Pathological Gait Detection of Parkinson's Disease Using Sparse Representation

Parkinson's disease is a progressively degenerative neurological disorder which impacts the control of body movements. While there is no known permanent cure for the disorder, it is possible to monitor the progression and establish management regime that could help the medical team, patients and their family cope with the condition. Gait analysis becomes an attractive quantitative and non-invasive mechanism that can aid early detection and monitoring of the response of patients to the management schedules. In this paper, we model cycles of human gait as a sparsely represented signal using over-complete dictionary. This representation forms the basis of a classification that allows the recognition of symptomatic subjects. Experiments have been conducted using signals of vertical ground reaction force (GRF) from subjects with Parkinson's disease from the publicly available gait database (physionet.org). Our method achieved a classification accuracy of 83% in recognising pathological cases and represents a significant improvement on previously published results that use a selection of the Fourier transform coefficients as features.