Hasil untuk "Sports medicine"

A. Albright, M. Franz, G. Hornsby et al.

Owen Terry

Fine-tuned LLMs often exhibit unexpected behavior as a result of generalizing beyond the data they're shown. We present results in which an LLM fine-tuned to prefer either coastal sports teams or Southern sports teams adopt political beliefs that diverge significantly from those of the base model. While we hypothesized that the coastal model would become more liberal and the southern model would become more conservative, we find that their responses are usually similar to each other, without a clear-cut liberal or conservative bias. In addition to asking the models for numerical ratings of agreement with relevant political statements, we ask them to elaborate on their more radical answers, finding varying degrees of willingness to justify themselves. Further work is needed to understand the mechanisms by which fine-tuning on simple, narrow datasets leads to seemingly unrelated changes in model behavior.

Nitish Kumar, Sannu Kumar, S Akash et al.

With the rapid proliferation of online sports journalism, extracting meaningful pre-game and post-game insights from articles is essential for enhancing user engagement and comprehension. In this paper, we address the task of automatically extracting such insights from articles published before and after matches. We curate a dataset of 7,900 news articles covering 800 matches across four major sports: Cricket, Soccer, Basketball, and Baseball. To ensure contextual relevance, we employ a two-step validation pipeline leveraging both open-source and proprietary large language models (LLMs). We then utilize multiple state-of-the-art LLMs (GPT-4o, Qwen2.5-72B-Instruct, Llama-3.3-70B-Instruct, and Mixtral-8x7B-Instruct-v0.1) to generate comprehensive insights. The factual accuracy of these outputs is rigorously assessed using a FactScore-based methodology, complemented by hallucination detection via the SummaC (Summary Consistency) framework with GPT-4o. Finally, we propose SUMMIR (Sentence Unified Multimetric Model for Importance Ranking), a novel architecture designed to rank insights based on user-specific interests. Our results demonstrate the effectiveness of this approach in generating high-quality, relevant insights, while also revealing significant differences in factual consistency and interestingness across LLMs. This work contributes a robust framework for automated, reliable insight generation from sports news content. The source code is availble here https://github.com/nitish-iitp/SUMMIR.

Tsz-To Wong, Ching-Chun Huang, Hong-Han Shuai

Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models often struggle with this temporal hierarchy, offering solutions that lack generalization, incur high development costs for new tasks, and suffer from poor interpretability. To overcome these limitations, we propose a reconfigurable Multi-Agent System (MAS) as a foundational framework for sports video understanding. In our system, each agent functions as a distinct "cognitive tool" specializing in a specific aspect of analysis. The system's architecture is not confined to a single temporal dimension or task. By leveraging iterative invocation and flexible composition of these agents, our framework can construct adaptive pipelines for both short-term analytic reasoning (e.g., Rally QA) and long-term generative summarization (e.g., match summaries). We demonstrate the adaptability of this framework using two representative tasks in badminton analysis, showcasing its ability to bridge fine-grained event detection and global semantic organization. This work presents a paradigm shift towards a flexible, scalable, and interpretable system for robust, cross-task sports video intelligence. The project homepage is available at https://aiden1020.github.io/COACH-project-page

Mehdi Houshmand Sarkhoosh, Frøy Øye, Henrik Nestor Sørlie et al.

Quantifying sponsor visibility in sports broadcasts is a critical marketing task traditionally hindered by manual, subjective, and unscalable analysis methods. While automated systems offer an alternative, their reliance on axis-aligned Horizontal Bounding Box (HBB) leads to inaccurate exposuremetrics when logos appear rotated or skewed due to dynamic camera angles and perspective distortions. This paper introduces ExposureEngine, an end-to-end system designed for accurate, rotation-aware sponsor visibility analytics in sports broadcasts, demonstrated in a soccer case study. Our approach predicts Oriented Bounding Box (OBB) to provide a geometrically precise fit to each logo regardless of the orientation on-screen. To train and evaluate our detector, we developed a new dataset comprising 1,103 frames from Swedish elite soccer, featuring 670 unique sponsor logos annotated with OBBs. Our model achieves a mean Average Precision (mAP@0.5) of 0.859, with a precision of 0.96 and recall of 0.87, demonstrating robust performance in localizing logos under diverse broadcast conditions. The system integrates these detections into an analytical pipeline that calculates precise visibility metrics, such as exposure duration and on-screen coverage. Furthermore, we incorporate a language-driven agentic layer, enabling users to generate reports, summaries, and media content through natural language queries. The complete system, including the dataset and the analytics dashboard, provides a comprehensive solution for auditable and interpretable sponsor measurement in sports media. An overview of the ExposureEngine is available online: https://youtu.be/tRw6OBISuW4 .

Wenbo Tian, Ruting Lin, Hongxian Zheng et al.

Existing intelligent sports analysis systems mainly focus on "scoring and visualization," often lacking automatic performance diagnosis and interpretable training guidance. Recent advances in Large Language Models (LLMs) and motion analysis techniques provide new opportunities to address the above limitations. In this paper, we propose SportsGPT, an LLM-driven framework for interpretable sports motion assessment and training guidance, which establishes a closed loop from motion time-series input to professional training guidance. First, given a set of high-quality target models, we introduce MotionDTW, a two-stage time series alignment algorithm designed for accurate keyframe extraction from skeleton-based motion sequences. Subsequently, we design a Knowledge-based Interpretable Sports Motion Assessment Model (KISMAM) to obtain a set of interpretable assessment metrics (e.g., insufficient extension) by contrasting the keyframes with the target models. Finally, we propose SportsRAG, a RAG-based training guidance model built upon Qwen3. Leveraging a 6B-token knowledge base, it prompts the LLM to generate professional training guidance by retrieving domain-specific QA pairs. Experimental results demonstrate that MotionDTW significantly outperforms traditional methods with lower temporal error and higher IoU scores. Furthermore, ablation studies validate the KISMAM and SportsRAG, confirming that SportsGPT surpasses general LLMs in diagnostic accuracy and professionalism.

Linfeng Dong, Yuchen Yang, Hao Wu et al.

We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first to provide large-scale, fine-grained annotations for racket pose alongside traditional ball positions, enabling research into complex human-object interactions. It is designed to tackle three interconnected tasks: fine-grained ball tracking, articulated racket pose estimation, and predictive ball trajectory forecasting. Our evaluation of established baselines reveals a critical insight for multi-modal fusion: while naively concatenating racket pose features degrades performance, a CrossAttention mechanism is essential to unlock their value, leading to trajectory prediction results that surpass strong unimodal baselines. RacketVision provides a versatile resource and a strong starting point for future research in dynamic object tracking, conditional motion forecasting, and multimodal analysis in sports. Project page at https://github.com/OrcustD/RacketVision

Ksenia A. Blinova, Irina E. Mishina, Galina E. Ivanova et al.

INTRODUCTION. The use of antitumor therapy in patients with breast cancer has led not only to an increase in their life expectancy, but also to the need to correct various side effects, including manifestations of cardiotoxicity. Rehabilitation of such patients in Russia is currently lacking. AIM. To search and analyze the literature on the effectiveness of physical training for the prevention of cardiotoxic complications of antitumor therapy. MATERIALS AND METHODS. Publications from the PubMed, Scopus, Web of Science, PEDro databases over the past 15 years were collected and analyzed 15 years by keywords in Russian and English: “cardiotoxicity”, “exercise”, “breast cancer”. 126 sources were selected, including systematic reviews and a Cochrane review. RESULTS AND DISCUSSION. Preclinical studies have shown that physical exercise reduces the accumulation of antitumor drugs in the myocardium and increases the proliferation of cardiomyocyte progenitor cells. Conducting physical training during and after anticancer treatment increases cardiorespiratory endurance and reduces the manifestations of anthracycline cardiotoxicity. This rehabilitation intervention leads to less fatigue, decreased depression, improved physical fitness, cognitive functions, and quality of life. The greatest effectiveness during and after anticancer therapy was shown by aerobic and strength exercises of moderate intensity, performed for 30–40 minutes 3–5 times a week, which provide 150 minutes of physical activity per week. The limitation of the use of physical training in patients is due to the impossibility of predicting the training heart rate by age, as well as the need to take into account concomitant diseases and the patient’s condition. CONCLUSION. The use of physical training can be used in cancer patients to prevent cardiotoxicity of anticancer therapy. Further research is needed to ensure their successful use in patients with different physical fitness and treatment tolerance.

Sumaya Mustafa, Mariwan Hama Saeed

Abstract Artificial intelligence (AI) models have demonstrated significant success in classifying various types of text. However, the complex nature of these models often complicates the interpretability of their classifications. To address these challenges and to enhance explainability, this study proposes a novel approach to text classification leveraging natural language processing (NLP) techniques and explainable AI (XAI) methods. Text preprocessing steps were essential for improving the quality of text analysis. This was gained by eliminating elements that contribute minimal semantic value. To achieve robust performance and mitigate the risk of overfitting, repeated stratified K-Fold cross-validation was utilized. Furthermore, the synthetic minority oversampling technique (SMOTE) was employed to address dataset imbalance issues. In the classification phase, nine machine learning models and hybrid/multi-model approaches were employed. To validate the explainability of the classifications, the local interpretable model-agnostic explanations (LIME) framework was utilized. The study utilized two datasets containing texts from domains such as sports, medicine, entertainment, politics, technology, and business. Empirical evaluations demonstrated the effectiveness of the proposed approach. The proposed hybrid model achieved exceptional performance across key metrics, including accuracy, precision, recall, and F1-score. The proposed hybrid model achieved results of up to 99% accuracy. This work can be used for various text analysis applications.

Zhanhong Liu, Qingsong Jiang, Liren Wang et al.

Tendon-to-bone healing is considered as a critical determinant influencing the quality of anterior cruciate ligament (ACL) reconstruction. The establishment of a microenvironment conducive to tendon-bone healing remains an urgent challenge for rapidly restoring the structural integrity and functional capacity of damaged tissue. In this study, an injectable hydroxyapatite/collagen type I (HAp/Col I) composite was developed and optimized. Its efficacy in ACL reconstruction was verified in a beagle dog model. During the early postoperative period, this composite successfully established an optimal regenerative microenvironment, thereby promoting cell proliferation, adhesion, and extracellular matrix secretion. Micro CT analysis revealed that the HAp/Col I composite significantly accelerated the mineralization process of local tissue and facilitated the contraction of the artificial bone tunnel. Tensile pull-out tests and nanoindentation experiments demonstrated that HAp/Col I composite enhanced both the macroscopic tensile pull-out strength of the ligament and the elastic modulus at the microscopic level. Furthermore, Raman spectroscopy and histological evaluations indicated that the tendon-to-bone interface exhibited a composition and structure closely resembling native tissue in terms of inorganic components and fiber alignment. Additionally, the injectable HAp/Col I composite consisted of safe, non-toxic materials, featured a convenient injection process, and was compatible with arthroscopic procedures, suggesting promising clinical application prospects.

Divya Shanmugam, Monica Agrawal, Rajiv Movva et al.

The increased capabilities of generative AI have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinicians, patients, clinical trial organizers, researchers, and trainees. We then discuss the many challenges -- including maintaining privacy and security, improving transparency and interpretability, upholding equity, and rigorously evaluating models -- which must be overcome to realize this potential, and the open research directions they give rise to.

Gian-Gabriel P. Garcia, J. Carlos Martínez Mori

Given a collection of historical sports rankings, can one tell which player is the greatest of all time (i.e., the GOAT)? In this work, we design a data-driven random walk on the symmetric group to obtain a stationary distribution over player rankings, spanning across different time periods in sports history. We combine this distribution with a notion of stochastic dominance to obtain a partial order over the players. Compared to existing methods, our approach is distinct in that i) using historical rankings captures the evolution of value systems and facilitates player comparisons when head-to-head data is unavailable, and i) aggregating into a partial order formally comes to terms with the possibility that, while some player comparisons can be established conclusively, others are "too close to call." We implement our methods using publicly available data from the Association of Tennis Professionals (ATP) and the Women's Tennis Association (WTA). Our main findings indicate that Steffi Graf and Serena Williams are the ones that come ahead as the GOATs of the WTA. Likewise, the "Big Three," that is Novak Djokovic, Roger Federer, and Rafael Nadal, are the ones that come ahead as the GOATs of the ATP. As a secondary finding, we note major differences in terms of career and dominance longevity for top players across the associations. While initially motivated by this application in sports analytics, our methods can also be applied to other practical domains where deriving rankings from historical data can inform operational decisions, such as route planning logistics.

Jiacheng Sun, Hsiang-Wei Huang, Cheng-Yen Yang et al.

Multi-object tracking in sports scenarios has become one of the focal points in computer vision, experiencing significant advancements through the integration of deep learning techniques. Despite these breakthroughs, challenges remain, such as accurately re-identifying players upon re-entry into the scene and minimizing ID switches. In this paper, we propose an appearance-based global tracklet association algorithm designed to enhance tracking performance by splitting tracklets containing multiple identities and connecting tracklets seemingly from the same identity. This method can serve as a plug-and-play refinement tool for any multi-object tracker to further boost their performance. The proposed method achieved a new state-of-the-art performance on the SportsMOT dataset with HOTA score of 81.04%. Similarly, on the SoccerNet dataset, our method enhanced multiple trackers' performance, consistently increasing the HOTA score from 79.41% to 83.11%. These significant and consistent improvements across different trackers and datasets underscore our proposed method's potential impact on the application of sports player tracking. We open-source our project codebase at https://github.com/sjc042/gta-link.git.

Aayush Chaudhary

This study explores the impact of upselling on user engagement. We model users' deposit behaviour on the fantasy sports platform Dream11. Subsequently, we develop an experimental framework to evaluate the effect of upselling using an intensity parameter. Our live experiments on user deposit behaviour reveal decreased user recall with heightened upselling intensity. Our findings indicate that increased upselling intensity improves user deposit metrics and concurrently diminishes user satisfaction and conversion rates. We conduct robust counterfactual analysis and train causal meta-learners to personalise users' upselling intensity levels to reach an optimal trade-off point.

Pablo Reis de Moraes, Kauã Felipe Kunz, Maiara Helena Rusch et al.

Introdução: O joelho é a principal articulação acometida pela osteoatrose (OA), com maior prevalência em mulheres idosas. Exercícios multifuncionais são eficazes no tratamento dessa condição, sendo a dança um exercício tolerável e bem aceito. Entretanto, não está claro qual a melhor modalidade de exercício traz maiores benefícios.  Objetivo: Comparar a funcionalidade articular entre mulheres com OA de joelhos que participam de um programa de atividade física monitorada de alongamentos e exercícios resistidos para terceira idade e entre participantes de um grupo de dança recreativa. Materiais e Métodos: Estudo transversal, descritivo e analítico. Foram incluídas 47 mulheres acima de 50 anos com OA de joelho. As participantes foram divididas em 2 grupos, um com 25 mulheres que participavam de um grupo de dança recreativa; outro com 22 mulheres que realizavam um programa monitorado de exercícios resistidos e alongamentos. Todas responderam um questionário sociodemográfico e de saúde; a função articular foi avaliada pelo questionário WOMAC. Resultados: As participantes apresentaram características amostrais similares quanto a características sociodemográficas e de saúde. As participantes do grupo de atividade física apresentaram uma maior pontuação no questionário WOMAC em relação as dimensões dor (p<0,001), rigidez (p<0,001) e função física (p<0,001), quando comparadas às do grupo dança. Conclusão: Os resultados demonstram que mulheres com OA de joelho do grupo de dança recreativa apresentaram menos dor, menor rigidez e melhor função física do joelho, quando comparados com o grupo de atividade física monitorada de alongamentos e de exercícios resistidos para terceira idade.

Marília da Silva Alves, Roberto Jerônimo dos Santos Silva, Cleidison Machado Santana et al.

Apesar dos investimentos realizados ao redor do mundo, seja no âmbito acadêmico, seja na implementação de políticas públicas, os níveis de atividade física não têm aumentado a contento. Assim, o objetivo deste trabalho é identificar quais os fatores que influenciam na participação em Programas Comunitários de Atividade Física na realidade brasileira. Para isso, utilizando a Pesquisa Nacional de Saúde 2019, investigou-se 20.014 sujeitos considerando como desfecho a participação nesses programas, com variáveis independentes divididas em biológicas e sociodemográficas. Para a análise dos dados utilizou-se da regressão logística binária, com p < 0,05, através do software Jamovi® versão 2.3.21. Observou-se que pessoas do gênero feminino (OR = 1,54; IC 95%: 1,40 - 1,69), “pessoas idosas” (OR = 1,10; IC 95%: 1,01 - 1,21) e pessoas “não brancas” (OR = 1,51; IC95%: 1,38 - 1,66) apresentaram chances elevadas de participação nos Programas Comunitários de Atividade Física. Para o segundo bloco, identificou-se que quem apresentou renda acima de cinco salários mínimos tiveram chances reduzidas em 34% (OR = 0,66; IC 95%: 0,57 - 0,76) quando comparados aos que relataram renda de até um salário, e, os que residiam próximo aos locais públicos para lazer apresentaram chances elevadas de participação (OR = 1,71; IC 95%: 1,52 - 1,92). Em suma, aspectos biológicos e sociodemográficos influenciaram na participação em Programas Comunitários de Atividade Física, contudo, a existência de locais públicos de lazer próximos às residências foi o fator de maior impacto evidenciado.

Nabil Mehta, Alexander J Acuna, Johnathon R McCormick et al.

# Background In 2020, the American Society of Shoulder and Elbow Therapists (ASSET) published an evidence-based consensus statement outlining postoperative rehabilitation guidelines following anatomic total shoulder arthroplasty (TSA). # Purpose The purpose of this study was to (1) quantify the variability in online anatomic TSA rehabilitation protocols, and (2) assess their congruence with the ASSET consensus guidelines. # Methods This study was a cross-sectional investigation of publicly available, online rehabilitation protocols for anatomic TSA. A web-based search was conducted in April 2022 of publicly available rehabilitation protocols for TSA. Each collected protocol was independently reviewed by two authors to identify recommendations regarding immobilization, initiation, and progression of passive (PROM) and active range of motion (AROM), as well as the initiation and progression of strengthening and post-operative exercises and activities. The time to initiation of various components of rehabilitation was recorded as the time at which the activity or motion threshold was permitted by the protocol. Comparisons between ASSET start dates and mean start dates from included protocols were performed. # Results Of the 191 academic institutions included, 46 (24.08%) had publicly available protocols online, and a total of 91 unique protocols were included in the final analysis. There were large variations seen among included protocols for the duration and type of immobilization post-operatively, as well as for the initiation of early stretching, PROM, AROM, resistance exercises, and return to sport. Of the 37 recommendations reported by both the ASSET and included protocols, 31 (83.78%) were found to be significantly different between groups (p\<0.05). # Conclusion Considerable variability was found among online post-operative protocols for TSA with substantial deviation from the ASSET guidelines. These findings highlight the lack of standardization in rehabilitation protocols following anatomic TSA. # Level of Evidence 3b

A. King, C. Macera, C. Castaneda-Sceppa et al.

Emanuele Regnani

This work aims to combine these two fields together by presenting a practical implementation of machine learning to the particular form of mental training that is the art of memory, taken in its competitive version called "Memory Sports". Such a fusion, on the one hand, strives to raise awareness about both realms, while on the other it seeks to encourage research in this mixed field as a way to, ultimately, drive forward the development of this seemingly underestimated sport.

Vélez Jiménez, Román Alberto, Lecuanda Ontiveros et al.

This paper presents a novel approach for optimizing betting strategies in sports gambling by integrating Von Neumann-Morgenstern Expected Utility Theory, deep learning techniques, and advanced formulations of the Kelly Criterion. By combining neural network models with portfolio optimization, our method achieved remarkable profits of 135.8% relative to the initial wealth during the latter half of the 20/21 season of the English Premier League. We explore complete and restricted strategies, evaluating their performance, risk management, and diversification. A deep neural network model is developed to forecast match outcomes, addressing challenges such as limited variables. Our research provides valuable insights and practical applications in the field of sports betting and predictive modeling.