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

TL;DR

This paper demonstrates that DeepHit neural networks can effectively forecast time-to-injury in elite female footballers using longitudinal data, providing accurate, interpretable predictions that surpass traditional models.

Contribution

It introduces a novel application of DeepHit survival analysis to football injury prediction, utilizing longitudinal data for dynamic risk estimation and interpretability.

Findings

DeepHit achieved a concordance index of 0.762, outperforming baseline models.

SHAP analysis identified key predictors aligned with known risk factors.

The approach offers individualized, time-varying injury risk estimates.

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.