Balancing efficiency and accuracy: Extreme gradient boosting and neural networks for near real-time brain deformation prediction in sports collisions

Rapid head motion during sports collisions can cause traumatic brain injury. Head motion can be measured with instrumented mouthguards and fed into finite element (FE) models to predict brain strain, a measure of brain deformation and injury. Due to the computational cost of FE models, deep neural networks have been developed for near real-time prediction. However, they are not used in pitch-side assessments due to their complexity and reliance on full kinematic data, which cannot be reliably transmitted in real-time.

We propose an extreme gradient boosting (XGBoost) model with simple input of two kinematic features. Its accuracy and efficiency were compared with two deep learning models: a multilayer perceptron (MLP) using 20 features, and a convolutional neural network (CNN) using entire kinematics. All models were trained on 1701 rugby impacts collected with mouthguards and simulated using the Imperial brain FE model. The XGBoost model predicted strain in key brain regions, while the deep learning models predicted whole-brain strain distributions.

All models showed reasonable accuracy in predicting regional strain, with R2 values 0.764–0.851 for XGBoost, 0.721–0.876 for MLP, and 0.744–0.887 for CNN. XGBoost required orders of magnitude fewer floating-point operations, and it used simple input that can be calculated on mouthguards and reliably transmitted in real-time.

This study suggests that different models can be used at different stages of brain injury assessment. We hope that the XGBoost model proposed here will lower the barriers for adopting brain strain combined with instrumented mouthguards for pitch-side assessments from elite to grassroot collision sports.