Search results

Prediction of running injuries from training load: a machine learning approach

The prediction of the running injuries based on selfreported training data on load is difficult. At present, coaches and researchers have no validated system to predict if a runner has an increased risk of injuries. We aim to develop an algorithm to predict the increase of the risk of a runner to sustain an injury. As a first step Self-reported data on training parameters and injuries from high-level runners (duration=37 weeks, n=23, male=16, female=7) were used to identify the most predictive variables for injuries, and train a machine learning tree algorithm to predict an injury. The model was validated by splitting the data in training and a test set. The 10 most important variables were identified from 85 possible variables using the Random Forest algorithm. To predict at an earliest stage, so the runner or the coach is able to intervene, the variables were classified by time to build tree algorithms up to 7 weeks before the occurrence of an injury. By building machine learning algorithms using existing self-reported training data can enable prospective identification of high-level runners who are likely to develop an injury. Only the established prediction model needs to be verified as correct.

Characteristics and risk factors of sport injuries in physical education students

Limited coping skills, young age, and high BMI are risk factors for injuries in contemporary dance

This study investigated potential risk factors (coping, perfectionism, and self-regulation) for substantial injuries in contemporary dance students using a prospective cohort design, as high-quality studies focusing on mental risk factors for dance injuries are lacking. Student characteristics (age, sex, BMI, educational program, and history of injury) and psychological constructs (coping, perfectionism, and self-regulation) were assessed using the Performing artist and Athlete Health Monitor (PAHM), a web-based system. Substantial injuries were measured with the Oslo Sports Trauma Research Center (OSTRC) Questionnaire on Health Problems and recorded on a monthly basis as part of the PAHM system. Univariate and multivariate logistic regression analyses were conducted to test the associations between potential risk factors (i.e., student characteristics and psychological constructs) and substantial injuries. Ninety-nine students were included in the analyses. During the academic year 2016/2017, 48 students (48.5%) reported at least one substantial injury. Of all factors included, coping skills (OR: 0.91; 95% CI: 0.84–0.98), age (OR: 0.67; 95% CI: 0.46–0.98), and BMI (OR: 1.38; 95% CI: 1.05–1.80) were identified as significant risk factors in the multivariate analysis. The model explained 24% of the variance in the substantial injury group. Further prospective research into mental risk factors for dance injuries with larger sample sizes is needed to develop preventive strategies. Yet, dance schools could consider including coping skills training as part of injury prevention programs and, perhaps, providing special attention to younger dancers and those with a higher BMI through transitional programs to assist them in managing the stress they experience throughout their (academic) career.

Jump landing characteristics predicts lower extremity injuries in indoor team sports

The aim of this study is to investigate the predictivevalue of landing stability and technique togain insight into risk factors for ankle and kneeinjuries in indoor team sport players. Seventyfivemale and female basketball, volleyball orkorfball players were screened by measuringlanding stability after a single-leg jump landingand landing technique during a repeated countermovement jump by detailed 3-dimensional kinematicsand kinetics. During the season 11 acuteankle injuries were reported along with 6 acuteand 7 overuse knee injuries by the teams’ physicaltherapist. Logistic regression analysis showedless landing stability in the forward and diagonaljump direction (OR 1.01–1.10, p ≤ 0.05) in playerswho sustained an acute ankle injury. Furthermorelanding technique with a greater ankle dorsiflexionmoment increased the risk for acuteankle injury (OR 2.16, p ≤ 0.05). A smaller kneeflexion moment and greater vertical groundreaction force increased the risk of an overuseknee injury (OR 0.29 and 1.13 respectively,p ≤ 0.05). Less one-legged landing stability andsuboptimal landing technique were shown inplayers sustaining an acute ankle and overuseknee injury compared to healthy players. Determiningboth landing stability and technique mayfurther guide injury prevention programs.

Monitoring perceived stress, recovery and non-traumatic lower extremity injuries in competitive runners

Runners often sustain lower extremity injuries (19-79%) (van Gent et al, 2007). In a theoretical model it has been described that a disturbance in perceived stress and recovery can increase the risk of sustaining an injury (Williams & Andersen, 1998). Therefore, the purpose of this study was to investigate changes in perceived stress and recovery preceding an injury of competitive runners.Methods: Twenty-four competitive runners were monitored over one full training season (46 weeks). Every week, the runners filled an on-line RESTQ-sport (Nederhof et al, 2008). Furthermore, runners and their coaches kept a log with injuries and physical complaints. A non-traumatic injury was defined as any pain, soreness or injury that was not caused by trauma and resulted from training and led to a decrease in training duration or training intensity for at least one week (Jacobsson et al, 2013). Because baseline levels of perception of stress and recovery vary largely between runners, the 19 scales of the RESTQ-Sport were normalized to Z-scores based on the runner’s individual average and standard deviation of the whole season (excl. injured periods). The normalized scores of 1, 2 and 3 weeks before the first sustained injury were compared to 0, which is the average normalized score, by repeated measures ANOVA’s.Results: Twenty-two runners sustained a non-traumatic lower extremity injury. Eight of these runners filled out the RESTQ-Sport all 3 weeks preceding the injury and their data was used for further analysis. The injuries sustained were non-traumatic injuries of the knee, Achilles tendon, ankle, foot and shin. It was shown that 1 week preceding the injury, runners scored lower than the average normalized score on “Success” (Z-score: -0.68±0.62) and 2 weeks preceding the injury runners scored higher than their average on “Fitness/Injuries” (Z-score: 1.04±1.12).Discussion: A decrease in perceived success may be a marker to predict a non-traumatic lower extremity injury. Also an increase in the perception of muscle ache, soreness, pain and vulnerability to injury (“Fitness/Injury”) preceded injuries. Thereby, monitoring changes in individual stress and recovery may help to prevent non-traumatic injuries.

Neurocognitive and neurophysiological functions related with ACL injury

Context: Only 55% of the athletes return to competitive sports after an anterior cruciate ligament (ACL) injury. Athletes younger than 25 years who return to sports have a second injury rate of 23%. There may be a mismatch between rehabilitation contents and the demands an athlete faces after returning to sports. Current return-to-sports (RTS) tests utilize closed and predictable motor skills; however, demands on the field are different. Neurocognitive functions are essential to manage dynamic sport situations and may fluctuate after peripheral injuries. Most RTS and rehabilitation paradigms appear to lack this aspect, which might be linked to increased risk of second injury.Objective: This systematic and scoping review aims to map existing evidence about neurocognitive and neurophysiological functions in athletes, which could be linked to ACL injury in an integrated fashion and bring an extensive perspective to assessment and rehabilitation approaches.Data Sources: PubMed and Cochrane databases were searched to identify relevant studies published between 2005 and 2020 using the keywords ACL, brain, cortical, neuroplasticity, cognitive, cognition, neurocognition, and athletes.Study Selection: Studies investigating either neurocognitive or neurophysiological functions in athletes and linking these to ACL injury regardless of their design and technique were included.Study Design: Systematic review. Level of Evidence: Level 3.Data Extraction: The demographic, temporal, neurological, and behavioral data revealing possible injury-related aspects were extracted and summarized.Results: A total of 16 studies were included in this review. Deficits in different neurocognitive domains and changes in neurophysiological functions could be a predisposing risk factor for, or a consequence caused by, ACL injuries.Conclusion: Clinicians should view ACL injuries not only as a musculoskeletal but also as a neural lesion with neurocognitive and neurophysiological aspects. Rehabilitation and RTS paradigms should consider these changes for assessment and interventions after injury.