Deep learning-based electroencephalic diagnosis of tinnitus symptom
Tinnitus is a neuropathological phenomenon caused by the recognition of external sound that does not actually exist. Existing diagnostic methods for tinnitus are rather subjective and complicated medical examination procedures. The present study aimed to diagnose tinnitus using deep learning analysi...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-04-01
|
Series: | Frontiers in Human Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1126938/full |
_version_ | 1797834406426050560 |
---|---|
author | Eul-Seok Hong Hyun-Seok Kim Sung Kwang Hong Dimitrios Pantazis Dimitrios Pantazis Byoung-Kyong Min Byoung-Kyong Min |
author_facet | Eul-Seok Hong Hyun-Seok Kim Sung Kwang Hong Dimitrios Pantazis Dimitrios Pantazis Byoung-Kyong Min Byoung-Kyong Min |
author_sort | Eul-Seok Hong |
collection | DOAJ |
description | Tinnitus is a neuropathological phenomenon caused by the recognition of external sound that does not actually exist. Existing diagnostic methods for tinnitus are rather subjective and complicated medical examination procedures. The present study aimed to diagnose tinnitus using deep learning analysis of electroencephalographic (EEG) signals while patients performed auditory cognitive tasks. We found that, during an active oddball task, patients with tinnitus could be identified with an area under the curve of 0.886 through a deep learning model (EEGNet) using EEG signals. Furthermore, using broadband (0.5 to 50 Hz) EEG signals, an analysis of the EEGNet convolutional kernel feature maps revealed that alpha activity might play a crucial role in identifying patients with tinnitus. A subsequent time-frequency analysis of the EEG signals indicated that the tinnitus group had significantly reduced pre-stimulus alpha activity compared with the healthy group. These differences were observed in both the active and passive oddball tasks. Only the target stimuli during the active oddball task yielded significantly higher evoked theta activity in the healthy group compared with the tinnitus group. Our findings suggest that task-relevant EEG features can be considered as a neural signature of tinnitus symptoms and support the feasibility of EEG-based deep-learning approach for the diagnosis of tinnitus. |
first_indexed | 2024-04-09T14:38:32Z |
format | Article |
id | doaj.art-e860c3b620d64060be770ed12f8d1327 |
institution | Directory Open Access Journal |
issn | 1662-5161 |
language | English |
last_indexed | 2024-04-09T14:38:32Z |
publishDate | 2023-04-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Human Neuroscience |
spelling | doaj.art-e860c3b620d64060be770ed12f8d13272023-05-03T11:32:24ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612023-04-011710.3389/fnhum.2023.11269381126938Deep learning-based electroencephalic diagnosis of tinnitus symptomEul-Seok Hong0Hyun-Seok Kim1Sung Kwang Hong2Dimitrios Pantazis3Dimitrios Pantazis4Byoung-Kyong Min5Byoung-Kyong Min6Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of KoreaBiomedical Engineering Research Center, Asan Medical Center, Seoul, Republic of KoreaDepartment of Otolaryngology, Hallym University College of Medicine, Anyang, Republic of KoreaMcGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA, United StatesDepartment of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, United StatesDepartment of Brain and Cognitive Engineering, Korea University, Seoul, Republic of KoreaInstitute of Brain and Cognitive Engineering, Korea University, Seoul, Republic of KoreaTinnitus is a neuropathological phenomenon caused by the recognition of external sound that does not actually exist. Existing diagnostic methods for tinnitus are rather subjective and complicated medical examination procedures. The present study aimed to diagnose tinnitus using deep learning analysis of electroencephalographic (EEG) signals while patients performed auditory cognitive tasks. We found that, during an active oddball task, patients with tinnitus could be identified with an area under the curve of 0.886 through a deep learning model (EEGNet) using EEG signals. Furthermore, using broadband (0.5 to 50 Hz) EEG signals, an analysis of the EEGNet convolutional kernel feature maps revealed that alpha activity might play a crucial role in identifying patients with tinnitus. A subsequent time-frequency analysis of the EEG signals indicated that the tinnitus group had significantly reduced pre-stimulus alpha activity compared with the healthy group. These differences were observed in both the active and passive oddball tasks. Only the target stimuli during the active oddball task yielded significantly higher evoked theta activity in the healthy group compared with the tinnitus group. Our findings suggest that task-relevant EEG features can be considered as a neural signature of tinnitus symptoms and support the feasibility of EEG-based deep-learning approach for the diagnosis of tinnitus.https://www.frontiersin.org/articles/10.3389/fnhum.2023.1126938/fulltinnituselectroencephalographydiagnosisclassificationdeep learning |
spellingShingle | Eul-Seok Hong Hyun-Seok Kim Sung Kwang Hong Dimitrios Pantazis Dimitrios Pantazis Byoung-Kyong Min Byoung-Kyong Min Deep learning-based electroencephalic diagnosis of tinnitus symptom Frontiers in Human Neuroscience tinnitus electroencephalography diagnosis classification deep learning |
title | Deep learning-based electroencephalic diagnosis of tinnitus symptom |
title_full | Deep learning-based electroencephalic diagnosis of tinnitus symptom |
title_fullStr | Deep learning-based electroencephalic diagnosis of tinnitus symptom |
title_full_unstemmed | Deep learning-based electroencephalic diagnosis of tinnitus symptom |
title_short | Deep learning-based electroencephalic diagnosis of tinnitus symptom |
title_sort | deep learning based electroencephalic diagnosis of tinnitus symptom |
topic | tinnitus electroencephalography diagnosis classification deep learning |
url | https://www.frontiersin.org/articles/10.3389/fnhum.2023.1126938/full |
work_keys_str_mv | AT eulseokhong deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom AT hyunseokkim deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom AT sungkwanghong deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom AT dimitriospantazis deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom AT dimitriospantazis deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom AT byoungkyongmin deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom AT byoungkyongmin deeplearningbasedelectroencephalicdiagnosisoftinnitussymptom |