| Title |
|
Training load prior to injury in professional rugby league players |
|
|
| Publication Date |
|
| Author(s) |
|
| Type of document |
|
| Language |
|
| Entity Type |
|
| Publisher |
|
European College of Sport Science |
|
|
| Place of publication |
|
| UNE publication id |
|
| Abstract |
INTRODUCTION:
Injury data analysis methods have focused predominately on univariate or simple multivariate correlations between training loads (TL) and injuries. These approaches result in limited insight into the overall effect of external TL variables and a lack of reliable predictive power for injury risk. Conversely, machine learning (ML) algorithms are useful for modeling phenomena described by multidimensional data with complex (usually non-linear) relationships. The application of ML to predicting injury risk in high-performance sport is relatively limited to date. Consequently, this study examined the efficacy of applying ML to multidimensional TL in predicting injury risk in rugby league. |
|
|
| Link |
|
| Citation |
|
European College of Sports Science Database, p. 1-1 |
|
|
| Start page |
|
| End page |
|