Background/Objectives: Identifying and decomposing compound ingredients within meal plans presents meal customization and nutritional analysis challenges. It is essential for accurately identifying and replacing problematic ingredients linked to allergies or intolerances and helping nutritional evaluation. Methods: This study explored the effectiveness of three large language models (LLMs)—GPT-4o, Llama-3 (70B), and Mixtral (8x7B), in decomposing compound ingredients into basic ingredients within meal plans. GPT-4o was used to generate 15 structured meal plans, each containing compound ingredients. Each LLM then identified and decomposed these compound items into basic ingredients. The decomposed ingredients were matched to entries in a subset of the USDA FoodData Central repository using API-based search and mapping techniques. Nutritional values were retrieved and aggregated to evaluate accuracy of decomposition. Performance was assessed through manual review by nutritionists and quantified using accuracy and F1-score. Statistical significance was tested using paired t-tests or Wilcoxon signed-rank tests based on normality. Results: Results showed that large models—both Llama-3 (70B) and GPT-4o—outperformed Mixtral (8x7B), achieving average F1-scores of 0.894 (95% CI: 0.84–0.95) and 0.842 (95% CI: 0.79–0.89), respectively, compared to an F1-score of 0.690 (95% CI: 0.62–0.76) from Mixtral (8x7B). Conclusions: The open-source Llama-3 (70B) model achieved the best performance, outperforming the commercial GPT-4o model, showing its superior ability to consistently break down compound ingredients into precise quantities within meal plans and illustrating its potential to enhance meal customization and nutritional analysis. These findings underscore the potential role of advanced LLMs in precision nutrition and their application in promoting healthier dietary practices tailored to individual preferences and needs.

Background: Endurance athletes require tailored nutrition strategies to optimize performance, recovery, and training adaptations. While traditional sports nutrition guidelines provide a foundational framework, individual variability in metabolic responses underscores the need for precision nutrition, informed by genetic, biological, and environmental factors. This scoping review evaluates the application of systems biology-driven sports nutrition for endurance athletes, focusing on ‘omics’ and wearable technologies. Methods: A scoping review of the literature was conducted in PubMed, Scopus, and Web of Science in accordance with the PRISMA-ScR checklist. Research questions, search strategies, and eligibility criteria were guided by the Population–Concept–Context framework with the following inclusion criteria: original research in English, involving endurance athletes, systems biology approaches, and nutritional interventions or continuous glucose monitoring (CGM). Results: Fifty-two studies were included, with distance runners as the most studied cohort. Eleven studies used metagenomics, eleven CGM, ten nutrigenetics, ten metabolomics, seven multi-omics, one proteomics, one epigenomics, and one lipidomics. Over half (n = 31; 60%) were randomized controlled trials (RCTs) with generally high methodological quality. Conclusions: Most studies were proof-of-concept investigations aimed at assessing biomarkers; however, the evidence linking these biomarkers to performance, recovery, and long-term health outcomes in endurance athletes remains insufficient. Future research should focus on well-powered replicated crossover RCTs, multivariate N-of-1 clinical trials, 360-degree systems-wide approaches, and the validation of genetic impacts on nutritional interventions to refine dietary guidelines.

Systematically, this study assessed the impact of digital technologies, including social media, on health, diet, and sports, amid rising concerns and acknowledged benefits. We performed a comprehensive review of literature spanning 20 years, up to June 2024, focusing on interventions targeted at youth aged 14-29. Our initial database search identified 8,278 articles. After removing duplicates and those that failed to meet inclusion criteria, 307 articles underwent a rigorous blinded peer review process, ultimately resulted in 29 studies for synthesis. Our analysis concludes the dual impact of digital technologies on youth: although they highlight the positive potential in colouring youth health behaviors, often linked to sports, nutrition, and active lifestyles, they also pose risks due to the unregulated and misleading content, emphasizing the necessity for enhanced digital literacy and critical engagement with content. In this context, five major theme highlight this paradoxical impact together: 1) Increasing awareness, knowledge and self-efficacy, 2) Hazards, misinformation, and credibility, 3) Attitudes and behavior change, 4) Social comparison, and 5) Product promotion. Eventually, we draw attention to the urgent need for regulations and systematic content verification to protect youth from misinformation and to strengthen the credibility, trustworthiness and effectiveness of health, diet and sport related content on these technologies.

Background: Physical activity induces the production of reactive oxygen species (ROS), which, at moderate levels mediate beneficial physiological adaptations, including insulin sensitivity and enhanced antioxidant defense. However, excessive ROS production during intense exercise may exceed endogenous antioxidant capacity, leading to oxidative stress and muscle damage. Objective: This study examined the effects of 30-day high-dose omega-3 fatty acid supplementation (9 g/day) on plasma fatty acid composition and the activity of antioxidant enzymes in recreational (n = 11) and trained (n = 10) runners, with emphasis on group- and time-specific responses. Methods: Plasma levels of arachidonic acid (AA), eicosapentaenoic acid (EPA), and docosahexaenoic acid (DHA) were assessed at three time points: pre-, during, and post-supplementation period. Enzymatic activities of glutathione peroxidase (GPx), superoxide dismutase (SOD), and catalase (CAT) were measured at six time points, including before and after exercise sessions involving a 2800 m run followed by a 400 m sprint. Results: Omega-3 supplementation increased plasma EPA and DHA. In trained runners, it was associated with a transient reduction in GPx and a pronounced mid-phase decline in SOD, whereas enzyme activities remained stable in recreational runners. CAT activity did not change significantly in either group. Conclusions: Short-term high-dose omega-3 supplementation modulates antioxidant enzyme activity in a group- and time-dependent manner. The observed downregulation of GPx and SOD in trained runners may reflect altered redox signaling; however, its relevance for exercise performance remains uncertain. Further studies are warranted to elucidate the physiological and functional consequences of these findings.

This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients. We evaluated three models-GPT-4o, Llama-3 (70b), and Mixtral (8x7b)-to assess their proficiency in recognizing and breaking down complex ingredient combinations. Preliminary results indicate that while Llama-3 (70b) and GPT-4o excels in accurate decomposition, all models encounter difficulties with identifying essential elements like seasonings and oils. Despite strong overall performance, variations in accuracy and completeness were observed across models. These findings underscore LLMs' potential to enhance personalized nutrition but highlight the need for further refinement in ingredient decomposition. Future research should address these limitations to improve nutritional recommendations and health outcomes.

Background: Endurance athletes require personalized nutrition strategies to optimize performance, recovery, and training adaptations. While traditional sports nutrition guidelines provide a foundation for personalization, individual variability in metabolic responses underscores the need for precision nutrition, tailored to genetic, biological, and environmental factors. This scoping review evaluates the application of systems biology-driven sports nutrition for endurance athletes, focusing on ‘omics’ and wearable technologies. Methods: A scoping review of the literature was conducted following PRISMA guidelines across PubMed, Scopus, and Web of Science with the following inclusion criteria: original research in English, involving endurance athletes, systems biology approaches, and nutritional interventions or continuous glucose monitoring (CGM). Relevant data were extracted in a systematic way. Results: Forty-eight reports were included with running as most studied sport. Eleven reports used metabolomics, ten nutrigenetics, nine metagenomics, nine CGM, six multi-omics, one proteomics, one epigenomics, and one lipidomics. Over half (62%) were randomized controlled trials (RCTs). Most studies were proof-of-concept investigations aimed at assessing biomarkers; however, the evidence linking these biomarkers to performance, recovery, and long-term health outcomes in endurance athletes remains insufficient. Significant inter-individual variability in responses to exercise and nutritional interventions was observed. Furthermore, many studies were constrained by small sample sizes and inadequate reporting of training status. Conclusions: While evidence is limited, some of the reviewed papers suggest a potential utility of systems biology-driven nutritional recommendations for endurance athletes. Future research should focus on well-powered replicated crossover RCTs, 360-degree systems-wide approaches, and validation of genetic impacts on nutritional interventions to refine dietary guidelines.