical positive adaptations.
Collapse
Affiliation(s)
| | - FaMing Song
- Civil Aviation Flight University of China, Deyang, Sichuan, China
| | - LiuXi Yang
- School of Athletic Performance, Shanghai University of Sport, Shanghai, China
| | - Qi Xu
- Gdansk University of Physical Education and Sport, Gdańsk, Poland
| |
Collapse
|
4
|
Asimakidis ND, Bishop CJ, Beato M, Mukandi IN, Kelly AL, Weldon A, Turner AN. A survey into the current fitness testing practices of elite male soccer practitioners: from assessment to communicating results. Front Physiol 2024; 15:1376047. [PMID: 38567112 PMCID: PMC10985349 DOI: 10.3389/fphys.2024.1376047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Accepted: 02/29/2024] [Indexed: 04/04/2024] Open
Abstract
This study provides insight into the current fitness testing practices in elite male soccer. One hundred and two practitioners from professional soccer leagues across 24 countries completed an online survey comprising 29 questions, with five sections: a) background information, b) testing selection, c) testing implementation, d) data analysis, and e) data reporting. Frequency analysis was used to evaluate the responses to fixed response questions and thematic analysis was used for open-ended questions to generate clear and distinct themes. Strength (85%) and aerobic capacity (82%) represent the most frequently assessed physical qualities. Scientific literature (80%) is the most influential factor in testing selection and practitioners conduct fitness testing less frequently than their perceived ideal frequency per season (3.6 ± 2 vs. 4.5 ± 2). Time and competitive schedule were the greatest barriers to fitness testing administration. Practitioners mostly used a 'hybrid' approach (45%) to fitness testing, blending 'traditional' (i.e., a day dedicated to testing) and 'integrated' (i.e., testing within regular training sessions) methods. Microsoft Excel is the most used software for data analysis (95%) and visualization (79%). An equal use of the combination of best and mean scores of multiple trials (44%) and the best score (42%) was reported. Comparing a player's test performance with previous scores (89%) was the most common method for interpreting test results. However, only 38% considered measurement error. Digital displays and verbal feedback are the most common data reporting methods, with different data reporting processes for coaches and players. Practitioners can use data and findings from this study to inform their current testing practices and researchers to further identify areas for investigation, with the overarching aim of developing the field of fitness testing in elite male soccer.
Collapse
Affiliation(s)
- Nikolaos D. Asimakidis
- Faculty of Science and Technology, London Sport Institute, Middlesex University, London, United Kingdom
| | - Chris J. Bishop
- Faculty of Science and Technology, London Sport Institute, Middlesex University, London, United Kingdom
| | - Marco Beato
- School of Health and Sports Sciences, University of Suffolk, Ipswich, United Kingdom
| | - Irvin N. Mukandi
- Faculty of Science and Technology, London Sport Institute, Middlesex University, London, United Kingdom
| | - Adam L. Kelly
- Faculty of Health, Education and Life Sciences, Birmingham City University, Birmingham, United Kingdom
| | - Anthony Weldon
- Faculty of Health, Education and Life Sciences, Birmingham City University, Birmingham, United Kingdom
| | - Anthony N. Turner
- Faculty of Science and Technology, London Sport Institute, Middlesex University, London, United Kingdom
| |
Collapse
|
5
|
Beato M, Madsen EE, Clubb J, Emmonds S, Krustrup P. Monitoring Readiness to Train and Perform in Female Football: Current Evidence and Recommendations for Practitioners. Int J Sports Physiol Perform 2024; 19:223-231. [PMID: 38307011 DOI: 10.1123/ijspp.2023-0405] [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: 10/20/2023] [Revised: 12/19/2023] [Accepted: 01/08/2024] [Indexed: 02/04/2024]
Abstract
PURPOSE Monitoring player readiness to train and perform is an important practical concept in football. Despite an abundance of research in this area in the male game, to date, research is limited in female football. The aims of this study were, first, to summarize the current literature on the monitoring of readiness in female football; second, to summarize the current evidence regarding the monitoring of the menstrual cycle and its potential impact on physical preparation and performance in female footballers; and third, to offer practical recommendations based on the current evidence for practitioners working with female football players. CONCLUSIONS Practitioners should include both objective (eg, heart rate and countermovement jump) and subjective measures (eg, athlete-reported outcome measures) in their monitoring practices. This would allow them to have a better picture of female players' readiness. Practitioners should assess the reliability of their monitoring (objective and subjective) tools before adopting them with their players. The use of athlete-reported outcome measures could play a key role in contexts where technology is not available (eg, in semiprofessional and amateur clubs); however, practitioners need to be aware that many single-item athlete-reported outcome measures instruments have not been properly validated. Finally, tracking the menstrual cycle can identify menstrual dysfunction (eg, infrequent or irregular menstruation) that can indicate a state of low energy availability or an underlying gynecological issue, both of which warrant further investigation by medical practitioners.
Collapse
Affiliation(s)
- Marco Beato
- School of Allied Health Sciences, University of Suffolk, Ipswich, United Kingdom
- Department of Neurosciences, Biomedicine and Movement Sciences, University of Verona, Verona, Italy
| | - Esben Elholm Madsen
- Department of Sports Science and Clinical Biomechanics, Sport and Health Sciences Cluster (SHSC), University of Southern Denmark, Odense, Denmark
| | - Jo Clubb
- Global Performance Insights Ltd, London, United Kingdom
| | - Stacey Emmonds
- Carnegie School of Sport, Leeds Beckett University, Leeds, United Kingdom
| | - Peter Krustrup
- Department of Sports Science and Clinical Biomechanics, Sport and Health Sciences Cluster (SHSC), University of Southern Denmark, Odense, Denmark
- Sport and Health Sciences, University of Exeter, Exeter, United Kingdom
- Danish Institute for Advanced Study (DIAS), University of Southern Denmark, Odense, Denmark
| |
Collapse
|