Time-to-Injury Forecasting in Elite Female Football: A DeepHit Survival Approach

2026-01-27

AI Summary

Current approaches to predicting soccer injuries often rely on static preseason data and binary outcomes, limiting their capacity for dynamic, individualized risk assessment. This study addresses this gap by applying the DeepHit deep survival model—used here for the first time—to predict time-to-injury absence among elite female soccer players. Leveraging longitudinal monitoring data, the model provides time-varying risk estimates and incorporates SHAP values to enhance clinical interpretability. Employing a multilayer perceptron architecture, multiple missing-data imputation strategies, and temporal cross-validation, the approach achieves a C-index of 0.762 on the SoccerMon dataset, outperforming baseline methods such as Random Forest and XGBoost. The analysis also identifies key risk factors consistent with established clinical knowledge.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: State Estimation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Injury occurrence in football poses significant challenges for athletes and teams, carrying personal, competitive, and financial consequences. While machine learning has been applied to injury prediction before, existing approaches often rely on static pre-season data and binary outcomes, limiting their real-world utility. This study investigates the feasibility of using a DeepHit neural network to forecast time-to-injury from longitudinal athlete monitoring data, while providing interpretable predictions. The analysis utilised the publicly available SoccerMon dataset, containing two seasons of training, match, and wellness records from elite female footballers. Data was pre-processed through cleaning, feature engineering, and the application of three imputation strategies. Baseline models (Random Forest, XGBoost, Logistic Regression) were optimised via grid search for benchmarking, while the DeepHit model, implemented with a multilayer perceptron backbone, was evaluated using chronological and leave-one-player-out (LOPO) validation. DeepHit achieved a concordance index of 0.762, outperforming baseline models and delivering individualised, time-varying risk estimates. Shapley Additive Explanations (SHAP) identified clinically relevant predictors consistent with established risk factors, enhancing interpretability. Overall, this study provides a novel proof of concept: survival modelling with DeepHit shows strong potential to advance injury forecasting in football, offering accurate, explainable, and actionable insights for injury prevention across competitive levels.

Problem

• injury prediction
• time-to-injury
• longitudinal data
• survival modelling
• elite female football

Innovation

• DeepHit
• time-to-injury forecasting
• survival analysis
• interpretable machine learning
• longitudinal athlete monitoring