Data-driven computing ligament loading mechanisms: integration of the computational ligament mechanics models with deep learning

Ankle injuries account for more than 25% of sports-related injuries. However, there is a lack of computational mechanics modeling and assessment tools for the ligament loading mechanism (LLM) caused by ankle injury. This study combines medical imaging data to construct the subject-specific ankle musculoskeletal model, which considers the subject’s individualized characteristics and ligamentous attributes. Furthermore, we developed the structural constitutive model to restore the nonlinear short-term viscoelastic properties of the ligament-dense connective tissue, which can more realistically revert the LLM and reveal the mechanical properties of ankle injury. Based on the computational ligament mechanics (CLM) model, we developed a deep learning-based prediction model to predict LLM by CLM data-driven modeling. The modeling simulation results are highly consistent with the calculation results from the dual fluoroscopic imaging system, which demonstrated that the CLM model has high accuracy. The data-driven modeling performs exceptionally well in predicting ligament loading forces. The findings indicate that the constructed CLM data-driven model has the potential to enhance the accuracy and safety of ankle rehabilitation robots, while also providing personalized, dynamically adjusted rehabilitation training programs. The proposed comprehensive solutions would bring benefits to more patients with sports injuries and the general rehabilitation population, and promote the development and advancement of the research field of CLM and biomechanical variable prediction.