Injuries exert an enormous impact on athletes and teams. This is seen especially in professional soccer, with a marked negative impact on team performance and considerable costs of rehabilitation for players. Existing studies provide some preliminary understanding of which factors are mostly associated with injury risk, but scientific systematic evaluation of the potential of statistical models in forecasting injuries is still missing. Some factors raise the risk of a sport injury, but there are also elements that predispose athletes to sports injuries. The biological mechanisms involved in non-contact musculoskeletal soft tissue injuries are poorly understood. Genetic risk factors may be associated with susceptibility to injuries, and may exert marked influence on recovery times. Athletes are complex systems, and depend on internal and external factors to attain and maintain stability of their health and their performance. Organisms, participants or traits within a dynamic system adapt and change when factors within that system change. Scientists routinely predict risk in a variety of dynamic systems, including weather, political forecasting and projecting traffic fatalities and the last years have started the use of predictive models in the human health industry. We propose that the use of artificial intelligence may well help in assessing risk and help to predict the occurrence of sport injuries.
Kakavas Georgios, Malliaropoulos Nikolaos, Pruna Ricard, Maffulli Nicola
Artificial intelligence, Big data, Genes, Injury, Injury risk, Machine learning, Neural networks, Prediction, Reduction, Sports trauma