Investigating the risk of anterior cruciate ligament rupture in female athletes

Female athletes tear their anterior cruciate ligaments at far higher rates than male athletes, yet the models used to predict injury risk are built on male anatomy and movement. This studentship will build the first computational model specifically designed to predict ACL rupture risk in female athletes, by tracking how movement changes with maturation and across the hormone cycle—factors that alter joint laxity from day to day. The problem is that existing injury-prevention tools treat female athletes as smaller versions of male athletes, ignoring real anatomical and physiological differences. Without a model that accounts for these variables, coaches and sports scientists lack reliable ways to identify who is at risk and when. If this research succeeds, it could change how female athletes train and compete. A digital twin—a computer model that simulates an individual athlete’s movement and joint stresses—could flag high-risk moments in real time, allowing targeted interventions before an injury happens. The same approach could eventually extend beyond elite sport to recreational athletes, physiotherapy, and rehabilitation, where personalised injury prediction is currently absent.