A classification study of kinematic gait trajectories in hip osteoarthritis

Abstract The clinical evaluation of patients in hip osteoarthritis is often done using patient questionnaires. While this provides important information it is also necessary to continue developing objective measures. In this work we further investigate the studies concerning the use of 3D gait analysis to attain this goal. The gait analysis was associated with machine learning methods in order to provide a direct measure of patient control gait discrimination. The applied machine learning method was the support vector machine (SVM). Applying the SVM on all the measured kinematic trajectories, we were able to classify individual patient and control gait cycles with a mean success rate of 88%. With the use of an ROC curve to establish the threshold number of cycles necessary for a subject to be identified as a patient, this allowed for an accuracy of higher than 90% for discriminating patient and control subjects. We then went on to determine the importance of each trajectory. By ranking the capacity of each trajectory for this discrimination, we provided a guide on their order of importance in evaluating patient severity. In order to be clinically relevant, any measure of patient deficit must be compared with clinically validated scores of functional disability. In the case of hip osteoarthritis (OA), the WOMAC scores are currently one of the most widely accepted clinical scores for quantifying OA severity. The kinematic trajectories that provided the best patient–control discrimination with the SVM were found to correlate well but imperfectly with the WOMAC scores, hence indicating the presence of complementary information in the two.