Predicting ACL Injury Using Machine Learning on Data From an Extensive Screening Test Battery of 880 Female Elite Athletes

Influence of Neuromuscular Training Interventions on Jump-Landing Biomechanics and Implications for ACL Injuries in Youth Females: A Systematic Review and Meta-analysis

BACKGROUND

Various exercise interventions are recommended to reduce the risk of anterior cruciate ligament (ACL) injury in females. However, the extent to which these training interventions influence lower-limb landing biomechanics in youth female remains unclear.

OBJECTIVE

This systematic review and meta-analysis aimed to quantitatively summarise the effectiveness of various training interventions on jump-landing biomechanics in youth females.

METHODS

We systematically searched PubMed, SPORTDiscus, EMBASE and Scopus. Articles were included if they: (1) conducted research on uninjured youth females (reported mean age < 18 years) with no restriction on playing level/experience or physical activity level; (2) performed any form of training intervention for ≥ 4 weeks; (3) reported any lower-limb kinematic (flexion/extension, adduction/abduction or internal/external rotation angles) or kinetic (joint moments or vertical ground reaction forces) data during the landing phase of jump-landing tasks, pre- and post-training intervention for both experimental and control groups, using a two- or three-dimensional motion capture system; (4) were randomised- or non-randomised controlled trials. The quality of the randomised controlled trials was assessed using the Risk of Bias tool 2, whereas the Downs and Black checklist was used for assessing the quality of non-randomised controlled trials. A multi-level meta-analytical model was used for conducting the quantitative analysis.

RESULTS

Thirteen studies (7 randomised controlled, 6 non-randomised controlled studies) involving 648 female participants were included in the final analyses. With regards to the overall quality of the included studies, three studies had high risk of bias while ten studies had some concerns. As part of the meta-analysis, we were able to analyse seven kinematic variables and two kinetic variables in aggregate. Compared with controls, the experimental group had significantly increased peak knee flexion angle (g = 0.58, p = 0.05) and reduced knee valgus motion (g =  - 0.86, p = 0.05) post-intervention. The effects on other kinematic and kinetic variables ranged from trivial to moderate and were not significantly altered as a result of various training interventions.

CONCLUSION

The findings from the synthesised literature indicate that training interventions have small to moderate effects on peak knee flexion angle and knee valgus motion during jumping tasks. However, further research employing more consistent study designs and methodologies is required to better understand the changes in jump-landing biomechanics in the youth female population following training interventions.

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.

Application of machine learning in the context of reoperation, outcome and management after ACL reconstruction - A systematic review

INTRODUCTION

Machine learning-based tools are becoming increasingly popular in clinical practice. They offer new possibilities but are also limited in their reliability and accuracy.

OBJECTIVES

The present systematic review updates and discusses the existing literature regarding machine learning algorithm-based tools to predict outcome and management in patients after ACL reconstruction.

METHOD

PubMed was searched for articles containing machine learning algorithms related to anterior cruciate ligament reconstruction and its outcome and management. No additional filters or time constraints were used. All eligible studies were accessed by hand.

RESULTS

After screening of 115 articles, 15 were included. Six studies evaluated predictors for reoperation after ACL surgery. Four studies investigated the clinical outcome prediction after ACL reconstruction including prediction of secondary meniscus tear and secondary knee osteoarthritis. Single topics addressed in patients with ACL reconstruction were costs, opioid use, the need for a femoral nerve block, short term complications, hospital admission, and reduction of the burden to complete the Knee Osteoarthritis and Outcome score questionnaire. Predictive power was very heterogeneous, depending on the specific research question and parameters included.

CONCLUSION

New machine-learning tools offer interesting insights into variables affecting the target outcome and general management of patients with ACL reconstruction. While present machine-learning based prediction models seem to outperform previous existing benchmark regression models, their predictive ability often is still too low to base individual decision making on them. With the rapid progress observed over the last few years, it is conceivable that this might change, however, in the foreseeable future.

A Critical Review of Trunk and Hip Exercise Prescription: Applying Evidence for a Modern Approach

Exercise targeting the trunk and hip (core) musculature is common practice in rehabilitation and performance training. Historical underpinnings of core exercise focus on providing stability to the spine, thus improving the function of the spine and extremities, while instability has been postulated to result in pathology and impaired performance. Mechanistic studies on the topic are often conflicting and indeterminate, suggesting the theoretical underpinnings of targeted core exercise may be over assumed in common practice. The best modes of intervention also remain undefined, with combined methods having potential to optimize outcomes. This includes moving beyond isolated exercise camps and being inclusive of both targeted exercise and progressive multi-joint movements. The purpose of this clinical commentary is to describe the historical mechanisms of the stability-instability continuum and the role of exercise intervention. A spectrum of ideologies related to core exercise are examined, while appreciating positive outcomes of exercise interventions across healthy and pathological populations. Finally, exercise summaries were compiled to improve critical reasoning within current practice and inspire future investigations.

Level of Evidence

5.

Anatomic Risk Factors for Initial and Secondary Noncontact Anterior Cruciate Ligament Injury: A Prospective Cohort Study in 880 Female Elite Handball and Soccer Players

BACKGROUND

Anterior cruciate ligament (ACL) injury is one of the most severe injuries for athletes. It is important to identify risk factors because a better understanding of injury causation can help inform athletes about risk and increase their understanding of and motivation for injury prevention.

PURPOSE

To investigate the relationship between anatomic factors and risk for future noncontact ACL injuries.

STUDY DESIGN

Cohort study; Level of evidence, 2.

METHODS

A total of 870, excluding 9 players with a new contact ACL injury and a player with a new noncontact ACL injury just before the testing, female elite handball and soccer players-86 of whom had a history of ACL injury-underwent measurements of anthropometrics, alignment, joint laxity, and mobility, including leg length, knee alignment, knee anteroposterior laxity, generalized joint hypermobility, genu recurvatum, and hip anteversion. All ACL injuries among the tested players were recorded prospectively. Welch t tests and chi-square tests were used for comparison between the groups (new injury group, which sustained a new ACL injury in the follow-up period, and no new injury group).

RESULTS

An overall 64 new noncontact ACL injuries were registered. No differences were found between athletes with and without a new ACL injury among most of the measured variables. However, static knee valgus was significantly higher in the new injury group than in the no new injury group among all players (mean difference [MD], 0.9°; P = .007), and this tendency was greater in players with a previous ACL injury (MD, 2.1°; P = .002). Players with secondary injury also had a higher degree of knee hyperextension when compared with those previously injured who did not have a secondary injury (MD, 1.6°; P = .007).

CONCLUSION

The anatomic factors that we investigated had a weak or no association with risk for an index noncontact ACL injury. Increased static knee valgus was associated with an increased risk for noncontact ACL injury, in particular for secondary injury. Furthermore, hyperextension of the knee was a risk factor for secondary ACL injury.

Predicting special forces dropout via explainable machine learning

Selecting the right individuals for a sports team, organization, or military unit has a large influence on the achievements of the organization. However, the approaches commonly used for selection are either not reporting predictive performance or not explainable (i.e., black box models). In the present study, we introduce a novel approach to selection research, using various machine learning models. We examined 274 special forces recruits, of whom 196 dropped out, who performed a set of physical and psychological tests. On this data, we compared four machine learning models on their predictive performance, explainability, and stability. We found that a stable rule-based (SIRUS) model was most suitable for classifying dropouts from the special forces selection program. With an averaged area under the curve score of 0.70, this model had good predictive performance, while remaining explainable and stable. Furthermore, we found that both physical and psychological variables were related to dropout. More specifically, a higher score on the 2800 m time, need for connectedness, and skin folds was most strongly associated with dropping out. We discuss how researchers and practitioners can benefit from these insights in sport and performance contexts.

Machine learning in knee injury sequelae detection: Unravelling the role of psychological factors and preventing long-term sequelae

Purpose

This study evaluated the performance of three machine learning (ML) algorithms-decision tree (DT), multilayer perceptron (MLP) and extreme gradient boosting (XGB)-in identifying regular athletes who suffered a knee injury several months to years prior. In addition, the contribution of psychological variables in addition to biomechanical ones in the classification performance of the ML algorithms was assessed, to better identify factors to get back to competitive sport with the lowest possible risk of new knee injury.

Methods

A cohort of 96 athletes, 36 with prior knee injuries, practicing an average of 5.7 ± 2.4 h per week, participated in a horizontal force-velocity test on a ballistic ergometer providing data of force, velocity and power from each lower limb. They also completed a psychological questionnaire, which included components from the Knee Injury and Osteoarthritis Outcome Score (KOOS) and the Sport Anxiety Scale (SAS). The three ML algorithms were trained on a thousand different train-test sets. Also, Shapley values were calculated for each input variable of a data set to highlight its contribution to the prediction from an ML model.

Results

Over a thousand cross-validations, higher area under the curve (AUC) values were obtained when accounted for the psychological attributes (p < 0.001). Also, higher AUC values were obtained from MLP compared to XGB or DT (p < 0.001). XGB exhibited higher AUC values than DT (p < 0.001).

Conclusions

Our results suggested that psychological factors play a more important role in recognition than biomechanical factors, with KOOS and SAS scores ranking high in the list of influential factors. Additionally, the computing stability of MLP could be recommended for classification tasks in the context of knee injuries.

Level of Evidence

Level III.

Validity and reliability of trunk and lower-limb kinematics during squatting, hopping, jumping and side-stepping using OpenCap markerless motion capture application

OpenCap is a web-based markerless motion capture platform that estimates 3D kinematics from videos recorded from at least two iOS devices. This study aimed to determine the concurrent validity and inter-session reliability of OpenCap for measuring trunk and lower-limb kinematics during squatting, hopping, countermovement jumping, and cutting. Nineteen participants (10 males, 9 females; age 27.7 ± 4.1 years) were included. Countermovement jump, single-leg triple vertical hop, single-leg squat, sidestep cutting and side hop tasks were assessed. For validity, OpenCap was compared to a marker-based motion capture system using root-mean-square error. Test-retest reliability of OpenCap was determined using intraclass correlations and minimum detectable change (MDC) from two testing sessions. The squat had the lowest RMSE across joint angles (mean = 7.0°, range = 2.9° to 13.6°). For peak angles, the countermovement jump (jump phase) (ICC = 0.62-0.93) and the squat (ICC = 0.60-0.92) had the best reliability across all joints. For initial contact, the side hop had the best inter-session reliability (ICC = 0.70-0.94) across all joint angles. As such, OpenCap validity and reliability are joint and task specific.

Rehabilitation and Return to Sport After Anterior Cruciate Ligament Reconstruction

Rehabilitation after an anterior cruciate ligament (ACL) reconstruction requires patience, devotion, and discipline. Rehabilitation should be individualized to each patient's specific need and sport. Return to sport is a continuum throughout the rehabilitation, and patients should not return to performance before passing a battery of muscle function tests and patient-reported outcomes, as well as change of direction-specific tests. Return to full participation should be an agreement between the patient, physical therapist, surgeon, and coach. For minimal risk for second ACL injury, patients should continue with maintenance and prevention training even after returning to sport.

Real-time sports injury monitoring system based on the deep learning algorithm

In response to the low real-time performance and accuracy of traditional sports injury monitoring, this article conducts research on a real-time injury monitoring system using the SVM model as an example. Video detection is performed to capture human movements, followed by human joint detection. Polynomial fitting analysis is used to extract joint motion patterns, and the average of training data is calculated as a reference point. The raw data is then normalized to adjust position and direction, and dimensionality reduction is achieved through singular value decomposition to enhance processing efficiency and model training speed. A support vector machine classifier is used to classify and identify the processed data. The experimental section monitors sports injuries and investigates the accuracy of the system's monitoring. Compared to mainstream models such as Random Forest and Naive Bayes, the SVM utilized demonstrates good performance in accuracy, sensitivity, and specificity, reaching 94.2%, 92.5%, and 96.0% respectively.

Performance and healthcare analysis in elite sports teams using artificial intelligence: a scoping review

Introduction

In competitive sports, teams are increasingly relying on advanced systems for improved performance and results. This study reviews the literature on the role of artificial intelligence (AI) in managing these complexities and encouraging a system thinking shift. It found various AI applications, including performance enhancement, healthcare, technical and tactical support, talent identification, game prediction, business growth, and AI testing innovations. The main goal of the study was to assess research supporting performance and healthcare.

Methods

Systematic searches were conducted on databases such as Pubmed, Web of Sciences, and Scopus to find articles using AI to understand or improve sports team performance. Thirty-two studies were selected for review.

Results

The analysis shows that, of the thirty-two articles reviewed, fifteen focused on performance and seventeen on healthcare. Football (Soccer) was the most researched sport, making up 67% of studies. The revised studies comprised 2,823 professional athletes, with a gender split of 65.36% male and 34.64% female. Identified AI and non-AI methods mainly included Tree-based techniques (36%), Ada/XGBoost (19%), Neural Networks (9%), K-Nearest Neighbours (9%), Classical Regression Techniques (9%), and Support Vector Machines (6%).

Conclusions

This study highlights the increasing use of AI in managing sports-related healthcare and performance complexities. These findings aim to assist researchers, practitioners, and policymakers in developing practical applications and exploring future complex systems dynamics.

Injury Prevention Programmes Fail to Change Most Lower Limb Kinematics and Kinetics in Female Team Field and Court Sports: A Systematic Review and Meta-Analysis of Randomised Controlled Trials

BACKGROUND

One mechanism by which exercise interventions may be effective in reducing anterior cruciate ligament (ACL) injury risk is through changes in lower limb biomechanics. Understanding how training programmes affect lower-limb kinematics and kinetics may help refine injury prevention programmes.

OBJECTIVE

The aim of this systematic review and meta-analysis was to assess the effect of injury prevention programmes on kinematics and kinetics during tasks related to ACL injury in female team field and court sports.

DATA SOURCES

Five databases were searched in October 2022.

ELIGIBILITY CRITERIA

Randomised controlled trials assessing the effect of injury prevention programmes compared with usual training/no training on lower limb kinematics and kinetics in female team field and court sports were eligible for review.

RESULTS

Sixteen studies were included. A total of 976 female athletes were included. Most of the studies included interventions with multiple components (12/16). Commonly used components were plyometrics (12/16), strength (8/16), and balance/stability (7/16). Thirteen studies had routine training or sham interventions as the control group and three studies had no training. Very low certainty evidence suggests that injury prevention programmes increase knee flexion angles (mean difference = 3.1° [95% confidence interval 0.8-5.5]); however, very low to low certainty evidence suggests no effect on hip flexion angles/moments, knee flexion moments, hip adduction angles/moments, knee adduction angles/moments, hip internal rotation angles/moments, ankle dorsiflexion angles, and ground reaction forces, compared with usual training/no training.

CONCLUSION

Injury prevention programmes may be effective in increasing knee flexion angles during dynamic landing and cutting tasks but may have no effect on other lower limb biomechanical variables. As such, the benefits of injury prevention programmes may be mediated by factors other than altered biomechanics and/or may happen through other biomechanical measures not included in this review.

Perceptions and beliefs on sports injury prediction as an injury risk reduction strategy: An online survey on elite athletics (track and field) athletes, coaches, and health professionals

OBJECTIVES

To explore perceptions and beliefs of elite athletics (track and field) athletes, coaches, and health professionals, towards the use of injury prediction as an injury risk reduction strategy.

DESIGN

Cross-sectional study.

METHOD

During the 2022 European Athletics Championships in Munich, registered athletes, coaches, and health professionals were asked to complete an online questionnaire on their perceptions and beliefs of injury prediction use as an injury risk reduction strategy. The perceived level of interest, intent to use, help, potential stress (psychological impact) and dissemination were assessed by a score from 0 to 100.

RESULTS

We collected 54 responses from 17 countries. Elite athletics stakeholders expressed a perceived level of interest, intent to use, and help of injury prediction of (mean ± SD) 85 ± 16, 84 ± 16, and 85 ± 15, respectively. The perceived level of potential stress was 41 ± 33 (range from 0 to 100), with an important inter-individual variability in each elite athletics stakeholder's category.

CONCLUSIONS

This was the first study investigating the perceptions and beliefs of elite athletics stakeholders regarding the use of injury prediction as an injury risk reduction strategy. Regardless of the stakeholders, there was a high perceived level of interest, intent to use and help reported in this potential strategy.

Development of an algorithm-based approach using neuromuscular test results to indicate an increased risk for non-contact lower limb injuries in elite football players

Objectives

This retrospective cohort study explored an algorithm-based approach using neuromuscular test results to indicate an increased risk for non-contact lower limb injuries in elite football players.

Methods

Neuromuscular data (eccentric hamstring strength, isometric adduction and abduction strength and countermovement jump) of 77 professional male football players were assessed at the start of the season (baseline) and, respectively, at 4, 3, 2 and 1 weeks before the injury. We included 278 cases (92 injuries; 186 healthy) and applied a subgroup discovery algorithm.

Results

More injuries occurred when between-limb abduction imbalance 3 weeks before injury neared or exceeded baseline values (threshold≥0.97), or adduction muscle strength of the right leg 1 week before injury remained the same or decreased compared with baseline values (threshold≤1.01). Moreover, in 50% of the cases, an injury occurred if abduction strength imbalance before the injury is over 97% of the baseline values and peak landing force in the left leg 4 weeks before the injury is lower than 124% compared with baseline.

Conclusions

This exploratory analysis provides a proof of concept demonstrating that a subgroup discovery algorithm using neuromuscular tests has potential use for injury prevention in football.

Suggested improvements to the 11+ as identified by coaches, players, strength and conditioning staff and medical staff in New Zealand Football

The aim of this study was to investigate the experience with the 11+, attitudes towards injury prevention, and potential improvements to the 11+ and the delivery of injury prevention strategies within football. A qualitative study design was used to investigate the views of four stakeholder groups (players, coaches, strength and conditioning staff and clinicians). Twenty-two adults participated (nine women; median age 35.5 years). Participants were purposively recruited and were based in New Zealand. They represented various levels of football, including different genders, ages and levels of play. Focus group interviews were conducted, which were recorded, transcribed and subject to thematic analysis. Four key themes were identified: understanding of the 11+ injury prevention warm-up, content of an ideal injury prevention programme, structure of the programme and education, adherence and dissemination. The study found that while participants appeared to have good awareness of the existing 11+ programme and an interest in injury prevention, adherence and enthusiasm towards the programme was limited. Participants highlighted a number of elements that may help shape the development of a new injury prevention strategy, including a desire to retain many of the elements of the 11+ and to have a proven programme. Participants wanted greater variety, more football-specific elements and to implement a new strategy throughout a session, rather than being seen as a stand-alone warm-up. Whether the intervention should also include strength-based exercises, or whether this should be promoted outside of a football training session, was less certain.