The pathogenesis of musculoskeletal disorders is closely associated with the cumulative damage and fatigue failure behavior of fibrous connective tissues under long-term repetitive loading. However, significant technological challenges remain in real-time dynamic monitoring of ligament fatigue life, particularly the lack of efficient computational mechanics modeling frameworks and precise assessment tools adaptable to real-world movement scenarios. The multimodal integrated framework for ligament fatigue life assessment was proposed in this study. First, the high-accuracy subject-specific musculoskeletal models were developed based on individualized medical imaging data. A coupled hyperelastic-viscoelastic constitutive model was incorporated to accurately characterize the nonlinear mechanical behavior of ligamentous tissues and their fatigue damage evolution under cyclic loading. Furthermore, by integrating continuum damage mechanics theory, a time-dependent cumulative damage evolution equation was established to systematically quantify the coupling relationship between fatigue failure probability and dynamic mechanical loading. In the data-driven prediction module, an innovative deep-learning model that integrates kinematic-dynamic coupling was developed. By integrating wearable inertial measurement units, the model enables real-time inversion of ligament loading force-fatigue failure states and prediction of fatigue life. This approach effectively overcomes the limitations of traditional mechanical modeling in long-term, multi-scenario dynamic monitoring, achieving high-precision and minimally invasive fatigue life evaluation of ligaments. The proposed computational framework breaks the static-loading constraints of conventional fatigue testing, achieving the dynamic biomechanical analysis and fatigue life prediction under real movement conditions. This work not only provides novel theoretical insights into the mechanisms and modeling of ligament fatigue damage, but also provides a generalizable tool for biomechanical injury prevention, rehabilitation planning, and soft tissue fatigue analysis in the musculoskeletal system.

Genu valgum (GV) is a common lower limb deformity that may increase the risk of anterior cruciate ligament (ACL) injury. This study used OpenSim musculoskeletal modeling and kinematic analysis to investigate the mechanical responses of the ACL under fatigue in females with GV. Eight females with GV and eight healthy controls completed a running-induced fatigue protocol. Lower limb kinematic and kinetic data were collected and used to simulate stress and strain in the anteromedial ACL (A–ACL) and posterolateral ACL (P–ACL) bundles, as well as peak joint angles and knee joint stiffness. The results showed a significant interaction effect between group and fatigue condition on A–ACL stress. In the GV group, A–ACL stress was significantly higher than in the healthy group both before and after fatigue (p < 0.001) and further increased following fatigue (p < 0.001). In the pre-fatigued state, A–ACL strain was significantly higher during the late stance phase in the GV group (p = 0.036), while P–ACL strain significantly decreased post-fatigue (p = 0.005). Additionally, post-fatigue peak hip extension and knee flexion angles, as well as pre-fatigue knee abduction angles, showed significant differences between groups. Fatigue also led to substantial changes in knee flexion, adduction, abduction, and hip/knee external rotation angles within the GV group. Notably, knee joint stiffness in this group was significantly lower than in controls and decreased further post-fatigue. These findings suggest that the structural characteristics of GV, combined with exercise-induced fatigue, exacerbate A–ACL loading and compromise knee joint stability, indicating a higher risk of ACL injury in fatigued females with GV.