Full Professor, Public and occupational health
Full Professor, AMS – Sports
Full Professor, APH – Health Behaviors & Chronic Diseases
Applying machine learning to identify the hamstring injury risk profile based on screening tests in elite football players
In football, the incidence of muscle injuries remains high. Machine learning approaches could add value through identification of complex multifactorial risk profiles which in turn facilitate athlete risk management. The identification of hamstring risk profiles in football players will help to build an injury risk score (web-based calculator), which is currently used in the health field throughout clinical prediction models. Those models contribute to identify athlete’s injury risk to aid prevention effort to target individual interventions in sports. Additionally, to develop more advanced predictive models we can use machine learning tools to add data over time and iterative updates to improve model’s predictive capacity.
- Health challenges
- Implementation challenges
- Technological challenges