At a glance
ClinicalIndex Comparison RecordStandardized by ClinicalIndex from the ClinicalTrials.gov record · verify against the source.
User-driven Retrospectively Supervised Classification Updating (RESCU) System for Robust Upper Limb Prosthesis Control
In Brief
A clinical study evaluating RESCU and Pattern Recognition for Amputation and Upper Limb. Completed, enrolled 4 participants across 1 site.
Detailed Summary
This study will compare the use of RESCU \[Experimental\] Prosthesis with a \[Standard\] pattern recognition prosthesis in a clinical setting and in unsupervised daily activity. The protocol will follow a single case experimental design (SCED) to compensate for the limited size of the patient population. Each of the participants will use the Standard and Experimental and systems over a 35-day period. The Standard system will include at least two controllable DoFs (hand, wrist, multi-articulated hand, etc) and a commercially-available pattern recognition controller. The RESCU system will use the same components as the Standard system but will differ with respect to incorporating eight IBT Element Electrodes (as required for pattern recognition control) and the RESCU control software. The hypothesis is that pattern recognition will outperform the commercially-available control strategy for most participants on in-clinic, at-home usage, and subjective measures.
Study Details
Timeline
Interventions
Retrospectively Supervised Classification Updating (RESCU) is founded on two innovations that promise significant improvement in performance and outcome. The first is a highly robust machine intelligence algorithm, an Extreme Learning Machine with Adaptive Sparse Representation (EASRC), and the second is a novel adaptive learning algorithm and communication interface we call Nessa. We contend that these two technologies allow the prosthetic device to adapt to its user from the initial fitting through continuing, long-term use in the activities of daily living, shifting the paradigm of training from the current prospective data gathering methods to a more dynamic retrospective application.
Pattern recognition prostheses associate the patterns of activity of multiple EMG sites to the action of a prosthesis. Such strategies have historically required prospective calibration of the EMG activation patterns.