Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SoccerGuard: Investigating Injury Risk Factors for Professional Soccer Players with Machine Learning

Finn Bartels, Lu Xing, Cise Midoglu, Matthias Boeker, Toralf Kirsten, Pål Halvorsen

TL;DR

FootballGuard, a novel framework for predicting injuries in women's soccer using Machine Learning (ML), is presented, which can ingest data from multiple sources, including subjective wellness and training load reports from players, objective GPS sensor measurements, third-party player statistics, and injury reports verified by medical personnel.

Abstract

We present SoccerGuard, a novel framework for predicting injuries in women's soccer using Machine Learning (ML). This framework can ingest data from multiple sources, including subjective wellness and training load reports from players, objective GPS sensor measurements, third-party player statistics, and injury reports verified by medical personnel. We experiment with a number of different settings related to synthetic data generation, input and output window sizes, and ML models for prediction. Our results show that, given the right configurations and feature combinations, injury event prediction can be undertaken with considerable accuracy. The optimal results are achieved when input windows are reduced and larger combined output windows are defined, in combination with an ideally balanced data set. The framework also includes a dashboard with a user-friendly Graphical User Interface (GUI) to support interactive analysis and visualization.

SoccerGuard: Investigating Injury Risk Factors for Professional Soccer Players with Machine Learning

TL;DR

FootballGuard, a novel framework for predicting injuries in women's soccer using Machine Learning (ML), is presented, which can ingest data from multiple sources, including subjective wellness and training load reports from players, objective GPS sensor measurements, third-party player statistics, and injury reports verified by medical personnel.

Abstract

We present SoccerGuard, a novel framework for predicting injuries in women's soccer using Machine Learning (ML). This framework can ingest data from multiple sources, including subjective wellness and training load reports from players, objective GPS sensor measurements, third-party player statistics, and injury reports verified by medical personnel. We experiment with a number of different settings related to synthetic data generation, input and output window sizes, and ML models for prediction. Our results show that, given the right configurations and feature combinations, injury event prediction can be undertaken with considerable accuracy. The optimal results are achieved when input windows are reduced and larger combined output windows are defined, in combination with an ideally balanced data set. The framework also includes a dashboard with a user-friendly Graphical User Interface (GUI) to support interactive analysis and visualization.

Paper Structure

This paper contains 27 sections, 6 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Athlete Monitoring
  4. Injury Analysis, Prediction, and Prevention
  5. Datasets
  6. SoccerMon
  7. WyScout Reports
  8. Injury Reports
  9. Synthetic Data
  10. Proposed Framework
  11. Preprocessing Block
  12. Data Source and Feature Selection
  13. Distributed Preprocessing
  14. Comprehensive Preprocessing
  15. Automated Machine Learning Block
  16. ...and 12 more sections

Figures (6)

  • Figure 1: The Preprocessing Block is comprised of two distinct preprocessing blocks. The first is the distributed preprocessing of the raw data, and the second is a comprehensive preprocessing of the temporary feature store.
  • Figure 2: The Automated Machine Learning Block consisting of two pipelines for training individual models on real data and training on both real and synthetic data.
  • Figure 3: Underlying pipeline of the /web application: Soccer Dashboard.
  • Figure 4: Soccer Dashboard: An overview of the matches, training sessions and injuries by date and player for the entire team.
  • Figure 5: Soccer Dashboard: A detailed view on the trend of a selected feature for a selected player including highlighted injuries by date.
  • ...and 1 more figures