AIRADL: A Deep Learning-Based Framework for Multimodal Physiological and Biomechanical Injury Risk Classification in Athletes

Abstract

Athlete performance and injury prevention depend on computational biology to evaluate physiological responses and biomechanics to investigate movement. Incorporating these areas with deep learning improves risk evaluation, allowing for data-driven training tactics. Conventional injury risk evaluations are frequently incorrect, depending on subjective evaluations. Existing models do not capture intricate interactions between biological and biomechanical factors, requiring a more accurate, data-driven method. Objectives: This research proposes the AIRADL (Athlete Injury Risk Assessment using Deep Learning) Framework to forecast injury risk by incorporating physiological and biomechanical data, enhancing classification accuracy, and assisting training decisions. The proposed AIRADL model is trained on the Athlete Health & Motion Analysis Dataset (AHMAD), which contains physiological data such as heart rate, oxygen level, lactate level, and muscle fatigue, in addition to biomechanical factors such as stride length, joint flexibility, and movement symmetry. The data preprocessing steps include mean imputation for missing numerical values, mode imputation for categorical values, label encoding for categorical features, Min-Max scaling for normalization, and Chi-Square feature selection to maintain the most pertinent predictors. The dataset is split into 80% training and 20% testing. A DL4J MLP Classifier is employed to learn trends and classify performance risk levels. The AIRADL framework employs a three-hidden-layer DL4J MLP architecture consisting of 64–128–64 neurons with ReLU activation, Adam optimizer, and early stopping to prevent overfitting. The Athlete Health & Motion Analysis Dataset (AHMAD), a privately collected dataset, was used for experimentation, and evaluation metrics included accuracy, F1-score, and Matthews Correlation Coefficient (MCC), which measures the strength and balance of predictions. Experimental validation confirms model stability, demonstrating consistent convergence behaviour and superior performance compared to baseline methods. The AIRADL model attained 92.3% accuracy in high-risk classification, with precision, recall, and F1-score of 91.8%, 89.6%, and 90.7%, respectively. The MCC score was 89.2%, indicating excellent predictive ability, with lactate level, muscle fatigue, and movement symmetry being important risk indicators. Conclusion: AIRADL shows deep learning's capability in athlete risk prediction and provides a powerful tool for injury prevention.