Artificial intelligence in ACL injury prediction and prevention: a systematic review

Abstract Background Anterior cruciate ligament (ACL) injuries are prevalent in sports, with significant physical, economic, and long-term health impacts. Artificial intelligence (AI) offers promising solutions for predicting and preventing ACL injuries through advanced data analysis. This systematic review evaluates AI applications in ACL injury prediction and prevention, focusing on techniques, performance metrics, sports contexts, and intervention effectiveness. Methods Following PRISMA 2020 guidelines, we searched PubMed, Scopus, Google Scholar, and Web of Science from inception to November 1, 2025 for peer-reviewed studies in English using AI for ACL injury prediction or prevention. Studies were excluded if they focused on other injuries or were non-original research. Two reviewers independently screened articles, extracted data (e.g., AI techniques, sample size, outcomes), and assessed methodological quality using the PROBAST + AI. Narrative synthesis was conducted due to methodological heterogeneity . Results Seven studies, published between 2019 and 2024, were included, involving 5–880 participants (age range 13–22.8 years) across sports like basketball, handball, and soccer. AI techniques included machine learning (e.g., support vector machines, random forest) and deep learning (e.g., convolutional neural networks), with applications in risk prediction and biomechanical assessment. Predictive models achieved accuracies of 79.5–96% and AUCs of 0.63–0.85, while prevention-focused studies reported high validity (e.g., R 2 : 0.9947–0.9992). Input data ranged from biomechanical parameters to video-based knee angles. PROBAST + AI demonstrated low ROB, indicating robust methodological quality for development. Conclusion AI demonstrates significant potential in predicting ACL injury risk and informing prevention strategies through biomechanical and kinematic analyses. However, small sample sizes, heterogeneous methodologies, and practical barriers (e.g., equipment costs) limit clinical adoption. Future research should focus on larger, diverse cohorts and standardized protocols to enhance generalizability and implementation. Registry number CRD420251230914.