Classification of gait patterns of anterior cruciate ligament deficient knees using gait analysis via deterministic learning

Abstract

Listen

Translate article

The aim of this study is to develop a new method to distinguish between gait patterns of anterior cruciate ligament (ACL) deficient knees and healthy controls with bilateral ACL-intact knees via deterministic learning. The classification approach consists of two phases: a training phase and a classification phase. In the training phase, gait features representing gait dynamics, including knee rotations and translations, are derived from the kinematic data of the knees in six-degree-of-freedom (6DOF). Gait dynamics underlying gait patterns of ACL-deficient knees and healthy controls with bilateral ACL-intact knees are locally accurately approximated by radial basis function (RBF) neural networks. The obtained knowledge of approximated gait dynamics is stored in constant RBF networks. Gait patterns of healthy controls and ACL-deficient knees are employed to constitute a training set. In the classification phase, a bank of dynamical estimators is constructed for all the training gait patterns. Prior knowledge of gait dynamics represented by the constant RBF networks is embedded in the estimators. By comparing the set of estimators with a test ACL-deficient knee gait pattern to be classified, a set of classification errors are generated. The average Li norms of the errors are taken as the classification measure between the dynamics of the training gait patterns and the dynamics of the test ACL-deficient knee gait pattern according to the smallest error principle. Finally, experiments are carried out to demonstrate that the proposed method can effectively separate the gait patterns between the groups of ACL-deficient and ACL-intact knees.