Predictive Analytic Techniques to Identify Hidden Relationships between Training Load, Fatigue and Muscle Strains in Young Soccer Players

Machine learning approaches to injury risk prediction in sport: a scoping review with evidence synthesis

OBJECTIVE

This study reviewed the current state of machine learning (ML) research for the prediction of sports-related injuries. It aimed to chart the various approaches used and assess their efficacy, considering factors such as data heterogeneity, model specificity and contextual factors when developing predictive models.

DESIGN

Scoping review.

DATA SOURCES

PubMed, EMBASE, SportDiscus and IEEEXplore.

RESULTS

In total, 1241 studies were identified, 58 full texts were screened, and 38 relevant studies were reviewed and charted. Football (soccer) was the most commonly investigated sport. Area under the curve (AUC) was the most common means of model evaluation; it was reported in 71% of studies. In 60% of studies, tree-based solutions provided the highest statistical predictive performance. Random Forest and Extreme Gradient Boosting (XGBoost) were found to provide the highest performance for injury risk prediction. Logistic regression outperformed ML methods in 4 out of 12 studies. Three studies reported model performance of AUC>0.9, yet the clinical relevance is questionable.

CONCLUSIONS

A variety of different ML models have been applied to the prediction of sports-related injuries. While several studies report strong predictive performance, their clinical utility can be limited, with wide prediction windows or broad definitions of injury. The efficacy of ML is hampered by small datasets and numerous methodological heterogeneities (cohort sizes, definition of injury and dependent variables), which were common across the reviewed studies.

Artificial intelligence applications in the football codes: A systematic review

Artificial Intelligence (AI) is increasingly being adopted across many domains such as transport, healthcare, defence and sport, with football codes no exception. Though there is a range of potential benefits of AI, concern has also been expressed regarding potential risks. An important first step in ensuring that AI applications in football are usable, beneficial, safe and ethical is to understand the current range of applications, the AI models adopted and their proposed functions. This systematic review aimed to identify different applications of AI across football codes to synthesise current knowledge and determine whether potential risks are being considered. The systematic review included 190 peer-reviewed articles. Nine areas of application were found ranging from athlete evaluation and event detection to match outcome prediction and injury detection and prediction. In total, 27 different AI models were identified, with artificial neural networks the most frequently applied. Five AI assessment metrics were identified including specificity, recall, precision, accuracy and F1-score. Four potential risks were identified, concerning data security, usability, data biases and inappropriate athlete load management. It is concluded that, though a wide range of AI applications currently exist, further work is required to develop AI for football and identify and manage potential risks.

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

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.

Data-Driven Approach for Upper Limb Fatigue Estimation Based on Wearable Sensors

Muscle fatigue is defined as a reduced ability to maintain maximal strength during voluntary contraction. It is associated with musculoskeletal disorders that affect workers performing repetitive activities, affecting their performance and well-being. Although electromyography remains the gold standard for measuring muscle fatigue, its limitations in long-term work motivate the use of wearable devices. This article proposes a computational model for estimating muscle fatigue using wearable and non-invasive devices, such as Optical Fiber Sensors (OFSs) and Inertial Measurement Units (IMUs) along the subjective Borg scale. Electromyography (EMG) sensors are used to observe their importance in estimating muscle fatigue and comparing performance in different sensor combinations. This study involves 30 subjects performing a repetitive lifting activity with their dominant arm until reaching muscle fatigue. Muscle activity, elbow angles, and angular and linear velocities, among others, are measured to extract multiple features. Different machine learning algorithms obtain a model that estimates three fatigue states (low, moderate and high). Results showed that between the machine learning classifiers, the LightGBM presented an accuracy of 96.2% in the classification task using all of the sensors with 33 features and 95.4% using only OFS and IMU sensors with 13 features. This demonstrates that elbow angles, wrist velocities, acceleration variations, and compensatory neck movements are essential for estimating muscle fatigue. In conclusion, the resulting model can be used to estimate fatigue during heavy lifting in work environments, having the potential to monitor and prevent muscle fatigue during long working shifts.

Effects of Playing Position and Contextual Factors on Internal Match Loads, Post-Match Recovery and Well-Being Responses of Elite Male Water Polo Players

This study aimed to investigate the effects of playing position and contextual factors (match outcome, final score difference, match location, travel duration, number of scored and conceded goals) on the internal match load, players' perceived recovery and players' well-being. The session-RPE (s-RPE), Perceived Recovery Scale (PRS) and Hooper Index (HI) of 17 male elite water polo players were monitored during all matches (regular season and play-out) of the 2021/22 Italian Serie A1 championship. Three separate, mixed linear models for repeated measures showed significant main effects: drawn compared to won matches led to higher s-RPE values (mean ± SE = 277 ± 17.6 vs. 237.3 ± 20.6), while longer travel duration (estimate = -0.148) and goals scored (estimate = -3.598) led to lower s-RPE values; balanced compared to unbalanced matches led to higher PRS values (mean ± SE = 6.8 ± 0.3 vs. 5.1 ± 0.4), while playing time (estimate = -0.041) and goals scored (estimate = -0.180) led to lower PRS values; higher scores of the HI were registered for regular season compared to the play-out (mean ± SE = 15.6 ± 0.9 vs. 13.5 ± 0.8). This study marks the importance of ecological and non-invasive monitoring tools to assess internal match load, recovery and the well-being of elite water polo players.

The Effect of Spinal Asymmetries on Physical Fitness Parameters in Young Elite Soccer Players

The purpose of the study was to examine the effect of spinal asymmetries on specific physical fitness parameters in young elite soccer players. Fifty male soccer players, all members of the under 17 (U17) and 15 (U15) National teams of Cyprus, were initially evaluated for thoracic kyphosis, lumbar lordosis and scoliosis asymmetries. Based on the spinal asymmetries’ initial evaluation, soccer players were categorized into the asymmetry group (AG) and normal group (NG) per spinal asymmetry. Hamstring and lower-back flexibility, countermovement jump (CMJ) and lower body isokinetic maximum force were evaluated between AG and NG. CMJ with arm swing was lower in kyphotic posture AG compared with the NG (AG: 41.70 ± 3.59 cm, NG: 44.40 ± 4.34 cm; p = 0.028). Single leg CMJ was lower in both legs in scoliotic posture AG compared with the NG (right: AG: 17.42 ± 1.86 cm, NG: 19.16 ± 2.42 cm, p = 0.008, left: AG: 17.54 ± 1.33 cm, NG: 19.97 ± 2.91 cm; p = 0.002). Sit-and-reach flexibility was lower in scoliotic posture AG (AG: 20.44 ± 5.76 cm, NG: 24.82 ± 6.83 cm; p = 0.024) and higher in lordotic posture AG (AG: 25.95 ± 6.59 cm, NG: 21.73 ± 6.45 cm; p = 0.04) both compared with the NG. No significant difference was found for quadriceps and hamstrings concentric peak torque between the AG and NG (p > 0.05). The current study revealed that kyphotic and scoliotic posture asymmetries deteriorate neuromuscular explosiveness performance and diminish lower limbs’ flexibility in young International-level soccer players.

A Systematic Review of the Relationship between Workload and Injury Risk of Professional Male Soccer Players

The number of studies on the relationship between training and competition load and injury has increased exponentially in recent years, and it is also widely studied by researchers in the field of professional soccer. In order to provide practical guidance for workload management and injury prevention in professional athletes, this study provides a review of the literature on the effect of load on injury risk, injury prediction, and interpretation mechanisms. The results of the research show that: (1) It appears that short-term fixture congestion may increase the match injury incidence, while long-term fixture congestion may have no effect on both the overall injury incidence and the match injury incidence. (2) It is impossible to determine conclusively whether any global positioning system (GPS)-derived metrics (total distance, high-speed running distance, and acceleration) are associated with an increased risk of injury. (3) The acute:chronic workload ratio (ACWR) of the session rating of perceived exertion (s-RPE) may be significantly associated with the risk of non-contact injuries, but an ACWR threshold with a minimum risk of injury could not be obtained. (4) Based on the workload and fatigue recovery factors, artificial intelligence technology may possess good predictive power regarding injury risk.

Forecasting football injuries by combining screening, monitoring and machine learning

Identifying players or circumstances associated with an increased risk of injury is fundamental for successful risk management in football. So far, time-constant and volatile risk factors are generally considered separately in either a screening (constant) or a monitoring (volatile) approach each resulting in a restricted set of explanatory variables. Consequently, improvements in predictive accuracy may be expected when screening and monitoring data are combined, especially when analysed with current machine learning (ML) techniques. This trial was designed as a prospective observational cohort study aiming to forecast non-contact time-loss injuries in male professional football (soccer). Injuries were registered according to the Fuller consensus. Gradient boosting with ROSE upsampling within a leave-one-out cross-validation was used for data analysis. The hierarchical data structure was considered throughout. Different splits of the original dataset were used to probe the robustness of results. Data of 88 players from 4 teams and 51 injuries could be analysed. The cross-validated performance of the gradient boosted model (ROC area under the curve 0.61) was promising and higher compared to models without integration of screening data. Importantly, holdout test set performance was similar (ROC area under the curve 0.62) indicating prospect of generalizability to new cases. However, the variation of predictive accuracy and feature importance with different splits of the original dataset reflects the relatively low number of events. It is concluded that ML-based injury forecasting based on the integration of screening and monitoring data is promising. However, external prospective verification and continued model development are required.