Tremor Control using DBS and Wearable Motion Sensors
Essential tremor (ET) is a nervous system (neurological) disorder that causes involuntary and rhythmic shaking. It can affect almost any part of the body, but the trembling occurs most often in the hands especially when doing simple tasks, such as drinking from a glass or tying shoelaces. The disease is usually not a dangerous condition, but it typically worsens over time and can be severe in some people. Other conditions don't cause essential tremor, although essential tremor is sometimes confused with Parkinson's disease.
Parkinson's disease which causes parkinsonian tremor (PT) is a brain disorder that leads to shaking, stiffness, and difficulty with walking, balance, and coordination. Parkinson's symptoms usually begin gradually and get worse over time. As the disease progresses, people may have difficulty walking and talking.
The main differences in these two conditions are timing of the tremor which means that ET occurs at postural or kinetic movements, while PT occurs while the patient is at rest. In addition, ET has a frequency between 6-12 Hz while that of Parkinson has 4-6 Hz.
- Detect signals from random body parts of ET and PT patients.
- Quantify these signals by calculating the features and comparing them to normal controls
- Creating a Matlab algorithm that automatically segments tremor signals and differentiates between PT and ET
- Try applying the same technique principle to DBS tremor patients for future work
We will use the BSN created at Medit to detect the tremor signals from the patients. These tremor signals are preferable to be separately recorded for each movement. These known movement recordings will be inputted to Matlab and processed according to specific features and we will use deep learning to automatically detect these signals and differentiate between the tremor types.
Universitätsklinikum RWTH Aachen, Aachen with Dr. Holtbernd