Classification of gait patterns in patients with unilateral anterior cruciate ligament deficiency based on phase space reconstruction, Euclidean distance and neural networks

• Published in: Soft computing (Berlin, Germany) Germany), 2020-02, Vol.24 (3), p.1851-1868
• Main Authors: Zeng, Wei, Ismail, Shiek Abdullah, Pappas, Evangelos
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Biomechanical engineering; Biomechanics; Classification; Computational Intelligence; Control; Engineering; Euclidean geometry; Gait; Injuries; Joint and ligament injuries; Joints (anatomy); Kinematics; Knee; Learning; Ligaments; Mathematical Logic and Foundations; Mechatronics; Methodologies and Application; Neural networks; Parameters; Robotics; System dynamics; Walking
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-019-04017-z

The anterior cruciate ligament (ACL) is one of the most important structures of the knee joint which plays a significant role in controlling knee joint stability. Patients with unilateral ACL deficiency often show alterations of their gait patterns in the deficient side in comparison with the unaffected contralateral side. Gait analysis is widely used to detect biomechanical changes in the lower limbs, aiming at diagnosing ACL injury, establishing physical therapy treatments or surgery, monitoring the progression of ACL deficiency over time. This paper proposes new combined methods to classify gait patterns between ACL deficient (ACL-D) knee and contralateral ACL-intact (ACL-I) knee in patients with unilateral ACL deficiency by using phase space reconstruction (PSR), Euclidean distance (ED) and neural networks. First knee, hip and ankle kinematic parameters are extracted and phase space has been reconstructed. The properties associated with the gait system dynamics are preserved in the reconstructed phase space. For the purpose of classification of ACL-D and ACL-I knee gait patterns, three-dimensional (3D) PSR together with EDs has been used. These measured parameters show significant difference in gait dynamics between the two groups and have been utilized to form the feature set. Neural networks are then used as the classifier to distinguish between ACL-D and ACL-I knee gait patterns based on the difference of gait dynamics between the two groups. 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 95.4 % and 93.3 % , respectively. Compared with other state-of-the-art methods, the results demonstrate superior performance and support the validity of the proposed method.