Purpose: This study aimed to estimate the incidence, prevalence, type, and mechanism of injuries among grappling athletes in the United Kingdom (UK) across the following disciplines: Brazilian Jiu-Jitsu (BJJ), Judo, Catch Wrestling, Sambo, and Mixed Martial Arts (MMA).
Methods: A retrospective, self-reported survey, delivered via JISC online survey software, was used to record the following information for all injuries sustained over the previous 12-month period: mechanism of injury, environment, severity, recurrence and body region. Additionally, injury diagnosis was reported where possible. Injury incidence for training exposure was calculated based on hours trained per week, while competition exposure was based on the number of bouts participated in during the year. One variable chi-square tests (X2) were used to calculate if observed values were significantly different from expected values.
Results: A total of 341 grappling athletes, 243 males and 97 females, with one participant preferring not to state gender (32 ± 9.3 years), completed the study over a 3-month period. The competition incident rates (IR) (24.16/1000 AE) were significantly higher than training (2.97/1000 AE). The knee was the most frequently injured site (24.5%). Ligament sprains were the most commonly diagnosed injury (24.3%). Most injuries occurred during practice sparring (65.8%), with the leading mechanisms being submission attempts and takedowns. Major injuries (>28 days recovery) accounted for 49.5% of all cases. BJJ exhibited the highest injury rate (3.49/1000 AE); patterns varied by discipline and gender.
Conclusion: Grappling sports pose a substantial risk of injury, particularly to the knee. Structured training, medical support, and tailored injury risk reduction programs should now be explored to enhance athlete safety.
Lukas Buess, Matthias Keicher, Nassir Navab
et al.
Generative artificial intelligence (AI) models, such as diffusion models and OpenAI's ChatGPT, are transforming medicine by enhancing diagnostic accuracy and automating clinical workflows. The field has advanced rapidly, evolving from text-only large language models for tasks such as clinical documentation and decision support to multimodal AI systems capable of integrating diverse data modalities, including imaging, text, and structured data, within a single model. The diverse landscape of these technologies, along with rising interest, highlights the need for a comprehensive review of their applications and potential. This scoping review explores the evolution of multimodal AI, highlighting its methods, applications, datasets, and evaluation in clinical settings. Adhering to PRISMA-ScR guidelines, we systematically queried PubMed, IEEE Xplore, and Web of Science, prioritizing recent studies published up to the end of 2024. After rigorous screening, 144 papers were included, revealing key trends and challenges in this dynamic field. Our findings underscore a shift from unimodal to multimodal approaches, driving innovations in diagnostic support, medical report generation, drug discovery, and conversational AI. However, critical challenges remain, including the integration of heterogeneous data types, improving model interpretability, addressing ethical concerns, and validating AI systems in real-world clinical settings. This review summarizes the current state of the art, identifies critical gaps, and provides insights to guide the development of scalable, trustworthy, and clinically impactful multimodal AI solutions in healthcare.
Large Language Models (LLMs) have exhibited remarkable capabilities in clinical scenarios. Despite their potential, existing works face challenges when applying LLMs to medical settings. Strategies relying on training with medical datasets are highly cost-intensive and may suffer from outdated training data. Leveraging external knowledge bases is a suitable alternative, yet it faces obstacles such as limited retrieval precision and poor effectiveness in answer extraction. These issues collectively prevent LLMs from demonstrating the expected level of proficiency in mastering medical expertise. To address these challenges, we introduce Med-R^2, a novel LLM physician framework that adheres to the Evidence-Based Medicine (EBM) process, efficiently integrating retrieval mechanisms as well as the selection and reasoning processes of evidence, thereby enhancing the problem-solving capabilities of LLMs in healthcare scenarios and fostering a trustworthy LLM physician. Our comprehensive experiments indicate that Med-R^2 achieves a 13.27\% improvement over vanilla RAG methods and even a 4.55\% enhancement compared to fine-tuning strategies, without incurring additional training costs. Furthermore, we find that our LLaMA3.1-70B + Med-R$^2$ surpasses frontier models, including GPT-4o, Claude3.5-Sonnet and DeepSeek-V3 by 1.05\%, 6.14\% and 1.91\%. Med-R$^2$ effectively enhances the capabilities of LLMs in the medical domain.
The rapid growth of healthcare data and advances in computational power have accelerated the adoption of artificial intelligence (AI) in medicine. However, AI systems deployed without explicit fairness considerations risk exacerbating existing healthcare disparities, potentially leading to inequitable resource allocation and diagnostic disparities across demographic subgroups. To address this challenge, we propose FairGrad, a novel gradient reconciliation framework that automatically balances predictive performance and multi-attribute fairness optimization in healthcare AI models. Our method resolves conflicting optimization objectives by projecting each gradient vector onto the orthogonal plane of the others, thereby regularizing the optimization trajectory to ensure equitable consideration of all objectives. Evaluated on diverse real-world healthcare datasets and predictive tasks - including Substance Use Disorder (SUD) treatment and sepsis mortality - FairGrad achieved statistically significant improvements in multi-attribute fairness metrics (e.g., equalized odds) while maintaining competitive predictive accuracy. These results demonstrate the viability of harmonizing fairness and utility in mission-critical medical AI applications.
Traditional Chinese medicine (TCM) exhibits remarkable therapeutic efficacy in healthcare through patient-specific formulas. However, current AI-based TCM formula recommendation models and methods mainly focus on data-based textual associations between symptoms and herbs, and have not fully utilized their features and relations at different scales, especially at the molecular scale. To address these limitations, we propose the Fusion of Multiscale Associations of Symptoms and Herbs (FMASH), a novel framework that effectively incorporates the properties of herbs on different scales with clinical symptoms and provides refined embeddings of their multiscale associations. The framework integrates molecular-scale features and macroscopic properties of herbs and combines complex local and global relations in the heterogeneous graph of symptoms and herbs. Moreover, it provides effective representation embeddings of the multiscale features and associations of symptoms and herbs in a unified semantic space. Comprehensive experiments have been conducted on FMASH, and the results demonstrate that our FMASH-based model outperforms the state-of-the-art (SOTA) model on both datasets, confirming the effectiveness of FMASH in building the TCM formula recommendation model. In Dataset1, our model has achieved a significant improvement compared to the SOTA model, with increases of 3.38% in Precision@5, 3.89% in Recall@5, and 3.69% in F1-score@5. In Dataset2, Precision@5, Recall@5, and F1-score@5 increase by 2.64%, 1.92%, and 2.23%, respectively. This work facilitates the application of the AI-based TCM formula recommendation and promotes the innovative development of TCM diagnosis and treatment.
Multi-object tracking, player identification, and pose estimation are fundamental components of sports analytics, essential for analyzing player movements, performance, and tactical strategies. However, existing datasets and methodologies primarily target mainstream team sports such as soccer and conventional 5-on-5 basketball, often overlooking scenarios involving fixed-camera setups commonly used at amateur levels, less mainstream sports, or datasets that explicitly incorporate pose annotations. In this paper, we propose the TrackID3x3 dataset, the first publicly available comprehensive dataset specifically designed for multi-player tracking, player identification, and pose estimation in 3x3 basketball scenarios. The dataset comprises three distinct subsets (Indoor fixed-camera, Outdoor fixed-camera, and Drone camera footage), capturing diverse full-court camera perspectives and environments. We also introduce the Track-ID task, a simplified variant of the game state reconstruction task that excludes field detection and focuses exclusively on fixed-camera scenarios. To evaluate performance, we propose a baseline algorithm called Track-ID algorithm, tailored to assess tracking and identification quality. Furthermore, our benchmark experiments, utilizing recent multi-object tracking algorithms (e.g., BoT-SORT-ReID) and top-down pose estimation methods (HRNet, RTMPose, and SwinPose), demonstrate robust results and highlight remaining challenges. Our dataset and evaluation benchmarks provide a solid foundation for advancing automated analytics in 3x3 basketball. Dataset and code will be available at https://github.com/open-starlab/TrackID3x3.
The rapid growth of medical knowledge and increasing complexity of clinical practice pose challenges. In this context, large language models (LLMs) have demonstrated value; however, inherent limitations remain. Retrieval-augmented generation (RAG) technologies show potential to enhance their clinical applicability. This study reviewed RAG applications in medicine. We found that research primarily relied on publicly available data, with limited application in private data. For retrieval, approaches commonly relied on English-centric embedding models, while LLMs were mostly generic, with limited use of medical-specific LLMs. For evaluation, automated metrics evaluated generation quality and task performance, whereas human evaluation focused on accuracy, completeness, relevance, and fluency, with insufficient attention to bias and safety. RAG applications were concentrated on question answering, report generation, text summarization, and information extraction. Overall, medical RAG remains at an early stage, requiring advances in clinical validation, cross-linguistic adaptation, and support for low-resource settings to enable trustworthy and responsible global use.
This study explored the effects of strength-focused, speed-focused, and non-specific resistance training on the athletic performance and sprint biomechanics through force-velocity-power (FVP) profile in youth professional soccer players (age: 17.6 ± 0.9 years). In a 6-week randomized-controlled trial, 24 male participants were assigned to strength, speed, or control groups (n = 8 each). We assessed sprint performance, including sprint split times and the sprint FVP profile. Post-training, all groups showed significant enhancements in sprint times (p = 0.000-0.004, η² = 0.32-0.75) and FVP profile variables (p = 0.000-0.049; η² = 0.17-0.73). The strength group exhibited notable improvements in the maximal ratio of horizontal-to-resultant force (p = 0.026, d = 0.78) and maximal power (Phmax) (p = 0.013, d = 0.89) compared to controls. However, maximum velocity and maximum velocity at the end of acceleration phase did not significantly change in any group. These findings demonstrate that both strength and speed training significantly enhance force production capabilities in youth soccer players, influencing key FVP profile characteristics, without substantially affecting maximum velocity.
Andrea Calderone, MSc, Svonko Galasso, PhD, Alessandro Marco De Nunzio, PhD
et al.
Objective: To consolidate evidence on the efficacy of muscle vibration therapy for neurorehabilitation, providing health care practitioners with insights for enhancing treatment protocols and guiding future research. Data Sources: Studies were identified from an online search of PubMed, Web of Science, and Embase databases, with a search time range of 2014-2024. Study Selection: A total of 26 studies involving 787 individuals were included in this systematic review, including diverse neurologic conditions and intervention protocols. Data Extraction: Keywords, Boolean operators, and controlled vocabulary were combined and tested in a gradual and iterative manner to achieve the highest possible sensitivity and specificity. The PRISMA flowchart was used to depict the process of selecting relevant studies. Data Synthesis: Research on segmental and local muscle vibration in upper limb rehabilitation for poststroke patients is promising, as it can improve motor function, decrease spasticity, and enhance muscle control. Whole-body vibration interventions also show advantages in lower limb spasticity and balance, with specific studies adducing better results when paired with task-specific training. Vibration therapy has shown promising outcomes for alleviating pain, managing spasticity, and improving motor function in various neurologic conditions such as SCI and cerebral palsy, highlighting its potential in treating different neurologic disorders. Conclusions: This review emphasizes the potential of muscle vibration therapy in neurorehabilitation, showing benefits in motor control, spasticity, and functional outcomes, while underscoring the importance of rigorous methods and further extensive research to improve result dependability.
Arthrography is an X-ray examination using a contrast agent to examine a joint, such as the knee or shoulder. In arthrography, serial X-rays are taken of the joint being examined in various positions after a contrast agent is injected into the joint. This examination is most often used to examine the knee and shoulder joints, but can also be used for other joints, such as the wrist, ankle, hip, or elbow. Similarly, direct MR arthrography also involves the injection of contrast material into the joint. The contrast material used for MR evaluation is different from that used for x-rays; it contains the substance gadolinium, which affects the local magnetic field in the MRI channel and shows up on the MR image. As in conventional direct arthrography, the contrast material outlines anatomical structures within the joint, such as cartilage, labrum, ligaments, and bones, and allows them to be evaluated after the MR image is produced. Direct CT arthrography uses the same type of contrast material as conventional direct arthrography using x-rays and can be supplemented with air to produce double-contrast CT arthrograms. CT creates cross-sectional images that are processed by a computer using x-rays.
The emerging trend of advancing generalist artificial intelligence, such as GPTv4 and Gemini, has reshaped the landscape of research (academia and industry) in machine learning and many other research areas. However, domain-specific applications of such foundation models (e.g., in medicine) remain untouched or often at their very early stages. It will require an individual set of transfer learning and model adaptation techniques by further expanding and injecting these models with domain knowledge and data. The development of such technologies could be largely accelerated if the bundle of data, algorithms, and pre-trained foundation models were gathered together and open-sourced in an organized manner. In this work, we present OpenMEDLab, an open-source platform for multi-modality foundation models. It encapsulates not only solutions of pioneering attempts in prompting and fine-tuning large language and vision models for frontline clinical and bioinformatic applications but also building domain-specific foundation models with large-scale multi-modal medical data. Importantly, it opens access to a group of pre-trained foundation models for various medical image modalities, clinical text, protein engineering, etc. Inspiring and competitive results are also demonstrated for each collected approach and model in a variety of benchmarks for downstream tasks. We welcome researchers in the field of medical artificial intelligence to continuously contribute cutting-edge methods and models to OpenMEDLab, which can be accessed via https://github.com/openmedlab.
The biological targets of traditional Chinese medicine (TCM) are the core effectors mediating the interaction between TCM and the human body. Identification of TCM targets is essential to elucidate the chemical basis and mechanisms of TCM for treating diseases. Given the chemical complexity of TCM, both in silico high-throughput drug-target interaction predicting models and biological profile-based methods have been commonly applied for identifying TCM targets based on the structural information of TCM chemical components and biological information, respectively. However, the existing methods lack the integration of TCM chemical and biological information, resulting in difficulty in the systematic discovery of TCM action pathways. To solve this problem, we propose a novel target identification model NP-TCMtarget to explore the TCM target path by combining the overall chemical and biological profiles. First, NP-TCMtarget infers TCM effect targets by calculating associations between drug/disease inducible gene expression profiles and specific gene signatures for 8,233 targets. Then, NP-TCMtarget utilizes a constructed binary classification model to predict binding targets of herbal ingredients. Finally, we can distinguish TCM direct and indirect targets by comparing the effect targets and binding targets to establish the action pathways of herbal components-direct targets-indirect targets by mapping TCM targets in the biological molecular network. We apply NP-TCMtarget to the formula XiaoKeAn to demonstrate the power of revealing the action pathways of herbal formula. We expect that this novel model could provide a systematic framework for exploring the molecular mechanisms of TCM at the target level. NP-TCMtarget is available at http://www.bcxnfz.top/NP-TCMtarget.
Sentiment analysis has become increasingly important in healthcare, especially in the biomedical and pharmaceutical fields. The data generated by the general public on the effectiveness, side effects, and adverse drug reactions are goldmines for different agencies and medicine producers to understand the concerns and reactions of people. Despite the challenge of obtaining datasets on drug-related problems, sentiment analysis on this topic would be a significant boon to the field. This project proposes a drug review classification system that classifies user reviews on a particular drug into different classes, such as positive, negative, and neutral. This approach uses a dataset that is collected from publicly available sources containing drug reviews, such as drugs.com. The collected data is manually labeled and verified manually to ensure that the labels are correct. Three pre-trained language models, such as BERT, SciBERT, and BioBERT, are used to obtain embeddings, which were later used as features to different machine learning classifiers such as decision trees, support vector machines, random forests, and also deep learning algorithms such as recurrent neural networks. The performance of these classifiers is quantified using precision, recall, and f1-score, and the results show that the proposed approaches are useful in analyzing the sentiments of people on different drugs.
The efficacy of large language models (LLMs) in domain-specific medicine, particularly for managing complex diseases such as osteoarthritis (OA), remains largely unexplored. This study focused on evaluating and enhancing the clinical capabilities of LLMs in specific domains, using osteoarthritis (OA) management as a case study. A domain specific benchmark framework was developed, which evaluate LLMs across a spectrum from domain-specific knowledge to clinical applications in real-world clinical scenarios. DocOA, a specialized LLM tailored for OA management that integrates retrieval-augmented generation (RAG) and instruction prompts, was developed. The study compared the performance of GPT-3.5, GPT-4, and a specialized assistant, DocOA, using objective and human evaluations. Results showed that general LLMs like GPT-3.5 and GPT-4 were less effective in the specialized domain of OA management, particularly in providing personalized treatment recommendations. However, DocOA showed significant improvements. This study introduces a novel benchmark framework which assesses the domain-specific abilities of LLMs in multiple aspects, highlights the limitations of generalized LLMs in clinical contexts, and demonstrates the potential of tailored approaches for developing domain-specific medical LLMs.
Kelly Harrington, Lindsey Eberman, Matthew Rivera
et al.
Objective: Compare patient satisfaction between telemedicine and in-office visits and between providers post-operatively in an orthopedics setting with athletic trainers and physicians. Design: Cross-sectional study Methods: Patients from a Sports Medicine Clinic that received an orthopedic surgical intervention from March 2020-September 2021, and engaged in telemedicine, or an in-office visit post-operatively. Provider type included full-time athletic trainers, resident athletic trainers, physician (MD) resident/fellows, and float athletic trainers. Press-Ganey Patient Experience Surveys were collected at the time of follow up visit, with focus on items, “likelihood to recommend” and “how well staff worked together.” Results: There was a total of 255 patients (age=50±17 years). Providers included the attending physician with full-time athletic trainers (n=134, 52.3%), resident athletic trainers (n=77, 30.1%), MD residents/fellows (n=38, 14.8%), or float athletic trainers (n=6, 2.3%). No significant difference was found with patient satisfaction between in-office (n=175, 68.4%), or telemedicine visits (n=80, 31.3%), (p>.44). Patients were more satisfied with care provided by the full-time athletic trainers compared to MD residents/fellows (p.18). Conclusions: This study demonstrates no significant differences with patient satisfaction between in-office or telemedicine visits. Patients seeing full-time athletic trainers had the highest patient satisfaction, demonstrating the capability of athletic trainers to effectively use telemedicine in a physician practice.
The emergence of affordable standalone virtual reality (VR) devices has allowed VR technology to reach mass-market adoption in recent years, driven primarily by the popularity of VR gaming applications such as Beat Saber. However, despite being the top-grossing VR application to date and the most popular VR e-sport, the population of over 6 million Beat Saber users has not yet been widely studied. In this report, we present a large-scale comprehensive survey of Beat Saber players (N=1,006) that sheds light on several important aspects of this population, including their background, biometrics, demographics, health information, behavioral patterns, and technical device specifications. We further provide insights into the emerging field of VR e-sports by analyzing correlations between responses and an authoritative measure of in-game performance.
J. M. Algarín, T. Guallart-Naval, E. Gastaldi-Orquín
et al.
The goal of this work is to showcase the clinical value that portable MRI can provide in crowded events and major sports competitions. We temporarily installed a low-field and low-cost portable MRI system for extremity imaging in the medical facilities of the Ricardo Tormo Motor Racing Circuit during the four days of the Motorcycle Grand Prix held in Valencia (Spain), which closed the 2022 season of the MotoGP. During this time, we scanned 14 subjects, running a total of 21 protocols for wrist, knee and ankle imaging. Each protocol included a minimum of one T1-weighted 3D-RARE sequence for general anatomical information, and one 3D-STIR sequence to highlight fluid accumulation and inflammation. The circuit medical staff were able to visualize a number of lesions and conditions in the low-field reconstructions, including gonarthrosis, effusion, or Haglund's syndrome, as well as metallic implants and tissue changes due to surgical interventions. Out of eight low-field acquisitions on previously diagnosed lesions, only two (a meniscus tear and a Baker cyst) were not detected by the experts that evaluated our images. The main highlight was that a low-field MRI scan on a subject reporting pain in a wrist revealed a traumatic arthritis which an X-ray radiograph and visual inspection had missed. We have operated in a scenario where high-field MRI is unlikely to play a role but where a low-field system can lead to improved medical attention. In the case reported here, system transport, installation in the circuit facilities and calibration were all uncomplicated. The images presented to the medical staff were mostly unprocessed and there is thus room for improvement. In conclusion, this work supports the claim that low-field MRI can likely provide added value whenever concepts such as accessibility, portability and low-cost outweigh exquisite detail in images.