Compensation Strategies for Bioelectric Signal Changes in Chronic Selective Nerve Cuff Recordings: A Simulation Study.

Stephen Sammut,Ryan G L Koh,José Zariffa

doi:10.3390/s21020506

Abstract

Peripheral nerve interfaces (PNIs) allow us to extract motor, sensory, and autonomic information from the nervous system and use it as control signals in neuroprosthetic and neuromodulation applications. Recent efforts have aimed to improve the recording selectivity of PNIs, including by using spatiotemporal patterns from multi-contact nerve cuff electrodes as input to a convolutional neural network (CNN). Before such a methodology can be translated to humans, its performance in chronic implantation scenarios must be evaluated. In this simulation study, approaches were evaluated for maintaining selective recording performance in the presence of two chronic implantation challenges: the growth of encapsulation tissue and rotation of the nerve cuff electrode. Performance over time was examined in three conditions: training the CNN at baseline only, supervised re-training with explicitly labeled data at periodic intervals, and a semi-supervised self-learning approach. This study demonstrated that a selective recording algorithm trained at baseline will likely fail over time due to changes in signal characteristics resulting from the chronic challenges. Results further showed that periodically recalibrating the selective recording algorithm could maintain its performance over time, and that a self-learning approach has the potential to reduce the frequency of recalibration.

Highlights

The peripheral nervous system controls the flow of motor, sensory, and autonomic information between the central nervous system and other parts of the body, mediating control over a multitude of physiological functions
Once a compound action potential had been propagated through the model, measurements at all 56 channels of the simulated nerve cuff electrode were obtained, 11 of 21as illustrated in Figure 7a
We characterized expected changes in the performance of of a selective recording approach during chronic implantationsthe and evaluated strategies a selective recording approach during chronic implantations and evaluated strategies to to compensate for these changes

Summary

Introduction

The peripheral nervous system controls the flow of motor, sensory, and autonomic information between the central nervous system and other parts of the body, mediating control over a multitude of physiological functions. Bioelectric signals recorded from the nervous system can be used to create commands for neuroprosthetic devices (which interact with the nervous system to restore lost function) and to regulate the activity of the nervous system through closed-loop neuromodulation. Examples of peripheral nerve recordings in neuroprosthetic applications include decoding motor signals to control a computer cursor [1,2], control a prosthetic limb [3,4], and using sensory feedback to control a functional electrical stimulation system [5,6]. Examples in neuromodulation applications include regulating blood pressure through selective vagus nerve stimulation [7]. A major roadblock to closed-loop neuroprosthetic and neuromodulation applications is the need for techniques that can extract useful information from low-amplitude, noisy recordings [10]. Of the available peripheral nerve electrode designs [11], nerve cuff electrodes are an appealing choice as they have a relatively long history of use [12,13,14] and have been shown to be safe for long-term or chronic implantation in both animals [15,16,17,18,19,20,21] and humans [6,22]

Methods

Results

Discussion

Conclusion