Pattern-recognition prostheses - Rehabilitation Institute of Chicago

Skip to Content

Pattern Recognition-based Myoelectric Control of Partial-Hand Prostheses

Project Overview

Northwestern University graduate students Eric Earley and Adenike
Adewuyi explain RIC's research efforts to improve prostheses for
individuals who have lost part of their hand.

Project D2, R4

Objective: To develop a pattern recognition–based myoelectric control strategy for partial-hand prostheses. The goal is to allow control of multiple hand grasps while retaining the ability to move the wrist, thus providing significant improvement in prosthesis control and function for partial-hand amputees.


Loss of part of the hand—e.g., the thumb or multiple digits—impairs the ability to make functional hand-grasps; this causes severe disability. Myoelectric prostheses use surface electromyographic (EMG) signals to control joint movements. Small, lightweight myoelectric prostheses such as motorized fingers have recently become available for partial-hand amputees. However, obtaining appropriate EMG control signals remains a challenge.

Controlling partial-hand prostheses using EMG signals from remaining intrinsic hand muscles (i.e., muscles within the hand) or touch-sensitive switches has shown promise. In practice, however, it is very difficult to get good EMG control signals from these muscles. The intrinsic muscles are small and sometimes damaged as a result of the injury or amputation. Also, because the palm of the hand is very mobile it is difficult to keep electrodes in place. It is also challenging to fit individuals with a socket that is comfortable, well-suspended, and does not impair wrist motion. Thus few individuals can successfully use a myoelectric partial-hand prosthesis.

Pattern recognition–based myoelectric control methods have been used successfully to provide enhanced, intuitive control of upper-limb prostheses. In this approach, movement-specific patterns of EMG signals are deciphered by a computer algorithm and used to determine user intent. 

Target Population

The most frequent cause of partial-hand amputation is trauma, often a result of work- or leisure activity–related accidents or combat-related injury, thus the majority of partial-hand amputations occur in relatively young, active individuals. These individuals need prostheses that can effectively replace lost function, allowing them to maintain productive, independent lifestyles, pursue employment, and engage in active pursuits. 


We will update this page periodically with project news.

YouTube Video (February 2015)

We recently posted an interview with Northwestern University graduate students Adenike Adewuyi and Eric Earley to RIC's YouTube channel. Adewuyi and Earley are both working on this project with Dr. Hargrove. In the video, they discuss RIC's efforts to improve the control of prosthesis for individuals who have lost part of their hand.


RESNA Conference (June 2014)

TEAMM members presented at the annual Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) conference, held this year in Indianapolis from June 11-15.  You can view TEAMM's presentation about improving myoelectric control for individuals with partial-hand amputations here.

Interview with Graduate Student Adenike Adewuyi (February 2014)

Northwestern University's Feinberg School of Medicine's news department recently interviewed graduate student Adenike Adewuyi, who is collaborating with Dr. Levi Hargrove on this project.

Adewuyi is an MD/PhD candidate in Northwestern's Medical Scientist Training Program and a researcher at the Center for Bionic Medicine. Her research focuses on creating algorithms for partial hand prostheses and improving control of powered, myoelectric partial hand prostheses.

For the past three years, Adewuyi has been investigating how wrist motion affects the properties of EMG (electromyographic) signals produced by the muscles of the forearm and hand when making grasps.  

Many partial-hand amputees are still able to move their wrist; however, this motion can interfere with EMG signals produced when one moves their hand. Adewuyi's goal is to incorporate recorded wrist motion information into a pattern recognition algorithm that will allow users to operate a partial-hand prosthesis while maintaining the ability to move their wrist.

Read two interviews with Adewuyi here and here.

A separate video interview with Adewuyi from the Biomedical Engineering Society follows below.


Project Staff

Levi HargroveLevi Hargrove, PhD, Principal Investigator.  Dr. Hargrove is director of the Neural Engineering for Prosthetics & Orthotics Lab within the Center for Bionic Medicine.  He is also a Research Assistant Professor in the Departments of Physical Medicine and Rehabilitation and in Biomedical Engineering at Northwestern University. Dr. Hargrove's research interests include pattern recognition, biological signal processing, and myoelectric control of powered prostheses. He received his BSc, MSc, and PhD degrees in electrical engineering from the University of New Brunswick, Canada. 

Adenike AdewuyiAdenike Adewuyi, BS, is an MD/PhD candidate in Northwestern's Medical Scientist Training Program and a researcher at the Center for Bionic Medicine. Her research focuses on creating algorithms for partial hand prostheses and improving control of powered, myoelectric partial hand prostheses. She earned her BS in biomedical engineering from Harvard University.

Eric EarleyEric Earley, MS, is a PhD student and researcher at the Center for Bionic Medicine. He received a BS in mechanical engineering from the Colorado School of Mines, Golden, CO, in 2012, and an MS in biomedical engineering from Northwestern University. His research interests include signal processing, pattern recognition, and machine learning techniques for control of myoelectric prostheses.

Additional staff members: Annie Simon, PhD, engineering manager; Virg Mazzeo, BS, research engineer.

This research is supported by the U.S. Department of Education, National Institute on Disability and Rehabilitation Research, grant number H133E130020.