Automatic characterization of the Parkinson disease by classifying the ipsilateral coordination and spatiotemporal gait patterns

摘要: Traditionally, the Parkinson disease is diagnosed and followed up by conventional clinical tests that are fully dependent on expert experience. The diffuse boundary between normal early stages high variability of gait patterns difficult any objective characterization this disease. An automatic herein proposed mixing different measures ipsilateral coordination spatiotemporal which then classified with a classical support vector machine. strategy was evaluated in population healthy control subjects, obtaining an average accuracy 87% for task classification.