An EEG-based approach for Parkinson’s disease diagnosis using capsule network

As the second most common neurodegenerative disease, Parkinson’s disease has caused serious problems worldwide. However, the pathology and mechanism of PD are still unclear, and a systematic early diagnosis and treatment method for PD has not yet been established. Many patients with PD have not been diagnosed or misdiagnosed. In this paper, we proposed an EEG-based approach to diagnosing Parkinson’s disease. The frequency band energy of the electroencephalogram (EEG) signal was mapped to the 2-dimensional image by using the interpolation method, and identified classification based on the capsule network (CapsNet) and achieved 89.34% classification accuracy for short-term EEG sections. By comparing the individual classification accuracy of different EEG frequency bands, we found that the gamma band has the highest accuracy, providing potential feature targets for the early diagnosis and clinical treatment of PD.