Aim: This scoping review examines the application of artificial intelligence (AI) in sports biomechanics, with a focus on enhancing performance and preventing injuries. The review addresses key research questions, including primary AI methods, their effectiveness in improving athletic performance, their potential for injury prediction, sport-specific applications, strategies for translating knowledge, ethical considerations, and remaining research gaps. Following the PRISMA-ScR guidelines, a comprehensive literature search was conducted across five databases (PubMed/MEDLINE, Web of Science, IEEE Xplore, Scopus, and SPORTDiscus), encompassing studies published between January 2015 and December 2024. After screening 3248 articles, 73 studies met the inclusion criteria (Cohen’s kappa = 0.84). Data were collected on AI techniques, biomechanical parameters, performance metrics, and implementation details. Results revealed a shift from traditional statistical models to advanced machine learning methods. Based on moderate-quality evidence from 12 studies, convolutional neural networks reached 94% agreement with international experts in technique assessment. Computer vision demonstrated accuracy within 15 mm compared to marker-based systems (6 studies, moderate quality). AI-driven training plans showed 25% accuracy improvements (4 studies, limited evidence). Random forest models predicted hamstring injuries with 85% accuracy (3 studies, moderate quality). Learning management systems enhanced knowledge transfer, raising coaches’ understanding by 45% and athlete adherence by 3.4 times. Implementing integrated AI systems resulted in a 23% reduction in reinjury rates. However, significant challenges remain, including standardizing data, improving model interpretability, validating models in real-world settings, and integrating them into coaching routines. In summary, incorporating AI into sports biomechanics marks a groundbreaking advancement, providing analytical capabilities that surpass traditional techniques. Future research should focus on creating explainable AI, applying rigorous validation methods, handling data ethically, and ensuring equitable access to promote the widespread and responsible use of AI across all levels of competitive sports.

Musculoskeletal injuries during the “Initial Training Phase” (ITP) are a major medical problem faced by law enforcement agencies worldwide. Aiming to develop an injury prevention strategy, we examined the incidence, type, associated factors, and severity of injuries and secondarily tracked their evolution over time by batches in a police academy. A retrospective cohort study was conducted using prospectively collected injury data on 979 newly recruited male police cadets enrolled in eight batches between 2015 and 2023. Among the 376 injured participants (age: 18.1 ± 0.3 years, body-mass: 75.8 ± 12.5 kg, body-height: 173.7 ± 4.0 cm, body mass index [BMI]: 25.1 ± 4.1 kg·m^-2, body-fat percentage: 18.1% ± 5.1%), 405 injuries were recorded during the ITP. Musculoskeletal injury data were analyzed according to type, associated-factors, severity, and evolution across batches. Almost half of the recruits (41.4%) sustained at least one musculoskeletal injury. Based on injury frequency (39–69 case) and exposure time (20,944.5–43,006.5 hours per participant) indices, and with an implication of scientific training tips, the long-term follow-up over-batches showed that the injury incidence was decreased 2.5-fold from Batch 1 to Batch 8 ( p < .0001). Most injuries occurred between Weeks 2 and 5 (80% cumulative). The most common injury type was medial tibial stress syndrome (36.0%), followed by iliotibial band syndrome (12.6%), and ankle sprain (10.4%). This injury profile aligns with previous studies on law enforcement recruits, although comparisons should be made cautiously due to variations in training programs and recruit characteristics between agencies. The most frequently reported perceived potential contributors of injuries were vitamin and mineral deficiencies (20.7%), overweight/obesity (19.1%), and harsh physical activities (13.0%). During ITP, almost half of the recruits sustained at least one musculoskeletal injury, most of them in the fourth week. Some of the major associated factors of injury could be controlled resulting in a potential reduction of the injury incidence by up to 2.5 times. Implementing tailored fitness programs, incorporating subjective and objective training load assessments, and enhancing monitoring could significantly decrease injury rates, improve recruit readiness, and reduce resource and time waste on injury treatment.

Background: Sports injuries impose a substantial burden on athletes. Machine learning (ML) and deep learning (DL) methods, collectively referred to as artificial intelligence (AI), are increasingly applied to develop predictive models and targeted prevention strategies. Objective: This scoping review aimed to map contemporary trends in AI applications for sports injury prediction and personalised prevention strategies, critically appraising the existing methodological approaches and identifying future research directions. Methods: Following PRISMA-ScR guidelines, we systematically searched five electronic databases, i.e., PubMed, Web of Science, Institute of Electrical and Electronics Engineers Xplore, Scopus, and Google Scholar, for peer-reviewed studies published up to February 2026 that applied AI methods for injury prediction and/or prevention in athletic populations. Results: Thirty-nine studies were included. Tree-based ML algorithms were the most common (59% of studies) methods used, with reported area under the curve values ranging from 0.82 to 0.95. DL was used in 18% of studies, with one hybrid model reporting 92% accuracy. Integrating multi-modal data was associated with improved model performance in 37% of studies. Among included studies, AI-informed prevention strategies were associated with injury reductions ranging from 23% to 42%, derived from synthesis-level and single-centre intervention evidence, respectively. The key challenges identified were heterogeneous injury definitions, small sample sizes, and data privacy concerns. Conclusions: AI models can inform personalised injury prevention, but their clinical use is limited by methodological issues. Key limitations include heterogeneous injury definitions, small sample sizes, and a lack of external validation. Standardised protocols are needed to improve the reliability and application of these models in practice.

Objective: This study compared the acute effects of caffeine capsule ingestion and caffeine mouth rinsing on physical performance and volleyball-specific skills at different times of day in trained adolescent male volleyball players. Methods: Twenty-four well-trained male volleyball players (age: 16.9 ± 0.7 years) completed a randomized, double-blind, placebo-controlled crossover study involving three supplementation conditions, caffeine capsule (CAFcap, 3 mg·kg⁻¹), caffeine mouth rinse (CAFrinse, 3 mg·kg⁻¹), and placebo (PLA), administered via a double-dummy procedure (nine sessions per participant: 3 conditions × 3 times of day) at 08:00, 12:00, and 18:00. Participants completed squat jump (SJ), countermovement jump (CMJ), block jump, attack jump, 10 × 10 m t-test, spike accuracy, and serve accuracy assessments. Data were analyzed using two-way repeated-measures ANOVA. Results: Significant main effects of condition and time of day were observed for all outcomes. Significant condition × time-of-day interactions were found for SJ, CMJ, attack jump, and change-of-direction speed, indicating that caffeine-related ergogenic effects were most evident in the morning and at midday, whereas these benefits were attenuated in the evening when baseline performance was highest. At 08:00 and 12:00, both CAFcap and CAFrinse improved jump performance and agility compared with PLA, with capsule ingestion showing a small-to-moderate advantage over mouth rinsing for selected lower-limb power outcomes at midday (mean difference range: 0.51–0.57 cm; dz = 0.57–0.65). For block jump, spike accuracy, and serve accuracy, both caffeine conditions improved performance relative to placebo, while a progressive improvement across the day was observed under all conditions, including placebo, confirming a diurnal rhythm effect independent of supplementation. Overall, the data indicate that caffeine partially reduced the amplitude of diurnal variation in several physical performance measures. Conclusions: Both caffeine capsule ingestion and caffeine mouth rinsing enhanced physical and volleyball-specific performance in trained adolescent male volleyball players. The ergogenic effects were more pronounced earlier in the day, suggesting that caffeine may be particularly useful for attenuating morning and midday performance decrements, while mouth rinsing represents a practical non-ingestive alternative with meaningful efficacy.