Determine whether knee kinematics features analyzed using machine-learning algorithms can identify different gait profiles in knee OA patients.
3D gait kinematic data were recorded from 42 patients (Kellgren-Lawrence stages III and IV) walking barefoot at individual maximal gait speed (0.98 ± 0.34 m/s). Principal component analysis, self-organizing maps, and k-means were applied to the data to identify the most relevant and discriminative knee kinematic features and to identify gait profiles.
Four different gait profiles were identified and clinically characterized as type 1: gait with the knee in excessive varus and flexion (n = 6, 14%, increased knee adduction and increased maximum and minimum knee flexion, p < 0.01); type 2: gait with knee external rotation, either in varus or valgus (n = 11, 26%, excessive maximum and minimum external rotation, p < 0.001); type 3: gait with a stiff knee (n = 17, 40%, decreased knee flexion range of motion, p < 0.001); and type 4: gait with knee varus 'thrust' and decreased rotation (n = 8, 19%, increased and reduced range of motion in the coronal and transverse plane, respectively, p < 0.05).
In a group of patients with homogeneous Kellgren-Lawrence classification of knee OA, gait kinematics data permitted to identify four different gait profiles. These gait profiles can be a valuable tool for helping surgical decisions and treatment. To allow generalization, further studies should be carried with a larger and heterogeneous population.

Copyright © 2021 Elsevier Ltd. All rights reserved.

Author