Quantifying pattern recognition- based myoelectric control of multifunctional transradial prostheses

Guanglin Li*, Aimee E. Schultz, Todd A. Kuiken

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

307 Scopus citations

Abstract

We evaluated real-time myoelectric pattern recognition control of a virtual arm by transradial amputees. Five unilateral patients performed 10 wrist and hand movements using their amputated and intact arms. In order to demonstrate the value of information from intrinsic hand muscles, this data was included in EMG recordings from the intact arm. With both arms, motions were selected in approximately 0.2 s on average, and completed in less than 1.25 s. Approximately 99% of wrist movements were completed using either arm; however, the completion rate of hand movements was significantly lower for the amputated arm (53.9\% ± 14.2\%) than for the intact arm ( 69.4\% ± 13.1\%). For the amputated arm, average classification accuracy for only 6 movementsincluding a single hand graspwas 93.1\% ± 4.1\%, compared to 84.4\% ± 7.2\% for all 10 movements. Use of 6 optimally-placed electrodes only reduced this accuracy to 91.5\% ± 4.9\%. These results suggest that muscles in the residual forearm produce sufficient myoelectric information for real-time wrist control, but not for performing multiple hand grasps. The outcomes of this study could aid the development of a practical multifunctional myoelectric prosthesis for transradial amputees, and suggest that increased EMG informationsuch as made available through targeted muscle reinnervationcould improve control of these prostheses.

Original languageEnglish (US)
Article number5378627
Pages (from-to)185-192
Number of pages8
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume18
Issue number2
DOIs
StatePublished - Apr 2010

Keywords

  • Electromyography
  • Multifunctional prosthesis
  • Pattern recognition
  • Real-time control
  • Transradial amputation

ASJC Scopus subject areas

  • Internal Medicine
  • Neuroscience(all)
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Quantifying pattern recognition- based myoelectric control of multifunctional transradial prostheses'. Together they form a unique fingerprint.

Cite this