Machine learning (ML) has emerged as a powerful tool to analyze gait data, yet the “black-box” nature of many ML models hinders their clinical application. Explainable artificial intelligence (XAI) promises to enhance the interpretability and transparency of ML models, making them more suitable for clinical decision-making. This systematic review, registered on PROSPERO (CRD42024622752), assessed the application of XAI in gait analysis by examining its methods, performance, and potential for clinical utility. A comprehensive search across four electronic databases yielded 3676 unique records, of which 31 studies met inclusion criteria. These studies were categorized into model-agnostic (n = 16), model-specific (n = 12), and hybrid (n = 3) interpretability approaches. Most applied local interpretation methods such as SHAP and LIME, while others used Grad-CAM, attention mechanisms, and Layer-wise Relevance Propagation. Clinical populations studied included Parkinson’s disease, stroke, sarcopenia, cerebral palsy, and musculoskeletal disorders. Reported outcomes highlighted biomechanically relevant features such as stride length and joint angles as key discriminators of pathological gait. Overall, the findings demonstrate that XAI can bridge the gap between predictive performance and interpretability, but significant challenges remain in standardization, validation, and balancing accuracy with transparency. Future research should refine XAI frameworks and assess their real-world clinical applicability across diverse gait disorders.

Tibial shock attenuation is part of the mechanism that maintains human body stabilization during running. It is crucial to understand how shock characteristics transfer from the distal to proximal joint in the lower limb. This study aims to investigate the shock acceleration and attenuation among maximalist shoes (MAXs), minimalist shoes (MINs), and conventional running shoes (CONs) in time and frequency domains. Time-domain parameters included time to peak acceleration and peak resultant acceleration, and frequency-domain parameters contained lower (3–8 Hz) and higher (9–20 Hz) frequency power spectral density (PSD) and shock attenuation. Compared with CON and MAX conditions, MINs significantly increased the peak impact acceleration of the distal tibia (p = 0.01 and p < 0.01). Shock attenuation in the lower frequency depicted no difference but was greater in the MAXs in the higher frequency compared with the MIN condition (p < 0.01). MINs did not affect the tibial shock in both time and frequency domains at the proximal tibia. These findings may provide tibial shock information for choosing running shoes and preventing tibial stress injuries.

Anterior cruciate ligament (ACL) injury often leads to lasting deficits in joint stability and neuromuscular control, even after reconstruction. Understanding how these deficits manifest during functional tasks is essential for improving rehabilitation strategies. This study recruited 25 male participants who had undergone ACL reconstruction, with assessments conducted at 3, 6, 9, and 12 months postoperatively. Surface electromyography (sEMG) signals from ten lower-limb muscles were collected during a standardized stair-descent task, and non-negative matrix factorization (NNMF) was applied to extract the corresponding muscle synergy patterns. Paired-samples t-tests and Wilcoxon rank-sum tests were performed to evaluate differences in muscle synergies between the ACL-reconstructed and contralateral limbs. Motor modules analysis revealed a preserved four-synergy structure in both limbs, with VAF exceeding 90%. At 3–6 months postoperatively, the reconstructed limb exhibited significantly elevated activation of the medial gastrocnemius (MG), biceps femoris (BF), and rectus femoris (RF) (p < 0.005). This was accompanied by reduced contributions from the semitendinosus (ST) and lateral gastrocnemius (LG) in Synergy 4, indicative of a compensatory, quadriceps-dominant control strategy. By 9 months, partial normalization of neuromuscular coordination was observed, with interlimb symmetry across all four synergies largely restored by 12 months. These findings demonstrate that recovery of physiological neuromuscular control following ACL reconstruction is a prolonged and staged process. Longitudinal motor module analysis captures the dynamic reorganization of modular control from early compensatory patterns to restored interlimb coordination and may provide a mechanism-based indicator to guide personalized neuromuscular rehabilitation.

Background. Detecting fatigue at the early stages of a run could aid training programs in making adjustments, thereby reducing the heightened risk of injuries from overuse. The study aimed to investigate the effects of running fatigue on plantar force distribution in the dominant and nondominant feet of amateur runners. Methods. Thirty amateur runners were recruited for this study. Bilateral time-series plantar forces were employed to facilitate automatic fatigue gait recognition using convolutional neural network (CNN) and CNN-based long short-term memory network (ConvLSTM) models. Plantar force data collection was conducted both before and after a running-induced fatigue protocol using a FootScan force plate. The Keras library in Python 3.8.8 was used to train and tune deep learning models. Results. The results demonstrated that more mid-forefoot and heel force occurs during bilateral plantar and less midfoot fore force occurs in the dominant limb after fatigue ( ). The time of peak forces was significantly shortened at the midfoot and sum region of the nondominant foot, while it was delayed at the hallux region of the dominant foot ( ). In addition, the ConvLSTM model showed higher performance (Accuracy = 0.867, Sensitivity = 0.874, and Specificity = 0.859) in detecting fatigue gait than CNN (Accuracy = 0.800, Sensitivity = 0.874, and Specificity = 0.718). Conclusions. The findings of this study could offer empirical data for evaluating risk factors linked to overuse injuries in a single limb, as well as facilitate early detection of fatigued gait.

Abnormal foot postures may affect foot movement and joint loading during locomotion. Investigating foot posture alternation during running could contribute to injury prevention and foot mechanism study. This study aimed to develop feature-based and deep learning algorithms to predict foot pronation during prolonged running. Thirty-two recreational runners have been recruited for this study. Nine-axial inertial sensors were attached to the right dorsum of the foot and the vertical axis of the distal anteromedial tibia. This study employed feature-based machine learning algorithms, including support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and deep learning, i.e., one-dimensional convolutional neural networks (CNN1D), to predict foot pronation. A custom nested k-fold cross-validation was designed for hyper-parameter tuning and validating the model’s performance. The XGBoot classifier achieved the best accuracy using acceleration and angular velocity data from the foot dorsum as input. Accuracy and the area under curve (AUC) were 74.7 ± 5.2% and 0.82 ± 0.07 for the subject-independent model and 98 ± 0.4% and 0.99 ± 0 for the record-wise method. The test accuracy of the CNN1D model with sensor data at the foot dorsum was 74 ± 3.8% for the subject-wise approach with an AUC of 0.8 ± 0.05. This study found that these algorithms, specifically for the CNN1D and XGBoost model with inertial sensor data collected from the foot dorsum, could be implemented into wearable devices, such as a smartwatch, for monitoring a runner’s foot pronation during long-distance running. It has the potential for running shoe matching and reducing or preventing foot posture-induced injuries.