Effects of lateral ankle sprain on range of motion, strength and postural balance in competitive basketball players: a cross-sectional study

Machine Learning for Predicting Lower Extremity Muscle Strain in National Basketball Association Athletes

Background

In professional sports, injuries resulting in loss of playing time have serious implications for both the athlete and the organization. Efforts to quantify injury probability utilizing machine learning have been met with renewed interest, and the development of effective models has the potential to supplement the decision-making process of team physicians.

Purpose/Hypothesis

The purpose of this study was to (1) characterize the epidemiology of time-loss lower extremity muscle strains (LEMSs) in the National Basketball Association (NBA) from 1999 to 2019 and (2) determine the validity of a machine-learning model in predicting injury risk. It was hypothesized that time-loss LEMSs would be infrequent in this cohort and that a machine-learning model would outperform conventional methods in the prediction of injury risk.

Study Design

Case-control study; Level of evidence, 3.

Methods

Performance data and rates of the 4 major muscle strain injury types (hamstring, quadriceps, calf, and groin) were compiled from the 1999 to 2019 NBA seasons. Injuries included all publicly reported injuries that resulted in lost playing time. Models to predict the occurrence of a LEMS were generated using random forest, extreme gradient boosting (XGBoost), neural network, support vector machines, elastic net penalized logistic regression, and generalized logistic regression. Performance was compared utilizing discrimination, calibration, decision curve analysis, and the Brier score.

Results

A total of 736 LEMSs resulting in lost playing time occurred among 2103 athletes. Important variables for predicting LEMS included previous number of lower extremity injuries; age; recent history of injuries to the ankle, hamstring, or groin; and recent history of concussion as well as 3-point attempt rate and free throw attempt rate. The XGBoost machine achieved the best performance based on discrimination assessed via internal validation (area under the receiver operating characteristic curve, 0.840), calibration, and decision curve analysis.

Conclusion

Machine learning algorithms such as XGBoost outperformed logistic regression in the prediction of a LEMS that will result in lost time. Several variables increased the risk of LEMS, including a history of various lower extremity injuries, recent concussion, and total number of previous injuries.

Development Status and Influencing Factors of Competitive Basketball Management System under the Background of Deep Learning

Competitive basketball is one of the most popular sports in the world. With the development of China's sports power strategy, the national movement has strengthened the status of basketball in sports. However, China's competitive basketball ranking is not high in the world, and the analysis of the reasons should start with the management system. Therefore, this paper aims to explore the development status and influencing factors of China's competitive basketball management system under the background of deep learning. For the background of deep learning, this paper describes the application of deep learning algorithms in basketball strategy. It adopts the expert interview method for the competitive basketball management system and elaborates in detail on five aspects: target mechanism, competition mechanism, selection mechanism, market mechanism, and incentive mechanism. The experimental results of the article believe that, based on the suggestions of 10 experts, the current Chinese competitive basketball selection mechanism is the most influential factor, with a weight of 16.1%, and the smallest impact is the level of athletes, accounting for 11.4%.

Effects of Soccer Exercise on Balance Ability and Kinesthesia of the Lower Limb Joints in Children Aged 5-6 Years

Age-, height- and weight-matched children were recruited to the experimental group (EG; n = 31) and control group (n = 32). Following a 16-week soccer training program, balance ability and dominant-side lateral knee and ankle kinesthesia changes were tested. Regarding balance ability, the Sway Index, when children stood on a firm or foam surface with their eyes closed in the static balance test, and the dynamic balance test time were 13.5%, 11.6%, and 14.3% lower in the EG than in the control group, respectively. The scores in the left and right directions were 23.7% and 24.2% higher in the EG, respectively. Regarding kinesthesia, the angle of knee extension and ankle metatarsal flexion and dorsiflexion were 13.4%, 20.0%, and 16.8% lower in the EG than in the control group. These results indicate children in the EG had a better performance. After soccer exercise, children aged 5-6 years displayed improved balance in the left and right directions and improved knee extension, ankle plantarflexion, and dorsiflexion kinesthesia.

On-court evaluation of selected key indicators of fitness among elite basketball players

BACKGROUND

The development of the norm of functional variables of fitness as a national database was considered the most important criterion of success in basketball. The current study aims to investigate the performance and skill-related determinants of physical fitness.

METHODS

43 elite basketball players (including 14 Center, 15 Forward and 14 Guard players) participated in this cross-sectional study. The biomechanical parameters of the vertical jump and on-court tests including 20-meter dash, 4×9m agility, 10×20 m shuttle run, repeated side hop, were evaluated. The values of these parameters were compared between different posts using MANOVA and Tukey Post hoc tests in SPSS software (ρ≤0.05).

RESULTS

The norm of physical fitness parameters was obtained by determining the percentage points of 0-10%, 10-25%, 25-50%, 50-75%, 75-90% and 90-100%. Furthermore, peak vertical jump velocity and relative jump power were significantly higher in the guards and forwards compared to the centers (p=0.007 and p=0.027, respectively). The forwards showed significantly higher mean agility, repeated shuttle running and EUR compared to the centers (P<0.001, P=0.020 and P=0.04, respectively). The repeated side jump was significantly lower in the centers by 8% compared to the guards (P=0.01).

CONCLUSIONS

Finally, it was concluded that exercises for guards with a stronger emphasis on agility and explosiveness (plyometric exercises) in combination with aerobic fitness should be considered. Center players, can benefit from resistance training in combination with jumping skills. Speed endurance and anaerobic power in skill related maneuvers are parameters of the players' poor performance in all three positions.