Design and testing of a genetic algorithm neural network in the assessmentof gait patterns

It is important to be able to quantify changes in gait pattern accurately i n order to understand the clinical implications of surgery or rehabilitatio n. Although supervised feed-forward backpropagation neural networks are ver y efficient in many pattern-recognition tasks, the genetic algorithm neural network (GANN), which can search in some appropriate space, has not been u sed previously for gait-pattern recognition. This study discusses how to us e the GANN approach in gait-pattern recognition, and evaluates the complexi ty and training strategy of the particular classification problem. Both the GANN and a traditional artificial neural network (ANN) were used to classi fy the gait patterns of patients with ankle arthrodesis and normal subjects . The GANN model was able to classify subjects with recognition rates of up to 98.7%. In contrast, the ANN trained by using all possible predictor var iables was only able to classify the subjects with recognition rates of 89. 7%. It is suggested that the GANN model is more suitable to exploit the pat ient's gait pattern. The value of the neuron output can be used as an index of the difference from normal. By this means, all pathological gait patter ns may be presented quantitatively. (C) 2000 IPEM. Published by Elsevier Sc ience Ltd. All rights reserved.