Classification of Phantom Finger, Hand, Wrist, and Elbow Voluntary Gestures in Transhumeral Amputees With sEMG

Abstract

Decoding finger and hand movements from sEMG electrodes placed on the forearm of transradial amputees has been commonly studied by many research groups. A few recent studies have shown an interesting phenomenon: simple correlations between distal phantom finger, hand and wrist voluntary movements and muscle activity in the residual upper arm in transhumeral amputees, i.e., of muscle groups that, prior to amputation, had no physical effect on the concerned hand and wrist joints. In this study, we are going further into the exploration of this phenomenon by setting up an evaluation study of phantom finger, hand, wrist and elbow (if present) movement classification based on the analysis of surface electromyographic (sEMG) signals measured by multiple electrodes placed on the residual upper arm of five transhumeral amputees with a controllable phantom limb who did not undergo any reinnervation surgery. We showed that with a state-of-the-art classification architecture, it is possible to correctly classify phantom limb activity (up to 14 movements) with a rather important average success (over 80% if considering basic sets of six hand, wrist and elbow movements) and to use this pattern recognition output to give online control of a device (here a graphical interface) to these transhumeral amputees. Beyond changing the way the phantom limb condition is apprehended by both patients and clinicians, such results could pave the road towards a new control approach for transhumeral amputated patients with a voluntary controllable phantom limb. This could ease and extend their control abilities of functional upper limb prosthetics with multiple active joints without undergoing muscular reinnervation surgery.

Characteristics of phantom upper limb mobility encourage phantom-mobility-based prosthesis control

“…Voluntary PLM have recently been shown to be a form of “real” motor execution 8 – 10 , with underlying neurophysiological mechanisms different from those of motor imagery 11 , 12 . The associated muscle activity varies with the type of executed PLM 9 , 11 , 13 even for different finger movements in above-elbow amputees 13 . This pattern-recognition approach has been extensively studied for below-elbow amputees whose residual limb usually contains muscles that mobilized the fingers before the amputation, and, therefore, provide an adapted measurement site together with relatively strong EMG signals.…”

“…While numerous adaptations of these approaches were made to above-elbow amputees in the 70 s/90s 14 – 16 , it is the development of targeted-muscle-reinnervation approaches 17 which has made this technique more viable and transferrable to patients 18 . Even so, several studies have recently revived this approach in amputees without targeted reinnervation, using only natural phantom-limb-mobility-related residual EMG signals 13 , 19 – 21 .…”

“…But these signals remain inevitably more complex and challenging to decode in daily life, especially without reinforcing these PLM related EMG signals through muscle reinnervation surgery 17 . Nevertheless, despite the development of more natural prosthetic control approaches based on PLM use/decoding 13 , 19 , 22 , 23 , little is known from an epidemiological point of view.…”

Voluntary phantom hand and finger movements in transhumerai amputees could be used to naturally control polydigital prostheses

“…Our approach is based on classical sEMG pattern recognition methods used in the present context to classify phantom finger and hand movements in order to have these phantom movements in real-time mimicked by a polydigital hand prosthesis. We were recently able to classify online phantom movements of elbow, wrist and hand based on the associated sEMG recordings from the residual upper-arm muscles, with an average successful classification rate over 80%, and to offer participants a real-time control over a graphical user interface through their phantom limb mobilization [15]. These preliminary results pushed us to believe that such approach could be transferred to the decoding of phantom finger activity, and used to a novel control approach of polydigital prostheses for the misconsidered upper arm amputees.…”

A Self-Selected Movement Classification Method for Forearm Via sEMG and Attitude Sensor

“…The sEMG are bioelectrical signals produced by muscle activity that contains information about various muscle activity [1][2][3] . The placement of electrodes on the muscle to extract signals from the user's muscle activity can be used to control the robot or prosthesis and can be used to assist muscle weakness and hemiplegia to control the exoskeleton for rehabilitation.…”