Gaussian Processes for hearing threshold estimation using Auditory Brainstem Responses
Gaussian Processes for hearing threshold estimation using Auditory Brainstem Responses
The Auditory Brainstem Response (ABR) plays an important role in diagnosing and managing hearing loss, but can be challenging and time-consuming to measure. Test times are especially long when multiple ABR measurements are needed, e.g., when estimating hearing threshold at a range of frequencies. While many detection methods have been developed to reduce ABR test times, the majority were designed to detect the ABR at a single stimulus level and do not consider correlations in ABR waveforms across levels. These correlations hold valuable information, and can be exploited for more efficient hearing threshold estimation. This was achieved in the current work using a Gaussian Process (GP), i.e., a Bayesian approach method for non-linear regression. The function to estimate with the GP was the ABR's amplitude across stimulus levels, from which hearing threshold was ultimately inferred. Active learning rules were also designed to automatically adjust the stimulus level and efficiently locate hearing threshold. Simulation results show test time reductions of up to <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula>50% for the GP compared to a sequentially applied Hotelling's T
2 test, which does not consider correlations across ABR waveforms. A case study was also included to briefly assess the GP approach in ABR data from an adult volunteer.
Auditory brainstem responses, Auditory system, Brainstem, Correlation, Covariance matrices, Estimation, Gaussian Process, Gaussian processes, Pediatrics, active learning, hearing threshold estimation
1-17
Chesnaye, Michael A.
5f337509-3255-4322-b1bf-d4d3836b36ec
Simpson, D.M.
53674880-f381-4cc9-8505-6a97eeac3c2a
Schlittenlacher, J.
4aa19f82-bc26-4c29-b52d-0be449ad91d2
Bell, S.L.
91de0801-d2b7-44ba-8e8e-523e672aed8a
Chesnaye, Michael A.
5f337509-3255-4322-b1bf-d4d3836b36ec
Simpson, D.M.
53674880-f381-4cc9-8505-6a97eeac3c2a
Schlittenlacher, J.
4aa19f82-bc26-4c29-b52d-0be449ad91d2
Bell, S.L.
91de0801-d2b7-44ba-8e8e-523e672aed8a
Chesnaye, Michael A., Simpson, D.M., Schlittenlacher, J. and Bell, S.L.
(2023)
Gaussian Processes for hearing threshold estimation using Auditory Brainstem Responses.
IEEE Transactions on Biomedical Engineering, .
(doi:10.1109/TBME.2023.3318729).
Abstract
The Auditory Brainstem Response (ABR) plays an important role in diagnosing and managing hearing loss, but can be challenging and time-consuming to measure. Test times are especially long when multiple ABR measurements are needed, e.g., when estimating hearing threshold at a range of frequencies. While many detection methods have been developed to reduce ABR test times, the majority were designed to detect the ABR at a single stimulus level and do not consider correlations in ABR waveforms across levels. These correlations hold valuable information, and can be exploited for more efficient hearing threshold estimation. This was achieved in the current work using a Gaussian Process (GP), i.e., a Bayesian approach method for non-linear regression. The function to estimate with the GP was the ABR's amplitude across stimulus levels, from which hearing threshold was ultimately inferred. Active learning rules were also designed to automatically adjust the stimulus level and efficiently locate hearing threshold. Simulation results show test time reductions of up to <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula>50% for the GP compared to a sequentially applied Hotelling's T
2 test, which does not consider correlations across ABR waveforms. A case study was also included to briefly assess the GP approach in ABR data from an adult volunteer.
Text
Manuscript_FINAL
- Accepted Manuscript
More information
Accepted/In Press date: 11 September 2023
e-pub ahead of print date: 28 September 2023
Additional Information:
Publisher Copyright:
IEEE
Keywords:
Auditory brainstem responses, Auditory system, Brainstem, Correlation, Covariance matrices, Estimation, Gaussian Process, Gaussian processes, Pediatrics, active learning, hearing threshold estimation
Identifiers
Local EPrints ID: 486311
URI: http://eprints.soton.ac.uk/id/eprint/486311
ISSN: 0018-9294
PURE UUID: 15935a28-73b4-43dd-bc9e-25efdd785155
Catalogue record
Date deposited: 17 Jan 2024 17:33
Last modified: 17 Oct 2024 01:37
Export record
Altmetrics
Contributors
Author:
Michael A. Chesnaye
Author:
J. Schlittenlacher
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
