Hong Yeol Yang, Jong-Keun Seon, Khairul Anwar Ayob
<i>Background and Objectives</i>: Mechanical alignment (MA) has long been the gold standard in total knee arthroplasty (TKA), aiming for neutral hip–knee–ankle alignment with proven long-term survivorship. However, up to 20% of patients remain dissatisfied, often due to neglect of individual constitutional limb variation and subsequent soft tissue imbalance. This has driven the development of alternative alignment philosophies. This current concepts review aims to determine the various evolving alignment strategies, elucidate their underlying principles, and demonstrate the available clinical outcomes data. <i>Materials and Methods</i>: This review examines MA and the paradigm shift towards personalized alignment techniques, including Kinematic Alignment (KA), restricted Kinematic Alignment (rKA), inverse Kinematic Alignment (iKA), adjusted mechanical alignment (aMA), and the most recent evolution, Functional Alignment (FA). <i>Results</i>: Kinematic alignment and its derivatives (rKA, iKA) seek to better replicate native joint morphology and tension, often reducing the need for soft tissue releases and improving functional outcomes compared to MA. rKA and iKA introduce protective boundaries to avoid extreme phenotypes and possible instability. FA leverages robotic platforms and integrates these principles with real-time gap balancing, demonstrating promise for consistent, personalized outcomes. Some reports, however, advise caution with adjusted Mechanical Alignment (aMA), particularly those that result in phenotypes such as Coronal Plane Alignment of the Knee (CPAK) VII or VIII, which may increase the risk of revision. <i>Conclusions</i>: The philosophy of TKA has evolved from a uniform mechanical target (MA) to a more nuanced, patient-specific strategy. While promising mid- to long-term outcomes and comparable survival data support the viability of KA and its derivatives, critical needs remain, including standardizing nomenclature (especially for FA) and conducting high-quality comparative trials. Future directions involve leveraging high-volume intraoperative data and Artificial Intelligence (AI) to refine decision-making and further personalize alignment strategies, without compromising long-term implant survivorship.
Tariq Ali, Asif Nawaz, Muhammad Rizwan Rashid Rana
et al.
Bone fracture diagnosis is a critical aspect of sports medicine, where accurate and timely detection enables effective treatment and rapid recovery. This study proposes Deep-Fed, a federated deep learning framework for fracture diagnosis in athletes. Deep-Fed integrates convolutional neural networks with a specialized classification module, FractureNet, and trains it across distributed athletic clinics using federated averaging without exchanging raw images, thereby preserving patient privacy while leveraging diverse data sources. The framework was evaluated on three benchmark datasets-Deep-I, Deep-II, and Deep-III-representing varied imaging conditions and patient groups. Deep-Fed achieved accuracy rates of 96.23 ± 0.42%, 97.11 ± 0.35%, and 96.73 ± 0.39%, respectively, significantly outperforming Baseline 1 (87.23 ± 0.68%), Baseline 2 (90.15 ± 0.55%), and Baseline 3 (94.49 ± 0.47%). Statistical analysis using paired t-tests confirmed that Deep-Fed's improvements were significant (p < 0.05) across all comparisons. These results demonstrate that federated learning can be effectively applied for high-accuracy fracture detection in decentralized clinical settings, enabling collaboration across institutions without compromising data privacy.
This study presents a quantitative framework to compare teams in collective sports with respect to their style of play. The style of play is characterized by the team's spatial distribution over a collection of frames. As a first step, we introduce an optimal transport-based embedding to map frames into Euclidean space, allowing for the efficient computation of a distance. Then, building on this frame-level analysis, we leverage quantization to establish a similarity metric between teams based on a collection of frames from their games. For illustration, we present an analysis of a collection of games from the 2021-2022 Ligue 1 season. We are able to retrieve relevant clusters of game situations and calculate the similarity matrix between teams in terms of style of play. Additionally, we demonstrate the strength of the embedding as a preprocessing tool for relevant prediction tasks. Likewise, we apply our framework to analyze the dynamics in the first half of the NBA season in 2015-2016.
This paper introduces Gate-Shift-Pose, an enhanced version of Gate-Shift-Fuse networks, designed for athlete fall classification in figure skating by integrating skeleton pose data alongside RGB frames. We evaluate two fusion strategies: early-fusion, which combines RGB frames with Gaussian heatmaps of pose keypoints at the input stage, and late-fusion, which employs a multi-stream architecture with attention mechanisms to combine RGB and pose features. Experiments on the FR-FS dataset demonstrate that Gate-Shift-Pose significantly outperforms the RGB-only baseline, improving accuracy by up to 40% with ResNet18 and 20% with ResNet50. Early-fusion achieves the highest accuracy (98.08%) with ResNet50, leveraging the model's capacity for effective multimodal integration, while late-fusion is better suited for lighter backbones like ResNet18. These results highlight the potential of multimodal architectures for sports action recognition and the critical role of skeleton pose information in capturing complex motion patterns. Visit the project page at https://edowhite.github.io/Gate-Shift-Pose
Precise Event Spotting (PES) in sports videos requires frame-level recognition of fine-grained actions from single-camera footage. Existing PES models typically incorporate lightweight temporal modules such as the Gate Shift Module (GSM) or the Gate Shift Fuse to enrich 2D CNN feature extractors with temporal context. However, these modules are limited in both temporal receptive field and spatial adaptability. We propose Multi-Focus Temporal Shifting Module (MFS) that enhances GSM with multi-scale temporal shifts and Group Focus Module, enabling efficient modeling of both short and long-term dependencies while focusing on salient regions. MFS is a lightweight, plug-and-play module that integrates seamlessly with diverse 2D backbones. To further advance the field, we introduce the Table Tennis Australia dataset, the first PES benchmark for table tennis containing over 4,800 precisely annotated events. Extensive experiments across five PES benchmarks demonstrate that MFS consistently improves performance with minimal overhead, achieving leading results among lightweight methods (+4.09 mAP, 45 GFLOPs).
Objective To develop an LLM based realtime compound diagnostic medical AI interface and performed a clinical trial comparing this interface and physicians for common internal medicine cases based on the United States Medical License Exam (USMLE) Step 2 Clinical Skill (CS) style exams. Methods A nonrandomized clinical trial was conducted on August 20, 2024. We recruited one general physician, two internal medicine residents (2nd and 3rd year), and five simulated patients. The clinical vignettes were adapted from the USMLE Step 2 CS style exams. We developed 10 representative internal medicine cases based on actual patients and included information available on initial diagnostic evaluation. Primary outcome was the accuracy of the first differential diagnosis. Repeatability was evaluated based on the proportion of agreement. Results The accuracy of the physicians' first differential diagnosis ranged from 50% to 70%, whereas the realtime compound diagnostic medical AI interface achieved an accuracy of 80%. The proportion of agreement for the first differential diagnosis was 0.7. The accuracy of the first and second differential diagnoses ranged from 70% to 90% for physicians, whereas the AI interface achieved an accuracy rate of 100%. The average time for the AI interface (557 sec) was 44.6% shorter than that of the physicians (1006 sec). The AI interface ($0.08) also reduced costs by 98.1% compared to the physicians' average ($4.2). Patient satisfaction scores ranged from 4.2 to 4.3 for care by physicians and were 3.9 for the AI interface Conclusion An LLM based realtime compound diagnostic medical AI interface demonstrated diagnostic accuracy and patient satisfaction comparable to those of a physician, while requiring less time and lower costs. These findings suggest that AI interfaces may have the potential to assist primary care consultations for common internal medicine cases.
Arti Virkud, Jessie K. Edwards, Michele Jonsson Funk
et al.
Identifying optimal medical treatments to improve survival has long been a critical goal of pharmacoepidemiology. Traditionally, we use an average treatment effect measure to compare outcomes between treatment plans. However, new methods leveraging advantages of machine learning combined with the foundational tenets of causal inference are offering an alternative to the average treatment effect. Here, we use three unique, precision medicine algorithms (random forests, residual weighted learning, efficient augmentation relaxed learning) to identify optimal treatment rules where patients receive the optimal treatment as indicated by their clinical history. First, we present a simple hypothetical example and a real-world application among heart failure patients using Medicare claims data. We next demonstrate how the optimal treatment rule improves the absolute risk in a hypothetical, three-modifier setting. Finally, we identify an optimal treatment rule that optimizes the time to outcome in a real-world heart failure setting. In both examples, we compare the average time to death under the optimized, tailored treatment rule with the average time to death under a universal treatment rule to show the benefit of precision medicine methods. The improvement under the optimal treatment rule in the real-world setting is greatest (additional ~9 days under the tailored rule) for survival time free of heart failure readmission.
Aim This study investigated the effect of the combining Tabata training and cinnamon supplementation on metabolic changes and body composition in overweight and obese soldiers.Materials and Methods 40 overweight and obese soldiers were divided into Tabata (T), Tabata training+supplement (T+S), supplement (S) and control (C) groups. The intervention completed during eight weeks with three sessions per week. Pre- and post-intervention assessments included body composition (body mass index [BMI], body fat percentage [BFP], performance parameters) push-up, squat, plank and vertical jump), metabolic markers (fasting blood sugar [FBS], insulin and [HOMA], liver enzymes (Serum Glutamic-Oxaloacetic Transaminase [SGOT], Serum Glutamic-Pyruvic Transaminase [SGPT], and Gamma-Glutamyl Transferase [GGT] (and inflammatory markers (C-Reactive Protein [CRP], Tumor Necrosis Factor-alpha [TNF-α], Adiponectin and Irisin). Cinnamon supplement was taken in 500 mg capsules three times a day.Results Body mass, BMI, and body fat percentage significantly decreased in all intervention groups (p < 0.001), with the greatest fat loss in T + S (−7.86%, p < 0.001), significantly more than T (p = 0.013). Performance (push-up, squat, plank, jump) improved in T and T + S (all p < 0.001), with no difference between them (p > 0.05). Fasting blood sugar, insulin, HOMA-IR, and liver enzymes (SGOT, SGPT, GGT) decreased across all interventions (p < 0.05), with the greatest reductions in T + S. Inflammatory markers (CRP, TNF-α) declined, while adiponectin and irisin increased in all interventions (p < 0.001), with superior changes in T + S versus all groups (p < 0.05). The control group showed no significant changes (p > 0.05).Conclusion Tabata training resulted in synergistically effect on performance, body composition, metabolic-inflammation markers, and liver enzyme function in overweight and obese individuals. Moreover, the cinnamon supplementation as an ergogenic potentiated the observed beneficial effects.