Noting that reliable and accurate control of multi-grip hands remains challenging, researchers conducted a study investigating participants’ at-home control and use of a prosthesis under pattern recognition and direct control. At the conclusion, the users demonstrated broader use of a variety grips at home and significant improvements in the Assessment of Capacity for Myoelectric Control outcome measure while controlling their prosthesis with pattern recognition compared to direct control.
Eleven people with unilateral transradial amputations were fitted with and trained to use an Ă–ssur i-Limb Ultra Revolution with Coapt Complete Control system. They participated in two eight-week home trials using the hand under myoelectric direct and pattern recognition control in a randomized order. All fittings and study testing were conducted at the at the Shirley Ryan AbilityLab and Walter Reed National Military Medical Center.
Offline analysis of calibration data showed that users had 81.5 percent accuracy across a range of three to five grips. Although EMG signal noise was identified during some calibrations, overall EMG quality was sufficient to provide users with control performance at or better than direct control, the study said.
At-home pattern recognition calibration data revealed that although signal noise and user timing issues were identified on some calibrations, overall EMG quality was sufficient to provide users with control performance at or better than direct control, and provided a more accurate story of how well EMG signals can be maintained during true daily use.
Additionally, the authors wrote, the calibration sessions highlighted an opportunity for near real-time analysis and user feedback that could provide additional information to resolve device or user errors and/or accelerate user training.
The open-access study, “User performance with a transradial multi-articulating hand prosthesis during pattern recognition and direct control home use,” was published in IEEE Transactions on Neural Systems and Rehabilitation Engineering.