Support vector machine classification of Parkinson's disease and essential tremor subjects based on temporal fluctuation

摘要: Tremor is a common symptom shared in both Parkinson's disease (PD) and Essential tremor (ET) subjects. The differential diagnosis of PD ET important since the realization treatment depends on specific medication. A novel feature developed based hypothesis that subject has larger fluctuation during resting than action task. signal collected using triaxial gyroscope sensor attached to subject's finger kinetic angular velocity analyzed by transforming one-dimensional two-dimensional relation its delay versions. defined as area 95% confidence ellipse covering signal. task used classification features. support vector machine classifier tested with 10-fold cross-validation. This provides perfect PD/ET 100% accuracy, sensitivity specificity.