98 Pivoting in a pandemic: opportunities for injury surveillance using video analysis in sport
Bibliographic record
Abstract
Introduction Prospective cohort studies represent the gold standard in injury surveillance. However, these methods require longitudinal monitoring and are highly resource intensive. We describe the use of video-analysis to inform injury prevention where no other surveillance data is available. Materials and Methods Forty-eight female varsity rugby union matches were analysed through video-analysis. A three-stage approach to informing injury prevention included match event coding, suspected injury and concussion analysis, and tackle analysis. Key stakeholder engagement at each stage and video tagging by researchers and clinicians were undertaken. To identify suspected injury and concussion, operationally defined criteria were used. These criteria were face and content validated. Four suspected injury and 15 suspected concussion criteria were used. Each coder was required to complete inter-rater reliability, using the group consensus as the gold standard response for comparison. Results 225 suspected injuries and 59 suspected concussions were identified. The median number of injury criteria met was 3/4, with medical attention being required in 81% of cases, yet only 29% required removal from the field. Median number of concussion criteria was 2/15. Medical attention was the injury criteria with the highest level of agreement between unique coders (78–100% agreement). Conclusion Video-analysis is an underused tool for capturing suspected injury/concussion events. When undertaken using clearly operationalised definitions and in consultation with medical experts, vital information can be acquired to inform prevention strategies. The implications of this are wide-ranging and offer new opportunities for surveillance and prevention in under-reported and/or under-resourced sporting environments, particularly youth and female sport.
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 | 0.008 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".