Automatic diagnosis of neuro-degenerative diseases using gait dynamics

Here an approach for the diagnosis of neuro-degenerative diseases based on gait dynamics is proposed. The proposed method uses information from a time series of stride intervals, swing intervals, stance intervals and double support intervals of stride-to-stride measures of footfall contact times using force-sensitive resistors. Different features were extracted from these time series and the best of them were selected for the diagnosis. The support vector machines using different kernels were examined for the diagnosis. The radial basis function kernel obtained the best performance for this aim. The results show that features derived from double support intervals are common effective features for the diagnosis of neuro-degenerative diseases using the gait dynamics.

► We present an automatic approach for the diagnosis of neuro-degenerative diseases. ► The method is a non-invasive way for the diagnosis of neuro-degenerative disease. ► The approach uses the information from the gait of the subjects. ► Common features have been derived from this approach for these diseases.