Evaluation of EMG pattern recognition for upper limb prosthesis control: a case study in comparison with direct myoelectric control.
Linda Resnik, He Helen Huang, Anna Winslow and 3 others
PMID 29544501WHAT IT FOUND
EMG pattern recognition did not beat direct myoelectric control in one transradial amputee using a 2-DOF prosthesis.
Most outcomes were similar, several favored direct control, and dexterity declined one week after pattern recognition training.
Key findings
01In the single user who completed both control conditions, EMG pattern recognition and direct myoelectric control produced very similar outcomes, with no overwhelming superiority.
02Nearly identical outcomes were reported for 75% of metrics, and about a quarter of test metrics favored direct control.
03Both subjects showed decline in dexterity one week after pattern recognition training ended.
STILL TO COME
How it was doneWhat they foundWhat it means for OTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only one participant completed the direct head-to-head comparison, so the main result is a single case. Two participants were analysed, and two of four recruited withdrew before testing; one of the two did not complete the crossover. Analyses were descriptive, not inferential, because the study was treated as a case series. All participants were already familiar with direct myoelectric control, which may have favored direct control. The prosthesis had only 2 degrees of freedom, so the comparison may not apply to 3 or more powered joints. Testing was in the laboratory, not during home use, so real-world benefit is unclear. Training stopped at a performance plateau or after a maximum of 20 hours, but participants may have needed more pattern recognition practice.
Declared interests
The supplied text lists funding from the U.S. Department of Health and Human Services Office of the Secretary, the National Science Foundation, and the U.S. Department of Veterans Affairs. It does not report author disclosures or commercial funding.
The easy way to misread this
Do not conclude that pattern recognition control is worse than direct control for all upper-limb prostheses. The comparison rested on a single participant using a 2-DOF device, and the authors said the results are preliminary.