Detecting the presence of anterior cruciate ligament injury based on gait dynamics disparity and neural networks

The aim of this study is to develop a new pattern recognition-based method to model and discriminate gait dynamics disparity between anterior cruciate ligament (ACL) deficient (ACL-D) knee and contralateral ACL-intact (ACL-I) knee in patients with unilateral ACL deficiency by using kinematic features and neural networks. Thereby the capabilities of these features to detect the presence of injury can be assessed. The proposed method consists of two stages. In the first (training) stage, gait analysis is performed. A two-dimensional five-link biped model used for imitating human gait locomotion is employed to demonstrate that functions containing kinematic data of lower extremities, including knee and hip flexion/extension angles and angular velocities, characterize the gait system dynamics. Knee angle-hip angle cyclograms, knee and hip angle-angular velocity phase portraits visually demonstrate the significant disparity of gait dynamics between the lower extremities of patients with unilateral ACL deficiency. Gait dynamics underlying gait patterns of ACL-D and ACL-I knees are locally accurately modeled and approximated by radial basis function (RBF) neural networks via deterministic learning theory. The derived knowledge of approximated gait dynamics is preserved in constant RBF networks. In the second (classification) stage, a bank of dynamical estimators is constructed using the preserved constant RBF networks to represent the learned training gait patterns. By comparing the set of estimators with a test gait pattern, the generated average $$L_1$$ L 1 norms of errors are taken as the disparity and classification measure between the training and test gait patterns to differentiate between ACL-D and ACL-I knees. Finally, experiments are carried out on forty-three patients to assess the effectiveness of the proposed method. By using the leave-one-out cross-validation style under normal and fast walking speed conditions, the correct classification rates for discriminating between ACL-D and ACL-I knees are reported to be 95.61 $$\%$$ % and 93.03 $$\%$$ % , respectively. Compared with other state-of-the-art methods, the results demonstrate that gait alterations in the presence of chronic ACL deficiency can be visualized through cyclograms and phase portraits, and can be detected with superior performance.