Decoding hand and Wrist Movement Intention From Chronic Stroke Survivors With Hemiparesis Using A Wearable, User-Centric Neural Interface

Unless this has figured out a way to disrupt the signals from spasticity this is not going to help the 30% of survivors that have spasticity.  Which if we had any leadership at all in stroke would have been one of the design requirements!

Decoding hand and Wrist Movement Intention From Chronic Stroke Survivors With Hemiparesis Using A Wearable, User-Centric Neural Interface

Author links open overlay panel

, , , ,

https://doi.org/10.1016/j.apmr.2022.01.039Get rights and content

Research Objectives

To investigate the use of the NeuroLife® Sleeve to decode hand and wrist movements in chronic stroke survivors with hemiparesis for the eventual control of assistive devices. The NeuroLife Sleeve is a wearable garment worn on the forearm with 150 embedded electrodes spread across the forearm to record high-resolution surface electromyography (sEMG).

Design

Using the NeuroLife Sleeve, EMG activity was recorded while participants attempted 12 hand and wrist movements during three separate 2-hour sessions.

Setting

All studies were conducted at Battelle's laboratories. Participants were referred from therapists in the Columbus area or recruited from local support groups.

Participants

Six chronic stroke survivors (>6 months after stroke) with upper extremity motor impairment (Upper Extremity Fugl-Meyer: 7-38).

Interventions

Participants followed a series of hand and wrist movements on a computer monitor and performed the shown movement to the best of their ability.

Main Outcome Measures

EMG decoding accuracy to correctly predict movement intention from EMG data recorded from the NeuroLife Sleeve.

Results

We demonstrate that the NeuroLife Sleeve can accurately decode 12 functional hand and wrist movements, including multiple types of grasps with 75% average accuracy across subjects in simulated real-time situations. These results highlight the utility of the NeuroLife Sleeve and decoding algorithms as potential control systems for assistive devices. Collected feedback from stroke survivors who tested the system demonstrate the user centric design of the NeuroLife Sleeve, including being simple to don and doff, comfortable, portable, and lightweight.

Conclusions

The NeuroLife Sleeve represents a user centric, platform technology to record and decode high-definition electromyography for the eventual real-time control of assistive devices.