Who is going to get hurt? Predicting injuries in professional soccer

Abstract

Injury prevention has a fundamental role in professional soccer due to the high cost of recovery for players and the strong influence of injuries on a club’s performance. In this paper we provide a predictive model to prevent injuries of soccer players using a multidimensional approach based on GPS measurements and machine learning. In an evolutive scenario, where a soccer club starts collecting the data for the first time and updates the predictive model as the season goes by, our approach can detect around half of the injuries, allowing the soccer club to save 70% of a season’s economic costs related to injuries. The proposed approach can be a valuable support for coaches, helping the soccer club to reduce injury incidence, save money and increase team performance.

Full text

Who is going to get hurt?
Predicting injuries in professional soccer
Luca Pappalardo -@lucpappalard
Department of Computer Science - University of Pisa

Injury Prediction

Injury Prediction

188,058,072 €
24,360
days of absence
16.23%
of season absence
Injury Prediction

“[…] any illness related to training load
are commonly viewed as preventable”
Gabbett, 2016
Injury Prediction

Data Collection
26 players
6central backs
4full backs
7middlefields
8wingers
2strikers
23 weeks
GPS portable (STATSports Viper
)

Training features Player features
Total Distance
High Speed Running (> 19.8 km/h)
Metabolic Distance (> 20W/kg)
High Metabolic Load Distance (> 25.5 W/Kg)
High Metabolic Load Distance per minute
Explosive Distance (> 25 W/kg < 19.8 Km/h)
Accelerations > 2m/s2
Accelerations > 3m/s2
Decelerations > 2m/s2
Decelerations > 3m/s2
Dynamic Stress Load (> 2g)
Fatigue Index
(Dynamic Stress Load/
Speed Intensity)
Age
Height
Weight
Role
Previous injuries

State of the art - ACWR
acute workload (7 days)
chronic workload (28 days)
monodimensional methods
ACWR =

high recall > 90%
low precision < 6%

multidimensional approach

16 weeks
Length of learning period

a practical tool
for coaches

Real-world scenario

In summary
From 6% to 94% precision
Interpretable rules for coaches
16 weeks needed for training
> 50% injuries detected
https://arxiv.org/pdf/1705.08079.pdf

Thanks for your attention
Luca Pappalardo
@lucpappalard
Department of Computer Science
University of Pisa
www.sobigdata.eu