Key result
An AI-guided personalized training program significantly reduced injury incidence to 10% compared to 36.7% with traditional training (RR 3.67) and improved functional movement and athletic performance in adolescent soccer players.
Why the study?
AI-guided training provides a personalized approach using real-time data to optimize performance and reduce injury risk, but its effects compared with traditional training in adolescent football players needed evaluation.
Does a 12-week AI-guided personalized training program improve performance metrics and reduce injury incidence in adolescent football players compared to traditional coach-led training?
RCT (n=60)
simple randomization
No
Does a 12-week AI-guided personalized training program improve performance metrics and reduce injury incidence in adolescent football players compared to traditional coach-led training?
Relative Risk: 3.67
Absolute Event Rate: 10% vs 36.7%
Absolute Risk Reduction: 26.7%
Number Needed to Treat: 4
p-value: p=0.034
AI-guided personalized training significantly improves athletic performance and reduces injury risk in adolescent football players compared to traditional coach-led training.
AI-guided training may boost performance and lower injury rates in adolescent soccer players; extends RCT evidence for personalized youth training.
Objective Artificial intelligence (AI)-guided training methods provide a personalized approach, leveraging real-time physiological and biomechanical data to optimize performance and reduce injury risk. The present research compared a 12-week AI-guided personalized training program with traditional coach-led training on performance metrics and injury incidence in adolescent football players. Methods A randomized controlled trial (RCT) was conducted with 60 adolescent athletes (ages 14–17 years) recruited from a football academy. Pre- and post-intervention performance was assessed using the Functional Movement Screen (FMS), 20 m sprint, T-test (agility), and countermovement jump (CMJ), while injury incidence was monitored by a certified physiotherapist. Results The AI-guided group demonstrated significantly greater improvements than the control group in FMS scores (+20%), sprint time (−4.93%), agility (−6.48%), and CMJ height (+11.86%), with large effect sizes (d = 0.88–1.42). Injury incidence was significantly lower in the AI group (10%) compared with the control group (36.7%) (p = .034; risk ratio = 3.67; 95% Confidence Interval). Conclusion These findings highlight the efficacy of AI-driven training in enhancing athletic performance and reducing injury risk among adolescent athletes, emphasizing the value of personalized, data-informed approaches over traditional methods. Further research with larger cohorts and extended follow-ups is recommended to validate these results across diverse sports populations.
No takes yet. Share an insight, caveat, or question.
Mukta et al. (2025) conducted an RCT in Adolescent soccer players (n=60). AI-guided personalized training program vs. Traditional coach-led training was evaluated on Injury incidence (RR 3.67, p=0.034). An AI-guided personalized training program significantly reduced injury incidence to 10% compared to 36.7% with traditional training (RR 3.67) and improved functional movement and athletic performance in adolescent soccer players.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: