Using Machine Learning to Predict Injury Risk From Athlete Kinetic Patterns
Bibliographic record
Abstract
In recent years, the infrastructure and support for young athletes to reach collegiate and professional leagues has rapidly expanded. Such opportunities have increased the emphasis on injury prevention and performance enhancement, prompting collaboration between the sports industry and data analytics. One approach to injury risk analysis is the Sparta Score: a summative quantity introduced by Sparta Science that synthesizes the Load, Explode, and Drive subscores to predict an athlete’s vulnerability to impairment. The research in this paper explores the correlation between Sparta Score and injury risk, utilizing artificial intelligent systems and machine learning to investigate the leading variables in determining one’s score. Random forests were used to calculate feature importance for certain variables, while neural networks were employed in mapping the accuracy of predicting injury risk from combinations of the identified variables. In performing these analyses, it was discovered that there was a relatively weak correlation between Sparta Score and injury risk; rather, a component dissection of the score yielded a higher accuracy in estimating injury risk level. Within this breakdown, Jump Drive proved to be the most influential factor, by a significant margin, highlighting that a complete assessment of elements is more conclusive than a simplified score.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".