Current Directions in Biomedical Engineering (Sep 2020)

Machine Learning Techniques for Parkinson’s Disease Detection using Wearables during a Timed-up-and-Go-Test

  • Hossein Tabatabaei Seyed Amir,
  • Pedrosa David,
  • Eggers Carsten,
  • Wullstein Max,
  • Kleinholdermann Urs,
  • Fischer Patrick,
  • Sohrabi Keywan

DOI
https://doi.org/10.1515/cdbme-2020-3097
Journal volume & issue
Vol. 6, no. 3
pp. 376 – 379

Abstract

Read online

In this paper, the classification models for Idiopathic Parkinson's syndrome (iPS) detection through timed-up-and-go test performed on iPS-patients are given. The models are based on the supervised learning. The data are extracted via Myo gesture armband worn on two hands. The corresponding models are based on extracted features from signal data and raw signal data respectively. The achieved accuracy from both models are 0.91 and 0.93 with reasonable specificity and sensitivity.

Keywords