From Markers to Models: AI Motion Analysis for ACL Injury Prevention in Female Footballers

Background: Anterior cruciate ligament (ACL) injuries disproportionately affect female football players, with rates up to 5-8 times higher than in males. Traditional marker-based motion analysis provides high-fidelity biomechanics for ACL risk screening but is lab-bound and costly. Emerging AI-enhanced markerless systems offer scalable alternatives for field-based prevention, yet comparative evidence is fragmented. Objectives: To systematically review and meta-analyze the accuracy, feasibility, and ACL risk prediction of AI-enhanced markerless versus marker-based motion analysis in female football players.Data sources: We searched PubMed, Scopus, Web of Science, SPORTDiscus, and IEEE Xplore from January 2015 to November 2025, supplemented by gray literature and hand-searching.Study eligibility criteria: Randomized controlled trials, cohort studies, and validation studies comparing AI-driven markerless (e.g., computer vision pose estimation) and marker-based (e.g., optical motion capture) systems for kinematic/kinetic outcomes in female football players aged 12-35 years. Outcomes included ACL risk metrics (e.g., knee valgus angle, ground reaction forces) and validity (e.g., RMSE). Participants and interventions: Female football athletes (amateur to elite); interventions were motion analysis approaches during tasks like cutting or landing.Study appraisal and synthesis methods: Two reviewers independently screened and extracted data using covidence.org; risk of bias assessed via ROBINS-I. Random-effects meta-analysis pooled mean differences in RMSE using inverse-variance methods; heterogeneity via I² and τ².Results: From 452 records, 18 studies (n=912 females) were included. Markerless systems showed comparable accuracy to marker-based gold standards (pooled MD RMSE 2.4° [95% CI 1.7-3.1°], I²=52%, 12 studies for knee angles). Markerless excelled in feasibility (e.g., 90% reduction in setup time). ACL risk prediction sensitivity was 86% (95% CI 78-92%) for markerless vs. 92% for marker-based (5 studies). Evidence quality was moderate (GRADE). Limitations of evidence: Few direct head-to-head trials in football-specific tasks; potential publication bias (Egger's p=0.08); underrepresentation of diverse ethnicities.Interpretation: AI-enhanced markerless motion analysis is a valid, feasible alternative to marker-based systems for ACL injury prevention screening in female football, supporting integration into programs like FIFA 11+. Hybrid approaches may optimize real-world implementation.