A Field-Based Approach to Determine Soft Tissue Injury Risk in Elite Futsal Using Novel Machine Learning Techniques

Ruiz-Pérez, Iñaki; López-Valenciano, Alejandro; Hernández-Sánchez, Sergio; Puerta-Callejón, José M.; Croix, Mark De Ste; Baranda, Pilar Sainz de; Ayala, Francisco

doi:10.3389/fpsyg.2021.610210

Cited by 19 publications

(19 citation statements)

References 73 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several studies have observed that physical and technical performance in sports (sprinting, jumping, agility, kicking, balance) decreases when the technical movement is limited by muscle tightness [25,26] or nonoptimal ROM [24]. Therefore, the success of the athlete requires specific or functional ROM values [24,27] that must be accompanied by optimal values in other sports performance parameters [28].…”

Section: Introductionmentioning

confidence: 99%

Lower Extremity Flexibility Profile in Basketball Players: Gender Differences and Injury Risk Identification

Cejudo

2021

IJERPH

View full text Add to dashboard Cite

Analysis of the flexibility profile of basketball players (BPs) can reveal differences in range of motion (ROM) by gender and also identify those players who are at higher risk for sports injuries. A descriptive observational study was conducted to determine the lower extremity flexibility profile of sixty-four basketball players and gender differences to identify players at higher risk of injury due to limited and asymmetric ROM in one or more movements. Participants: Sixty-four (33 male and 31 female) competitive athletes from the national leagues of the Spanish basketball league system participated in the present study (power of sample size ≥0.99). The eight passive ROM tests of the hip, knee and ankle were assessed using the ROM-SPORT battery. Each player completed a questionnaire on age, basic anthropometric data, dominant extremities, and training and sport-related variables. The lower extremity flexibility profile was established at 15° and 10° hip extension (HE), 39° and 38° ankle dorsiflexion with knee extended (ADF-KE), 40° and 39° ankle dorsiflexion with knee flexed (ADF-KF), 43° and 43° hip abduction (HAB), 75° and 61° hip abduction with the hip flexed (HAB-HF), 78° and 83° hip flexion with the knee extended (HF-KE), 134° and 120° knee flexion (KF), and 145° and 144° hip flexion (HF) by male and female basketball players, respectively. Sex differences in HE, HAB-HF, and KF were observed in BPs (p ≤ 0.01; Hedges’ g ≥ 1.04). Players reported limited ROM in ADF-KF, HE, HAB-HF, HF-KE, and KF; and asymmetric ROM mainly in HE, ADF-KE, KF, ADF-KF, and HF-KE. In conclusion, this study provides gender-specific lower extremity flexibility profile scores in BPs that can help athletic trainers and athletic and conditioning trainers to identify those players who are at higher risk of injury due to abnormal ROM scores.

show abstract

Section: Introductionmentioning

confidence: 99%

Lower Extremity Flexibility Profile in Basketball Players: Gender Differences and Injury Risk Identification

Cejudo

2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…Knee ligament injuries often have some long-lasting residual effects and restrictions in HIR and KF ROMs of the injured limb (anecdotical evidence from the authors’ extensive experience in team sports injury prevention and rehabilitation). As a higher incidence of knee ligament injury has been documented in female futsal players then it may be a plausible argument to justify why they presented two-fold more positive cases of significant bilateral differences in the HIR and KF ROMs ( Ruiz-Pérez et al, 2021 ).…”

Section: Discussionmentioning

confidence: 99%

“…In this sense, the findings reported by the studies that have addressed this issue in intermittent team-sport athletes (mainly football and basketball players) are often contradictory, whereby for the same physical performance measure (e.g., jump height), some studies exhibited negative associations ( García-Pinillos et al, 2015 ; Mills et al, 2015 ) while others did not find a clear influence ( Domínguez-Díez et al, 2021 ) and even better scores were observed in players with poor ROM values ( Rey et al, 2016 ). On the other hand, a growing number of prospective studies have been recently published using contemporary Machine Learning techniques (e.g., supervised learning algorithms) and resampling methods (e.g., fivefold cross validation, leave-one-out, bootstrapping) to build valid and generalizable screening models (area under the receiver operator characteristics [ROC] scores > 0.700) to predict non-contact soft-tissue lower extremities injuries in intermittent team-sport athletes (including futsal players) ( Fousekis et al, 2011 ; López-Valenciano et al, 2018 ; Rossi et al, 2018 ; Ayala et al, 2019 ; Oliver et al, 2020 ; Rommers et al, 2020 ; Ruiz-Pérez et al, 2021 ). Among these studies, those that provided learning algorithms the opportunity to select (or not) measures of ROMs to build prediction models have identified some restricted lower extremities hip (flexion), knee (flexion), and ankle (dorsiflexion) ROMs and bilateral asymmetries as primary predictors of non-contact soft-tissue injury (mainly thigh muscle strains and knee and ankle ligament sprains and tears) in football ( López-Valenciano et al, 2018 ; Ayala et al, 2019 ), handball ( López-Valenciano et al, 2018 ), and futsal players ( Ruiz-Pérez et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, a growing number of prospective studies have been recently published using contemporary Machine Learning techniques (e.g., supervised learning algorithms) and resampling methods (e.g., fivefold cross validation, leave-one-out, bootstrapping) to build valid and generalizable screening models (area under the receiver operator characteristics [ROC] scores > 0.700) to predict non-contact soft-tissue lower extremities injuries in intermittent team-sport athletes (including futsal players) ( Fousekis et al, 2011 ; López-Valenciano et al, 2018 ; Rossi et al, 2018 ; Ayala et al, 2019 ; Oliver et al, 2020 ; Rommers et al, 2020 ; Ruiz-Pérez et al, 2021 ). Among these studies, those that provided learning algorithms the opportunity to select (or not) measures of ROMs to build prediction models have identified some restricted lower extremities hip (flexion), knee (flexion), and ankle (dorsiflexion) ROMs and bilateral asymmetries as primary predictors of non-contact soft-tissue injury (mainly thigh muscle strains and knee and ankle ligament sprains and tears) in football ( López-Valenciano et al, 2018 ; Ayala et al, 2019 ), handball ( López-Valenciano et al, 2018 ), and futsal players ( Ruiz-Pérez et al, 2021 ). Therefore, and with a certain degree of caution, it could be stated that knowing whether (or not) futsal players may develop sport-specific adaptations from training and matches that would cause significant impairments and bilateral differences in lower extremities joints ROMs might help coaches and sport scientists in the decision-making process for injury prevention.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comprehensive Lower Extremities Joints Range of Motion Profile in Futsal Players

et al. 2021

Self Cite

View full text Add to dashboard Cite

The purposes of this study were to describe the lower extremities joints range of motion (ROM) profile using a comprehensive approach in futsal players and to examine potential player position (goalkeepers vs. outfield players), competitive level (first [top] division vs. second division), number of playing years, sex (males vs. females), and bilateral (dominant limb vs. non-dominant limb) differences. A total of 72 male and 67 female elite futsal players from 11 clubs were measured of passive hip (flexion with knee flexed [HFKF] and extended [HFKE], extension [HE], abduction [HA], external [HER], and internal [HIR] rotation), knee (flexion [KF]) and ankle (dorsiflexion with knee flexed [ADFKF] and extended [ADFKE]) ROMs. Bayesian inferences exploring differences between player position, competitive level, sex and limb were made. A Bayesian correlation analysis was conducted to explore the influence of playing years on joints ROMs. The results showed no significant player position or competitive level related differences in any average ROM score. However, statistically significant sex-related differences were documented whereby female players reported higher hip and knee joints ROM average values than their male counterparts. Especially relevant were the proportions of males (72%) and players from teams engaged in the second division (61%) displaying limited HFKE ROMs. Likewise, around 35% of all players showed restricted ADFKF ROMs. In addition, approximately 21, 18, 22, and 25% of the futsal players were identified as having bilateral asymmetries (≥8°) for HA, HIR, HER, and KF ROMs, respectively. Finally, Bayesian correlation analysis did not report any significant association between years of playing futsal and ROM measures (all r values < 0.34). The implications that these restricted HFKE and ADFKF ROMs and bilateral asymmetries in hip (abduction, internal and external rotation) and knee (flexion) ROMs caused by the practice of futsal may have on physical performance and injury risk warrant future research.

show abstract

“…Taking into account the above-reported existing methodologies and their limitations, as well the recent advances in artificial intelligence (AI), the application of machine-learning algorithms appears to be a promising approach for diagnosis and prediction in several fields, such as ACL injury [ 24 , 25 , 26 , 27 , 28 , 29 , 30 ], and, more generally, in biomedicine approaches [ 31 , 32 , 33 ]. Focusing on ACL, diagnosis and prediction represent two correlated analyses that permit us to solve two different issues.…”

Section: Introductionmentioning

confidence: 99%

A Machine-Learning Approach to Measure the Anterior Cruciate Ligament Injury Risk in Female Basketball Players

Taborri

Molinaro

Santospagnuolo

et al. 2021

Sensors

View full text Add to dashboard Cite

Anterior cruciate ligament (ACL) injury represents one of the main disorders affecting players, especially in contact sports. Even though several approaches based on artificial intelligence have been developed to allow the quantification of ACL injury risk, their applicability in training sessions compared with the clinical scale is still an open question. We proposed a machine-learning approach to accomplish this purpose. Thirty-nine female basketball players were enrolled in the study. Leg stability, leg mobility and capability to absorb the load after jump were evaluated through inertial sensors and optoelectronic bars. The risk level of athletes was computed by the Landing Error Score System (LESS). A comparative analysis among nine classifiers was performed by assessing the accuracy, F1-score and goodness. Five out nine examined classifiers reached optimum performance, with the linear support vector machine achieving an accuracy and F1-score of 96 and 95%, respectively. The feature importance was computed, allowing us to promote the ellipse area, parameters related to the load absorption and the leg mobility as the most useful features for the prediction of anterior cruciate ligament injury risk. In addition, the ellipse area showed a strong correlation with the LESS score. The results open the possibility to use such a methodology for predicting ACL injury.

show abstract

A Field-Based Approach to Determine Soft Tissue Injury Risk in Elite Futsal Using Novel Machine Learning Techniques

Cited by 19 publications

References 73 publications

Lower Extremity Flexibility Profile in Basketball Players: Gender Differences and Injury Risk Identification

Lower Extremity Flexibility Profile in Basketball Players: Gender Differences and Injury Risk Identification

Comprehensive Lower Extremities Joints Range of Motion Profile in Futsal Players

A Machine-Learning Approach to Measure the Anterior Cruciate Ligament Injury Risk in Female Basketball Players

Contact Info

Product

Resources

About