Sports Classification Research Articles

Are some sports riskier than others? An investigation into child athlete experiences of interpersonal violence in relation to sport type and gender

Interpersonal violence in sport has serious consequences for athletes, sports organisations and society at large. Despite recent advances in safeguarding sport participants from interpersonal violence, empirical evidence regarding its prevalence and risk factors across different sports remains scarce. In this study, we investigated differences in the prevalence of interpersonal violence among a convenience sample of 9989 adults from six European countries who participated in organised sport before age 18. Utilising binary logistic regression analyses and CHAID regression tree analyses, we examined variations in reported experiences of neglect, psychological, physical, non-contact sexual and contact sexual forms of interpersonal violence based on gender and three sport classifications: type of sport (individual vs. team), sports attire (non-revealing vs. body-fitting/revealing) and weight-sensitivity (less weight-sensitive vs. weight-sensitive sports). Men participating in team sports reported significantly higher levels of victimisation across all types of interpersonal violence. Women in sports with non-revealing attire and men in less weight-sensitive sports also reported higher prevalence rates. The study underscores the need for a nuanced understanding of interpersonal violence characteristics and dynamics across different sports. Insights into the factors influencing victimisation enable tailored prevention and response strategies to be developed to better address the needs of athletes and sport organisations.

Initial Symptom Severity and Recovery of Sport-Related Concussion in Team Versus Individual Sport Athletes.

Recovery after sport-related concussion is variable, and potential differences between team vs individual sport athletes are not fully understood. In a cohort of athletes with concussions, we sought to compare these groups across (1) symptom severity score, (2) individual symptom cluster scores, and (3) recovery metrics. A retrospective, cohort study of 13 to 23-year-old athletes treated at a regional sport concussion center between November 2017 and April 2022 was conducted. Athletes were categorized into team vs individual sport athletes, with additional classification of individual sports based on strong vs minimal team elements (ie, the degree of interdependence displayed by athletes). The primary outcomes were symptom severity score, measured by either the Sport Concussion Assessment Tool-5th Edition or the Immediate Post-Concussion Assessment and Cognitive Testing, and physical, cognitive, emotional, and sleep symptom cluster scores. Secondary outcomes were recovery metrics, including time to return-to-learn, symptom resolution, and return-to-play. Of the 1051 athletes, 954 (90.8%) were in team sports and 97 (9.2%) in individual sports. In multivariable linear regression, individual sport athletes had higher emotional symptom severity compared with team sport athletes (β = 0.09 [0.01, 0.17], P = .034) when adjusting for sex, attention-deficit/hyperactivity disorder, psychological disorders, time to clinic, on-field evaluation, and Immediate Post-Concussion Assessment and Cognitive Testing vs Sport Concussion Assessment Tool-5th Edition scale. There were no significant differences in return-to-learn (P = .104), symptom resolution (P = .941), or return-to-play (P = .279) on univariate regressions. In the current single-center, pilot study of athletes with a sport-related concussion, individual sport athletes exhibited more emotional symptoms than team sport athletes. These preliminary data lend early support that individual sport athletes may be more at risk of emotional symptoms than team sport athletes after a sport-related concussion. Clinicians may use these findings to identify athletes who may be particularly vulnerable to emotional symptoms.

Research on sports image classification method based on SE-RES-CNN model

As computer image processing and digital technologies advance, creating an efficient method for classifying sports images is crucial for the rapid retrieval and management of large image datasets. Traditional manual methods for classifying sports images are impractical for large-scale data and often inaccurate when distinguishing similar images. This paper introduces an SE module that adaptively adjusts the weights of input feature mapping channels, and a Res module that excels in deep feature extraction, preventing gradient vanishing, multi-scale processing, and enhancing generalization in image recognition. Through extensive experimentation on network structure adjustments, the SE-RES-CNN neural network model is applied to sports image classification. The model is trained on a sports image classification dataset from Kaggle, alongside VGG-16 and ResNet50 models. Training results show that the proposed SE-RES-CNN model improves classification accuracy by approximately 5% compared to VGG-16 and ResNet50 models. Testing revealed that the SE-RES-CNN model classifies 100 out of 500 sports images in 6 s, achieving an accuracy rate of up to 98% and a single prediction time of 0.012 s. This validates the model's accuracy and effectiveness, significantly enhancing sports image retrieval and classification efficiency. This validates the model's accuracy and effectiveness, significantly enhancing sports image retrieval and classification efficiency.

A critical examination of sport discipline typology: identifying inherent limitations and deficiencies in contemporary classification systems.

Exercise scientists (especially in the field of biomolecular research) frequently classify athletic cohorts into categories such as endurance, strength, or mixed, and create a practical framework for studying diverse athletic populations between seemingly similar groups. It is crucial to recognize the limitations and complexities of these classifications, as they may oversimplify the multidimensional characteristics of each sport. If so, the validity of studies dealing with such approaches may become compromised and the comparability across different studies challenging or impossible. This perspective critically examines and highlights the issues associated with current sports typologies, critiques existing sports classification systems, and emphasizes the imperative for a universally accepted classification model to enhance the quality of biomolecular research of sports in the future.

Athletes' Perspectives of the Classification System in Para Alpine Skiing for Those With Visual Impairment.

This study explored the classification experiences and views of Para Alpine skiers with visual impairment. Data from 11 interviews were analyzed using reflexive thematic analysis to generate three themes: Suitability-The skiers questioned the suitability of the visual measurements, testing environment, and the information they received regarding classification; Exclusivity-Skiers felt certain aspects of the system remain exclusive due to the restrictions of sport classes and lack of the athlete voice; and (Dis)trust-Skiers felt distrust in those implementing the system and in other athletes due to intentional misrepresentation. Speculation surrounding this resulted in the skiers' feeling doubt in their own classification. While there is not a "one size fits all" approach to classification, understanding skiers' experiences can be a vital first step and will help to guide future research into the evolution of this sport's classification.

MODERN STATE OF SPORTS AND RECREATIONAL TOURISM

The article explores the concept of sports and recreational tourism. It defines the basic characteristics and goals of sports and recreational tourism, analyzes its varieties and functions. Various approaches to defining this concept are examined, and typical features and peculiarities are identified. The classification of sports and recreational tourism contributes to a more in-depth study of its modifications, determining key development trends and characteristics, and facilitates the systematization of knowledge for a deeper understanding of the essence of sports and recreational tourism. Health and sports activities are one of the most accessible and widespread forms of recreation. Its role will continue to grow, considering the objectively determined decrease in physical mobility and activity among people due to the nature of the development of modern society. Sports tourism is a component of modern tourism, the most active and dynamic part of tourist activity based on communal principles. Sports tourism is also a type of sport that includes various active tourist activities, sports hikes of all difficulty levels, championships, and competitions in all types of sports tourism (hiking, skiing, mountain, water, cycling, motorcycle, car, spelunking, and sailing), complex events, and expeditions. This type of tourism not only offers the opportunity to travel but also involves engaging in sports, preserving and improving health while deriving pleasure from active recreation. One of the key characteristics of sports and recreational tourism is the variety of activities that can be involved in this type of travel. This may include cycling tourism, hiking, water sports, mountaineering, skiing resorts, kayaking or canoeing, snowboarding, and many other activities. This variety provides the opportunity to choose sports activities according to physical abilities and personal preferences. The second key component of sports and recreational tourism is its promotion of a healthy lifestyle. The activities offered by this type of tourism contribute to physical fitness improvement, health preservation, and overall well-being. It allows people not only to relax but also to maintain and improve their health, deriving satisfaction from activity and new travel experiences. Moreover, sports and recreational tourism contribute to understanding among people and create a favourable atmosphere for interaction and joint activities. Travellers who choose this type of journey often travel in groups, where they interact, support each other, and collectively achieve sports goals. This also contributes to the formation of new friendships and team relationships. With the development of infrastructure, sports and recreational tourism become more accessible and popular for the public. This type of travel offers the opportunity to combine the pleasure of relaxation and activity, preserving and improving health, and provides unforgettable travel experiences. Key words: tourism, sports and recreational tourism, sports tourism, functions of sports and recreational tourism, types of sports and recreational tourism.

Sverdlovsk esports student league - reserve of the Sverdlovsk region national team

Relevance. The first official competitions of the Sverdlovsk region in computer sports were the 2019 Sverdlovsk Region Cup in computer sports. Teams consisting of 5 people were allowed to participate in competitions in the Combat Arena discipline, in the form of the DOTA2 program. 8 teams took part in the competition, and 3 teams in full were the teams of Yekaterinburg universities. This is a very important point, since without the participation of university teams, athletes of the Sverdlovsk region would not be able to meet the discharge standards, since in accordance with the requirements of the Unified All-Russian Sports Classification (hereinafter EVSK) for the sport of computer sports, at least 6 teams are required to perform discharge standards.The purpose of the study was to quantify such a trend of mass sports as student computer sports. Methods and organization of the study: as a result of the analysis of data on the composition of the teams participating in the Sverdlovsk Region Cup (hereinafter CSR) in computer sports in 2019-2023 according to the combat arena discipline, in the form of the DOTA2 program and the identification among them of the national teams of educational institutions participating in the Sverdlovsk esports Student League, as well as the data are compared with the number of participating teams SCSL in the specified program type.The results of the study and their discussion. Low motivation of athletes remains among the main problems in student computer sports, as well as high-achievement computer sports. Not all gamers are esports players. By participating in competitions, they try to become them, but the goal of a gamer is to enjoy video games. And the main motivation of a gamer when entering computer sports is the desire to earn income in the form of cash prizes.Conclusions. To increase motivation, the following solutions are possible: Divide the WKSL into two parallel tournaments for university and university students. To supplement the current EVSC in computer sports with the possibility of fulfilling the discharge standards for the winners of regional physical education events.

English

The social changes related to gender identity that have been taking place in recent years have a notable and growing impact on sports practice. The incorporation of people with sex reassignment, transsexuals, and intersex (different sexual development) in sports competition raises issues that until now were very rare and relevant but that are currently causing doubts, debate, and controversy. The Spanish Society of Sports Medicine (SEMED), aware that this issue has important repercussions, both on the professional practice of physicians who care for athletes, and on the health of the athletes themselves, understands that it is necessary to deepen the knowledge of the sports practice of people with sex reassignment, transsexuals and intersexuality and considers it appropriate to make an official position on this issue. This work addresses sex reassignment, transsexuality, and intersexuality, shedding light on their definitions, their prevalence, and the differences in sports performance between men and women. He also considers it important to make a reference to the forms of classification in sport, as well as the role of androgens (testosterone and dihydrotestosterone, DHT) in sport. It analyzes the sports participation of people with sex reassignment, transsexuals and intersexuals since the emergence of the Caster Semenya case to end with the positioning of the Spanish Society of Sports Medicine and the recommendation on actions proposed to the sports authorities on addressing the sports participation of people with sex reassignment, transsexuals, and intersex from the perspective of the functional, injury and incentive consequences of women's sports practice.

Implementation of Sports Classification and Person Recognition System

The Implementation of Sports Classification and Persons Recognition System addresses the growing demand for automated and intelligent solutions in the sports industry. This project focuses on the development and deployment of a robust system that combines sports classification and person recognition to enhance the overall experience for both athletes and spectators. Automatically categorize and classify different sports activities. The system utilizes real time video feeds or recorded footage to identify and distinguish various sports such as soccer, basketball, tennis, and more. This involves implementing facial recognition, body posture analysis, and other features to accurately throughout the sporting activities, athlete performance analysis, enables better coaching strategies, and enhances security measures in sports venues. Keywords: Sports Classification, Person Recognition

Peculiarities of sports classification for athletes with mental and physical disabilities

The article discusses the question of determining whether athletes with mental and physical disabilities belong to a certain classification group which determines the athlete's right to participate in the Paralympic Games. It has been established that sports classification is a necessary condition for the participation in competitions of athletes sanctioned by the International Paralympic Committee. It has been proven that in Paralympic sports the result depends not only on the abilities of the athlete, the professionalism of the coach, material and technical support, but also on the preserved movement capabilities of the disabled person. The purpose of the article is to study the peculiarities of the classification of athletes with mental and physical disabilities for participation in the Paralympic Games and Special Olympics. The status of an athlete with mental and physical disabilities in a certain classification group ІІ1, ІІ2, ІІ3 indicates whether the athlete at the national level must undergo an assessment in the future or whether it is permanent. The status of an athlete in a certain classification group II1, II2, II3 at the national level which is determined by a psychologist/classifier after the evaluation procedure, will be one of the following: 1) new: the athlete is given the status of “new” until he visits the first psychological assessment procedure held by a psychologist/ classifier;
 2) under observation (review): if the psychologist/classifier believes that additional psychological assessment procedures are needed, or all primary documents were not provided or the athlete demonstrated a lack of cooperation during the classification; 3) permanent: a) in the case of already passed and approved international classification; b) in the event that the classification group (psychologist/classifier, doctor) is satisfied that the specified impairment of intelligence or other deviations of adaptive behavior, additional impairments of the athlete, his ability to perform certain tasks and actions fundamental for athletics, swimming and table tennis remain stable; 4) inadequate: a) in case of non-compliance with the specified criteria of any classification group; b) in the case of diagnosed atlantoaxial instability in athletes with Down syndrome.

University Club Sport Student-Athlete Concussion Profiles Differ by Sport and Sex

Athletes’ history of concussions is an important indicator of risk potential in organized sports. The purpose of this project was to explore differences by sport classification (contact vs. noncontact) and sex on concussion history among university club sports participants. This was a cross-sectional quality improvement study ( n = 593). The outcomes were self-reported answers to: (1) How many times have you been diagnosed with a concussion? and (2) How many times have you had your “bell rung”/“dinged”? Multivariable logistic regression models examined the association of contact club sport participation and sex on the history of concussion and prior experience of having their bell rung. Models were adjusted for age, race, participation in multiple sports, and years of participation in sports, and years in college. When compared to those in non-contact club sports, the adjusted odds of reporting ever having a concussion were 2.29 times higher for those participating in contact club sports (OR = 2.29; 95% CI: 1.49, 3.53). In the model for having a bell rung, those participating in a contact sport had 1.90 times greater odds of reporting having their bell rung in the past compared to those in noncontact sports (OR = 1.90; 95% CI: 1.25, 2.88). Whereas males and females did not differ in their self-reported concussion history, females had significantly lower odds of reporting having their bell rung in the past than males (OR = 0.46; 95% CI: 0.30, 0.69). Female athletes have a higher reporting of concussion incidence than that of male athletes. The use of terminology and variance in slang versus medical terms has the potential to affect reporting outcomes. Reporting of concussion incidents has the potential to be influenced by the nature of sport culture and sport participation in contact versus noncontact sports. Club sport athletes could benefit from tailored education related to concussions based on these results.

Wearable electronic devices in parasports: A focused review on para athlete classification.

Wearable electronic devices are being used to evaluate movement patterns, track workload, prevent injuries, and optimize performance in athletes. Para athletes have unique characteristics to consider separately from the general population. One such difference in competitive parasports includes consideration of athlete classification systems. These sport-specific classification systems consider athletes' eligible medical conditions that lead to permanent physical, visual, and/or intellectual impairments and objectively evaluate the impact of their impairments on sport functions. Para athletes are assigned sport classes and compete with athletes of similar functional levels. This promotes equitable opportunities to compete while minimizing the effect their impairment has on their sport performance. With recent reports of misrepresentation or incorrect and unfair classification providing unfair advantages to some athletes, parasports classification has been controversial. Having an objective, evidence-based, and fair classification system in parasports is critical to maintain the integrity of parasports competition. Wearable electronic devices have potential to provide more objective analysis of movement patterns in para athletes to assist in sport classification. This review identifies and analyzes the available literature on wearable electronic technology and its role in parasports classification. A comprehensive PubMed and Google Scholar search identified six articles included in this review. These studies used inertial sensors, motion capture systems, or surface electromyography in wheelchair basketball, rugby, tennis, sit skiing, and boccia. This review identifies the potential value of wearable electronic devices to assist in parasports classification. Additional studies are needed to create standardized protocols for each sport and sensor type.

Classification of Transfers in Sports

The increase in the number of conflict situations that arise when athletes and coaches are transfered to other employers is due, among other things, to the lack of a unified theoretical approach to the definition of this concept and, therefore, the delimitation of sports transfers from related phenomena. At present, a relatively small number of scientific works are devoted to the classification of sports transfer, which seems to be a significant gap in the theoretical understanding of sports transfers that needs to be filled. The paper proposes a classification of sports transfers depending on the type of jurisdiction to which the subjects of the sports transfer belong (national and international); the period of its implementation (permanent and temporary; its subjects (transfers of athletes and coaches). Some types can be distinguished between from the point of view of forms of labor regulation sports transfer: a) transitions (transfers) based on termination of the employment contract concluded with the previous employer in the manner established by paragraphs 3, 4 of Art. 77 of the Labor Code of the Russian Federation, Article 80 of the Labor Code of the Russian Federation, and on concluding a new employment contract with a new employer; b) transitions (transfers) involving the termination of an employment contract by agreement of the parties (clause 1 of Article 77 of the Labor Code of the Russian Federation) with the subsequent conclusion of an employment contract with another employer; c) transitions (transfers) in the order of transferring an employee to work for another employer (clause 5 of Article 77 of the Labor Code of the Russian Federation); d) transitions (transfers) in the order of temporary transfer of an athlete to another employer in the manner established by Article 348.4 of the Labor Code of the Russian Federation. The absence of reasons for identifying a sports transfer with a change of sports citizenship is substantiated.

Sports Classification and Athletes With Intellectual Disabilities: Measuring Health Status Using a Questionnaire Based on the International Classification of Functioning, Disability and Health.

Most people with intellectual disabilities have comorbid health conditions, which will impact optimization of sporting performance. Classification is used in Paralympic events to ensure that those with similar levels of functional ability compete fairly against each other. An evidence-based approach needs to be developed for athletes with intellectual disabilities to be classified in relation to their overall functional capacity into competition groups of similar ability. This research builds on previous work using the taxonomy of The International Classification of Functioning, Disability and Health (ICF) to group athletes with intellectual disabilities into comparable competition groups as an approach to Paralympic classification. Three groups of athletes-Virtus, Special Olympics, and Down syndrome-are compared using the ICF questionnaire indicating functional health status in relation to sporting performance. The questionnaire was found to discriminate between athletes with Down syndrome and other athletes, and an approach to using a cutoff score to develop competition classes is explored.

A machine learning approach for the classification of sports based on a coaches’ perspective of environmental, individual and task requirements: A sports profile analysis

ABSTRACT Well-designed talent programmes in sports with a focus on talent identification, orientation, development, and transfer support the engagement of young individuals and the pursuit of elite performance. To facilitate these processes, an analysis of task, environmental and individual characteristics per sport is much needed. The aims of this study were to 1) analyse whether unique profiles per sport could be established by generic characteristics and 2) to discuss similarities and differences for the potential application in talent development and transfer. By means of a validated survey, 1247 coaches from 34 sports ranked 18 characteristics on importance to their sports (0 = not important − 10 = very important). To discriminate the responses per sport a Discriminant Analysis (DA) was carried out. To refine the DA-classification, Uniform Manifold Approximation and Projection (UMAP) with CatBoost classifier was performed. To test the performance of the CatBoost classifier-algorithm, a confusion-matrix was generated. The cross-validated DA showed that 70.2% of the coaches were correctly classified to their sport. The UMAP/CatBoost technique revealed 75.1% accuracy with correctly predicted responses per sport ranging from 18.2% (sailing) to 98.2% (soccer). With varying precision, the algorithm was able to differentiate sports by importance of its characteristics indicating similarities and differences per sport.

Ahletic adaptations of thin-walled structures of the heart: a cross-sectional echocardiographic study of elite athletes

Abstract Background Cardiac adaptation to exercise is characterized by eccentric remodeling due to increased volume load[1], it is however unclear how systolic function is affected in all chambers. Endurance sports is a known risk factor for later onset atrial fibrillation[2]. Moreover, recent studies of the acute effects of exercise have reported reversable right ventricular (RV) dilation and reduced function in triathletes resembling ARVC, while the left ventricle (LV) was unchanged[3]. These findings have raised concern regarding the long-term adaptations in the thin-walled chambers of the heart. Purpose The aim of the current study was to assess atrial and RV remodeling by echocardiography in elite athletes. Methods A cross-sectional study of 482 healthy active elite athletes from 30 sports was investigated with a standard resting echocardiogram. Using the Mitchell sports classification, athletes were grouped according to levels of endurance demands for their sport into low (Mitchel 1A), intermediate (Mitchel 1B-C, 2A-B-C), and high endurance demand (3A-B-C). All measures were adjusted for body surface area (BSA), sex, and age. Analysis of Covariance models was used to allow for adjustments for categorical variables and continuous covariates. Results Left atrial minimum volume/BSA (LAminV/BSA) was higher in athletes who performed high endurance demanding sports than in the intermediate and low groups (High: 11.3 ml/m2, confidence interval (CI): 10.1-12.5; Int: 8.9 ml/m2, CI: 8.3-9.5, p<0.01; Low: 7.7 ml/m2, CI: 5.8-9.7, p<0.01). We found no difference between the low and intermediate groups. RV systolic area/BSA (RVsysA/BSA) was significantly higher in the high and intermediate groups compared to the low group (high 9.5 ml/m2, CI: 9.1-9.8, p=0,014; Int 9.3 ml/m2, CI: 9.1-9.5, p=0.04; Low: 8.3 ml/m2, CI: 7.7-9.0). The LA/RV minimum size ratio showed a larger size difference between the groups in the LA compared to the RV (High 1.183, CI: 1.063-1.303; Int 0.968, CI: 0.906-1.029, p<0.01, Low 0.921, CI: 0.726-1.116 p=0.02). A comparison of LA and LV size (LAminV/LVsysV) showed a significant decrease between high and intermediate groups, but not the low group (High: 0.366; Int: 0.296, p<0.01; Low: 0.302, p=0.16). The LA/RA size ratio was equal in all groups. LA strain analysis showed reduced contraction in the high and intermediate groups compared to the low group (High -10.2, CI: -10.9-(-9.4), p<0,01, Int -10.6, CI: -11.1-(-10.2), p<0.01, Low: -12.9, CI: -14.2-(-11.6)), the same pattern was not found in RA function, RV freewall and LV GLS (table 1). Conclusion We found a bilateral increase in atrial size while LA (but not RA) also showed reduced contraction in athletes from intermediate and high endurance demanding sports. Athletes from sports with high and intermediate endurance demands exhibited dilated ventricles but no decreased function was detected. Adaptations of atrial size and function were more pronounced than that of either ventricle.Table 1:Population characteristicsTable 2:Echocardiographic measures

Research on application of model ensemble in sports image classification based on environmental information

In recent years, a deep convolutional neural network has been widely used in the field of image classification. However, training a satisfactory network is very arduous, not only to tune the hyper-parameters in the network but also to avoid the overfitting problem caused by a deep neural network. Another point is that it is difficult for a neural network to learn subtle details without human annotation. Therefore this paper proposed a preferable classification algorithm for sports classification tasks that combines the deep neural network with the object detection algorithm to obtain the prediction result. In this paper, the author compared the differences between classification directly using neural networks and a modified model ensemble approach to classification from a holistic perspective, as well as elaborating the advantages and disadvantages of the two approaches. The conclusion shows that the use of the improved model ensemble classification algorithm performs better than the direct use of neural networks and also achieves a high degree of accuracy in the test set.

Sports video retrieval and classification using focus u-net based squeeze excitation and residual mapping deep learning model

Sports videos are widely used by athletes and coaches for training and match analysis purposes outside the mainstream audience. Sports videos should be effectively classified into different genres to easily retrieve and index them from large video datasets. Manual labelling classification methods may cause errors and have low accuracy. Classification based on video content analysis is challenging for computer vision-based techniques. This work introduces an improved focus-net deep learning (DL) model called the Convolutional squeeze U-Net based encoder-decoder for sports video retrieval and classification. First, the keyframes are extracted from the input sports video using a clustering and optical flow analysis method. In the next stage, the frames are pre-processed using a smoothed shock filtering technique to remove the noise. The process of image segmentation is carried out using a Convolutional squeeze U-Net based encoder-decoder model. Finally, the sports video can be classified using the softmax classifier. A CNN (convolutional neural network) is utilized at the encoder section for extracting the features and fed to the decoder for video classification. The experiments are performed in the UCF101 dataset, and the proposed model achieved an overall accuracy of 99.68%. Hence, it is proven that the proposed focus-net model can be efficiently utilized in sports video classification.

MRI radiomics for hamstring strain injury identification and return to sport classification: a pilot study.

To determine if MRI-based radiomics from hamstring muscles are related to injury and if the features could be used to perform a time to return to sport (RTS) classification. We hypothesize that radiomics from hamstring muscles, especially T2-weighted and diffusion tensor imaging-based features, are related to injury and can be used for RTS classification. MRI data from 32 athletes at the University of Wisconsin-Madison that sustained a hamstring strain injury were collected. Diffusion tensor imaging and T1- and T2-weighted images were processed, and diffusion maps were calculated. Radiomics features were extracted from the four hamstring muscles in each limb and for each MRI modality, individually. Feature selection was performed and multiple support vector classifiers were cross-validated to differentiate between involved and uninvolved limbs and perform binary (≤ or > 25days) and multiclass (< 14 vs. 14-42 vs. > 42days) classification of RTS. The combination of radiomics features from all diffusion tensor imaging and T2-weighted images provided the most accurate differentiation between involved and uninvolved limbs (AUC ≈ 0.84 ± 0.16). For the binary RTS classification, the combination of all extracted radiomics offered the most accurate classification (AUC ≈ 0.95 ± 0.15). While for the multiclass RTS classification, the combination of features from all the diffusion tensor imaging maps provided the most accurate classification (weighted one vs. rest AUC ≈ 0.81 ± 0.16). This pilot study demonstrated that radiomics features from hamstring muscles are related to injury and have the potential to predict RTS.

Utilizing spinal cord injury stratification during classification for allocation of para surfing sport classes.

The purpose of this study was to determine which stratification (anatomical versus functional) forms a better construct for classification of para surfers with spinal cord injury; to assess the groupings of these para surfers; and to evaluate the strength of association between manual muscle testing and surfing performance. Cross-sectional. Archived data from classification records including demographics, spinal cord injury levels, trunk strength, and limb strength were compared to judged wave scores and competition rankings. Participants (n = 70, male n = 56; female n = 14) met inclusion criteria and were classified into Para Surfing Kneeling (n = 9); Sit (n = 11); Prone 1 (n = 25); and Prone 2 (n = 25) sport classes. Reliability statistics showed that functional grouping (Cronbach's α = 0.759) is better grouped with strength testing and rankings compared to anatomical grouping (Cronbach's α = 0.721). Under exploratory factor analysis with 2 fixed components, based on the factor loadings (rank and strength) functional stratification (0.978) is better aligned compared to anatomical stratification (0.785) for grouping of surfers. Further, the association and impact of strength with functional spinal cord level stratification were confirmed using regression analysis (chi-square of 74.06 with p-value <.0001). Trunk and limb strengths have been shown to influence wave riding performance in surfers with spinal cord injury. Surfers with spinal cord injury can equitably be classified into one of the four para surfing sport classes. The use of functional stratification of spinal cord injury with trunk and limb strengths should be considered as an integral component in para surfing athlete sport classification.