Cueing of Parkinson's Disease Patients by Standard Smart Devices and Deep Learning Approach

Abstract

Parkinson's disease is one of the most common neurological diseases. The patients suffer from different symptoms, e.g., tremor, bradykinesia, or walk gait disorders. One of the gait disorders which affects Parkinson's disease patients is freezing of gait, which shows as a sudden gait interruption without the ability to take the next step. It is hard to manage this symptom by medication. However, there are ways to address this symptom by applying different visual or vibration aids. This work presents a system for automatic detection and cue of freezing of gait events provided by ordinary smart devices. We used a deep learning approach to detect such events automatically. The test results and the doctors' opinions on the practical experience with the patients suggest the benefits of the provided solution.