Table 1 Descriptive data for the highlighted papers
From: Machine Learning for Understanding and Predicting Injuries in Football
No. of players | No. of injuries | Age group (years) | Injury type | Dataset time span | |
|---|---|---|---|---|---|
Rossi et al. [33] | 26 | 21 | 20–30 | Every non-contact | 23 weeks |
Naglah et al. [35] | 21 | 36 | Unreported | Every non-contact | 16 months |
López-Valenciano et al. [36] | 132 | 32 | Unreported | Lower leg muscle | Pre-season + 1 Season |
Ayala et al. [37] | 96 | 18 | Unreported | Hamstring strain | Pre-season + 1 season |
Rommers et al. [39] | 734 | 368 | 10–15 | Acute and overuse | Pre-season + 1 season |
Oliver et al. [41] | 400 | 99 | 10–18 | Non-contact lower leg | Pre-season + 1 season |
Vallance et al. [42] | 40 | 142 | 23.6–35.2 | Every non-contact | Pre-season + 1 season |
Venturelli et al. [43] | 84 | 27 | 14–18 | Thigh muscle strain | Pre-season + 1 season |
Kampakis [44] | Unreported | Unreported | Unreported | Not specified | Unreported |