Multimodal assessment of Parkinson’s disease: a deep learning approach
J. C. Vasquez-Correa, T. Arias-Vergara, J. R. Orozco-Arroyave, B. Eskofier, J. Klucken, E. Noth
This work aims to model difficulties in starting or to stoping movements in speech, handwriting, and gait and use those transitions to train convolutional neural networks to classify patients and healthy subjects. The subjects performed a total of 14 tasks divided into writing and drawing tasks on a tablet that captured six different signals: x-position, yposition, in-air movement, azimuth, altitude, and pressure.
Tags: Parkinson's disease