Patient training for functional use of pattern recognition-controlled prostheses.

Published on Apr 1, 2012in Jpo Journal of Prosthetics and Orthotics
· DOI :10.1097/JPO.0b013e3182515437
Ann M. Simon19
Estimated H-index: 19
Blair A. Lock19
Estimated H-index: 19
K.A. Stubblefield14
Estimated H-index: 14
Pattern recognition control systems have the potential to provide better, more reliable myoelectric prosthesis control for individuals with an upper-limb amputation. However, proper patient training is essential. We begin user training by teaching the concepts of pattern recognition control and progress to teaching how to control, use, and maintain prostheses with one or many degrees of freedom. Here we describe the training stages, with relevant case studies, and highlight several tools that can be used throughout the training process, including prosthesis-guided training (PGT)—a self-initiated, simple method of recalibrating a pattern recognition–controlled prosthesis. PGT may lengthen functional use times, potentially increasing prosthesis wear time. Using this training approach, we anticipate advancing pattern recognition control from the laboratory to the home environment and finally realizing the full potential of these control systems.
  • References (13)
  • Citations (43)
📖 Papers frequently viewed together
598 Citations
424 Citations
968 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
#1Aaron J. Young (Rehabilitation Institute of Chicago)H-Index: 22
#2Levi J. Hargrove (Rehabilitation Institute of Chicago)H-Index: 35
Last. Todd A. Kuiken (Rehabilitation Institute of Chicago)H-Index: 45
view all 3 authors...
Myoelectric pattern recognition systems for prosthesis control are often studied in controlled laboratory settings, but obstacles remain to be addressed before they are clinically viable. One important obstacle is the difficulty of maintaining system usability with socket misalignment. Misalignment inevitably occurs during prosthesis donning and doffing, producing a shift in electrode contact locations. We investigated how the size of the electrode detection surface and the placement of electrod...
117 CitationsSource
#1Ann M. SimonH-Index: 19
#2Levi J. HargroveH-Index: 35
Last. Todd A. Kuiken (NU: Northwestern University)H-Index: 45
view all 4 authors...
Despite high classification accuracies (~95%) of myoelectric control systems based on pattern recognition, how well offline measures translate to real-time closed-loop control is unclear. Recently, a real-time virtual test analyzed how well subjects completed arm motions using a multiple-degree of freedom (DOF) classifier. Although this test provided real-time performance metrics, the required task was oversimplified: motion speeds were normalized and unintended movements were ignored. We includ...
106 CitationsSource
#1Ann M. Simon (Rehabilitation Institute of Chicago)H-Index: 19
#2Levi J. Hargrove (Rehabilitation Institute of Chicago)H-Index: 35
Last. Todd A. Kuiken (Rehabilitation Institute of Chicago)H-Index: 45
view all 4 authors...
Real-time pattern recognition control is frequently affected by misclassifications. This study investigated the use of a decision-based velocity ramp that attenuated movement speed after a change in classifier decision. The goal was to improve prosthesis positioning by minimizing the effect of unintended movements. Nonamputee and amputee subjects controlled a prosthesis in real time using pattern recognition. While performing a target achievement test in a virtual environment, subjects had a sig...
76 CitationsSource
#1Guanglin Li (Rehabilitation Institute of Chicago)H-Index: 26
#2Aimee E. Schultz (Rehabilitation Institute of Chicago)H-Index: 9
Last. Todd A. Kuiken (Rehabilitation Institute of Chicago)H-Index: 45
view all 3 authors...
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 com...
259 CitationsSource
ABSTRACTThe Academy's Ninth State of the Science Conference included a group of engineers, prosthetists, and therapists brought together to discuss upper limb prosthetic outcome measures. After a presentation of the evidence based review and discussions on the history of the field and the various pe
38 CitationsSource
#1Francesco Tenore (Johns Hopkins University)H-Index: 17
#2Ander RamosH-Index: 7
Last. Nitish V. Thakor (Johns Hopkins University)H-Index: 66
view all 6 authors...
Upper limb prostheses are increasingly resembling the limbs they seek to replace in both form and functionality, including the design and development of multifingered hands and wrists. Hence, it becomes necessary to control large numbers of degrees of freedom (DOFs), required for individuated finger movements, preferably using noninvasive signals. While existing control paradigms are typically used to drive a single-DOF hook-based configurations, dexterous tasks such as individual finger movemen...
213 CitationsSource
#1Todd A. Kuiken (NU: Northwestern University)H-Index: 45
#2Guanglin Li (NU: Northwestern University)H-Index: 26
Last. Kevin Englehart (UNB: University of New Brunswick)H-Index: 24
view all 7 authors...
Context Improving the function of prosthetic arms remains a challenge, because access to the neural-control information for the arm is lost during amputation. A surgical technique called targeted muscle reinnervation (TMR) transfers residual arm nerves to alternative muscle sites. After reinnervation, these target muscles produce electromyogram (EMG) signals on the surface of the skin that can be measured and used to control prosthetic arms. Objective To assess the performance of patients with u...
598 CitationsSource
#1Pradeep Shenoy (UW: University of Washington)H-Index: 19
#2Kai J. Miller (UW: University of Washington)H-Index: 41
Last. Rajesh P. N. Rao (UW: University of Washington)H-Index: 50
view all 4 authors...
This paper presents a two-part study investigating the use of forearm surface electromyographic (EMG) signals for real-time control of a robotic arm. In the first part of the study, we explore and extend current classification-based paradigms for myoelectric control to obtain high accuracy (92-98%) on an eight-class offline classification problem, with up to 16 classifications/s. This offline study suggested that a high degree of control could be achieved with very little training time (under 10...
187 CitationsSource
ABSTRACT Since the mid-1990s, there has been considerable activity internationally on development and validation of pediatric prosthetic functional status measures for use with children with an upper extremity limb loss. In contrast, there are few prosthesis-specific functional status measures available specifically for use with adults with upper limb loss. The recent emphasis on outcome measurement across rehabilitation reflects the recognition that understanding of outcome results is an essent...
39 CitationsSource
: Target motor reinnervation can produce additional myoelectric control signals for improved powered prosthesis control. This reinnervation allows simultaneous operation of multiple functions in an externally powered prosthesis with physiologically appropriate pathways, and it provides more intuitive control than is possible with conventional myoelectric prostheses. Target sensory reinnervation has the potential to provide the sensory feed-back to the amputee that feels like it is in the missing...
73 CitationsSource
Cited By43
#1Morten B Kristoffersen (UMCG: University Medical Center Groningen)H-Index: 2
#2Andreas Franzke (UMCG: University Medical Center Groningen)H-Index: 1
Last. Raoul M. Bongers (UMCG: University Medical Center Groningen)H-Index: 19
view all 5 authors...
Human-machine interfaces have not yet advanced to enable intuitive control of multiple degrees of freedom as offered by modern myoelectric prosthetic hands. Pattern Recognition (PR) control has been proposed to make human-machine interfaces in myoelectric prosthetic hands more intuitive, but it requires the user to generate high-quality, i.e., consistent and separable, electromyogram (EMG) patterns. To generate such patterns, user training is required and has shown promising results. However, ho...
1 CitationsSource
#1Erik Haring (University of Antwerp)H-Index: 1
#2Seth Van Akeleyen (University of Antwerp)
Last. Stijn Verwulgen (University of Antwerp)H-Index: 3
view all 5 authors...
The uprising of multi-channel wearable EMG sensors combined with machine learning pattern recognition algorithms offers the possibility to control multiple degree of freedom hand prosthetics. Such human-machine interaction systems require training from the user, mostly to link gestures with underlying EMG patterns. As intended end users have a missing hand, the question arises how to train them to use myo-electric prosthetics without instructing them to perform gestures; A key element to start t...
#1Ali Hussaini (UNB: University of New Brunswick)H-Index: 3
#2Wendy Hill (UNB: University of New Brunswick)H-Index: 4
Last. Peter J. Kyberd (University of Greenwich)H-Index: 30
view all 3 authors...
Background:The refined clothespin relocation test is a test used to evaluate the performance of a prosthesis user by analysing the compensatory motions and time to complete a grasping and placement...
#1Ann M. SimonH-Index: 19
#2Kristi TurnerH-Index: 4
Last. Todd A. KuikenH-Index: 45
view all 5 authors...
Although more multi-articulating hand prostheses have become commercially available, replacing a missing hand remains challenging from a control perspective. This study investigated myoelectric direct control and pattern recognition home use of a multi-articulating hand prosthesis for individuals with a transradial amputation. Four participants were fitted with an i-limb Ultra Revolution hand and a Coapt COMPLETE CONTROL system. An occupational therapist provided training for each control style ...
4 CitationsSource
AbstractPurpose: This review was conducted to provide an overview of current literature as it relates to upper limb difference, available componentry, and prosthetic options and design. Emerging te...
#1Avinash Sharma (Johns Hopkins University)H-Index: 2
#1Avinash Sharma (Johns Hopkins University)H-Index: 3
Last. Nitish V. ThakorH-Index: 66
view all 6 authors...
Adjusting to amputation can often time be difficult for the body. Post-surgery, amputees have to wait for up to several months before receiving a properly fitted prosthesis. In recent years, there has been a trend toward quantitative outcome measures. In this paper, we developed the augmented reality (AR) version of one such measure, the Prosthetic Hand Assessment Measure (PHAM). The AR version of the PHAM - HoloPHAM, offers amputees the advantage to train with pattern recognition, at their own ...
#1Martin Aman (Medical University of Vienna)H-Index: 4
#2Matthias E. Sporer (Medical University of Vienna)H-Index: 3
Last. Oskar C. Aszmann (Medical University of Vienna)H-Index: 27
view all 8 authors...
: Even though the hand comprises only 1% of our body weight, about 30% of our central nervous systems (CNS) capacity is related to its control. The loss of a hand thus presents not only the loss of the most important tool allowing us to interact with our environment, but also leaves a dramatic sensory-motor deficit that challenges our CNS. Reconstruction of hand function is therefore not only an essential part of restoring body integrity and functional wholeness but also closes the loop of our n...
#1Linda Resnik (Providence VA Medical Center)H-Index: 25
#2Frantzy Acluche (Providence VA Medical Center)H-Index: 4
Last. Sam L. PhillipsH-Index: 5
view all 5 authors...
The DEKA Arm has multiple degrees of freedom which historically have been operated primarily by inertial measurement units (IMUs). However, the IMUs are not appropriate for all potential users; new control methods are needed. The purposes of this study were: 1) to describe usability and satisfaction of two controls methods—IMU and myoelectric pattern recognition (EMG-PR) controls—and 2) to compare ratings by control and amputation level. A total of 36 subjects with transradial (TR) or transhumer...
#1James Austin (U of A: University of Alberta)H-Index: 1
#2Ahmed W. Shehata (U of A: University of Alberta)H-Index: 4
Last. Jacqueline S. Hebert (U of A: University of Alberta)H-Index: 11
view all 5 authors...
Performance using myoelectric prostheses, especially considering recent developments in pattern recognition-based control, is significantly impacted by user training with the selected control strategy. However, minimal research has been done into the effect of functional user training with different myoelectric control strategies, since doing so typically requires training and evaluating prosthesis users with differing device configurations and customized socket fittings. Intermediate platforms ...
2 CitationsSource
#1Linda ResnikH-Index: 25
#2Frantzy AclucheH-Index: 4
Last. Shana Lieberman KlingerH-Index: 7
view all 3 authors...
INTRODUCTION: A commercially available EMG Pattern Recognition (EMG-PR) control system was adapted to interface with the multi-degree of freedom (DOF) DEKA Arm. PURPOSE: To describe users' experience of controlling the DEKA Arm using EMG-PR. METHODS: Sample: Twelve persons with upper limb amputation participated, 10 with transradial (TR), 2 with transhumeral (TH) level amputation. Ten were male, and 11 were users of a prosthesis at baselines. Design: This was a two-part study consisting of in-la...
2 CitationsSource