CC BY-NC-ND 4.0 · Laryngorhinootologie 2019; 98(S 02): S131-S132
DOI: 10.1055/s-0039-1686389
Abstracts
Otology

Classification investigations on invasively recorded auditory evoked potentials in cochlear implant users

S Haumann
1   Medizinische Hochschule Hannover, Hannover
,
MG Bleichner
2   Carl-von-Ossietzky-Universität Oldenburg, Oldenburg
,
MJ Teschner
1   Medizinische Hochschule Hannover, Hannover
,
S Debener
2   Carl-von-Ossietzky-Universität Oldenburg, Oldenburg
,
T Lenarz
1   Medizinische Hochschule Hannover, Hannover
,
G Bauernfeind
1   Medizinische Hochschule Hannover, Hannover
› Author Affiliations
DFG Exzellenzcluster Hearing4All
 

Introduction:

A promising approach to improve cochlear implants (CI) is to use brain signals to control the device. Closing the auditory loop will allow the user passive and active control over the CI. Initial EEG studies have already shown promising results. These studies are based on the noninvasive measurement of auditory evoked potentials (AEP). For a CI controlled by brain signals implantable electrode are more convenient. Especially if the electrodes are integrated into the CI (which needs to be implanted anyway) the use of invasively recorded signals is promising. Additionally, implantation is expected to provide better signal quality and thus better classification accuracy.

Methods:

In this project three additional epidural electrodes were temporarily placed in ten patients during CI insertion. In the days after surgery, different AEPs, among others by Cortical Evoked Response Audiometry (CERA), were measured and compared to recordings with surface electrodes. Signals were recorded invasively (epidural) and with surface electrodes. Subsequently, the CERA AEPs were used for a first investigation on single-trial classification.

Results:

Data analysis from different subjects showed single-trial classification accuracies of up to 99.2% for heard vs. not heard sounds. Accuracy's of up to 89.1% were also achieved in the classification of sounds heard at different volumes. The highest classification accuracies were achieved by epidural recordings.

Conclusions:

In summary, the epidural recording approach used in this study is suitable and provides clear and well-classifiable AEP responses in CI user. These results encourage an implementation of this method into CI systems for realizing Closed-Loop-Systems.



Publication History

Publication Date:
23 April 2019 (online)

© 2019. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial-License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/).

Georg Thieme Verlag KG
Stuttgart · New York