Predictive Modeling of Hamstring Strain Injuries in Elite Australian Footballers

Ruddy, Joshua D; Shield, Anthony; Maniar, Nirav; Williams, Morgan; Duhig, Steven; Timmins, Ryan G.; Hickey, Jack; Bourne, Matthew N.; Opar, David A.

doi:10.1249/mss.0000000000001527

Cited by 73 publications

(133 citation statements)

References 28 publications

Supporting

Mentioning

121

Contrasting

Order By: Relevance

“…Perhaps the limited number of risk factors determined by Ruddy et al [32] to build the models may explain the discrepancy found with the predictive scores reported in the current study. Based on the general agreement that the etiology of HSI is multifactorial and that no powerful individual predictors have been found, the combination of information from several modifiable and non-modifiable risk factors might lead to the development of a more robust model with an improved predictive ability.…”

Section: Discussioncontrasting

confidence: 92%

“…The predictive ability of the model developed in the current study to identify athletes at high risk of HSI is higher than the model used in the only study published to date that has used supervised learning algorithms with the aim of predicting the incidence of HSI in Australian footballers [32]. Ruddy et al investigated the ability of some individual (age, history of HSI last season, stature, mass and primary playing position) and strength (eccentric hamstring strength) risk factors to identify Australian footballers at high risk of HSI through the use of some supervised learning algorithms (Naive Bayes, Logistic regression, Random forest, Support vector machine, Neural network) reporting AUC scores lower than 0.6.…”

Section: Discussionmentioning

confidence: 73%

See 1 more Smart Citation

A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms

et al. 2019

View full text Add to dashboard Cite

Hamstring strain injury (HSI) is one of the most prevalent and severe injury in professional soccer. The purpose was to analyze and compare the predictive ability of a range of machine learning techniques to select the best performing injury risk factor model to identify professional soccer players at high risk of HSIs. A total of 96 male professional soccer players underwent a pre-season screening evaluation that included a large number of individual, psychological and neuromuscular measurements. Injury surveillance was prospectively employed to capture all the HSI occurring in the 2013/2014 season. There were 18 HSIs. Injury distribution was 55.6% dominant leg and 44.4% non-dominant leg. The model generated by the SmooteBoostM1 technique with a cost-sensitive ADTree as the base classifier reported the best evaluation criteria (area under the receiver operating characteristic curve score=0.837, true positive rate=77.8%, true negative rate=83.8%) and hence was considered the best for predicting HSI. The prediction model showed moderate to high accuracy for identifying professional soccer players at risk of HSI during pre-season screenings. Therefore, the model developed might help coaches, physical trainers and medical practitioners in the decision-making process for injury prevention.

show abstract

Section: Discussioncontrasting

confidence: 92%

Section: Discussionmentioning

confidence: 73%

A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Over the last few years, the first studies using predictive analysis in sports injury research were conducted [6,9,16,17]. Previous studies have, however, focused solely on the prediction task with-out paying attention to the explainability of the models.…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies have, however, focused solely on the prediction task with-out paying attention to the explainability of the models. In addition, two of the studies also used a very low number of variables (from 3-11), although a larger set might have increased the accuracy [9,16]. The need and potential of predictive machine learning methods in sports injury prediction have been recognized, but more research is needed [12,17].…”

Section: Introductionmentioning

confidence: 99%

New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes

et al. 2020

View full text Add to dashboard Cite

The purpose of this article is to present how predictive machine learning methods can be utilized for detecting sport injury risk factors in a data-driven manner. The approach can be used for finding new hypotheses for risk factors and confirming the predictive power of previously recognized ones. We used three-dimensional motion analysis and physical data from 314 young basketball and floorball players (48.4% males, 15.72±1.79 yr, 173.34±9.14 cm, 64.65±10.4 kg). Both linear (L1-regularized logistic regression) and non-linear methods (random forest) were used to predict moderate and severe knee and ankle injuries (N=57) during three-year follow-up. Results were confirmed with permutation tests and predictive risk factors detected with Wilcoxon signed-rank-test (p<0.01). Random forest suggested twelve consistent injury predictors and logistic regression twenty. Ten of these were suggested in both models; sex, body mass index, hamstring flexibility, knee joint laxity, medial knee displacement, height, ankle plantar flexion at initial contact, leg press one-repetition max, and knee valgus at initial contact. Cross-validated areas under receiver operating characteristic curve were 0.65 (logistic regression) and 0.63 (random forest). The results highlight the difficulty of predicting future injuries, but also show that even with models having relatively low predictive power, certain predictive injury risk factors can be consistently detected.

show abstract

“…The calculation involves the assessment of the current 1-week workload (acute) relative to the chronic workload (typically 2, 3, or 4-weekly average) [5]. Previous research has used a combination of ACWR and/or accumulated weekly TLs to investigate the relationship with injury across a range of sports, including: rugby [14][15][16][17][18][19], Australian rules football (AFL) [20][21][22][23][24][25][26], American football [27,28], handball [29], Gaelic football [30], and soccer [12,[31][32][33][34][35][36][37]. Despite this growing body of research, there have been conflicting findings within the literature.…”

Section: Introductionmentioning

confidence: 99%

Workload and Injury in Professional Soccer Players: Role of Injury Tissue Type and Injury Severity

et al. 2019

View full text Add to dashboard Cite

The purpose of the present study was to examine the influence of workload prior to injury on injury (tissue type and severity) in professional soccer players. Twenty-eight days of retrospective training data prior to non-contact injuries (n=264) were collated from 192 professional soccer players. Each injury tissue type (muscle, tendon and ligament) and severity (days missed) were categorised by medical staff. Training data were recorded using global positioning system (GPS) devices for total distance (TD), high speed distance (HSD,>5.5 m/s−1), and sprint distance (SPR,>7.0 m/s−1). Accumulated 1, 2, 3, 4-weekly loads and acute:chronic workload ratios (ACWR) (coupled, uncoupled and exponentially weighted moving average (EWMA) approaches) were calculated. Workload variables and injury tissue type were compared using a one-way ANOVA. The association between workload variables and injury severity were examined using a bivariate correlation. There were no differences in accumulated weekly loads and ACWR calculations between muscle, ligament, and tendon injuries (P>0.05). Correlations between each workload variable and injury severity highlighted no significant associations (P>0.05). The present findings suggest that the ability of accumulated weekly workload or ACWR methods to differentiate between injury type and injury severity are limited using the present variables.

show abstract

Predictive Modeling of Hamstring Strain Injuries in Elite Australian Footballers

Cited by 73 publications

References 28 publications

A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms

A Preventive Model for Hamstring Injuries in Professional Soccer: Learning Algorithms

New Machine Learning Approach for Detection of Injury Risk Factors in Young Team Sport Athletes

Workload and Injury in Professional Soccer Players: Role of Injury Tissue Type and Injury Severity

Contact Info

Product

Resources

About