Finger Tapping Clinimetric Score Prediction in Parkinson's Disease Using Low-Cost Accelerometers

<table>Not all 18 features may be useful in building the model. A subset of features can be selected to maximize the predictive performance of the model.</table>

Computational Intelligence and Neuroscience

fig5

Figure 5

Figure 5: Finger Tapping Clinimetric Score Prediction in Parkinson's Disease Using Low-Cost Accelerometers 