Neonatal seizure detection algorithms: The effect of channel count
The number of electrodes used to acquire neonatal EEG signals varies between institutions. Therefore, tools for automatic EEG analysis, such as neonatal seizure detection algorithms, need to be able to handle different electrode montages in order to find widespread use. The aim of this study was to...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2022-09-01
|
Series: | Current Directions in Biomedical Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1515/cdbme-2022-1154 |
_version_ | 1811159429421203456 |
---|---|
author | Borovac Ana Runarsson Thomas Philip Thorvardsson Gardar Gudmundsson Steinn |
author_facet | Borovac Ana Runarsson Thomas Philip Thorvardsson Gardar Gudmundsson Steinn |
author_sort | Borovac Ana |
collection | DOAJ |
description | The number of electrodes used to acquire neonatal EEG signals varies between institutions. Therefore, tools for automatic EEG analysis, such as neonatal seizure detection algorithms, need to be able to handle different electrode montages in order to find widespread use. The aim of this study was to analyse the effect of montage on neonatal seizure detector performance. A full 18-channel montage was compared to reduced 3- and 8-channel montages using a convolutional neural network for seizure detection. Sensitivity decreased by 10 - 18 % for the reduced montages while specificity was mostly unaffected. Electrode artefacts and artefacts associated with biological rhythms caused incorrect classification of nonseizure activity in some cases, but these artefacts were filtered out in the 3-channel montage. Other types of artefacts had little effect. Reduced montages result in some reduction in classifier accuracy, but the performance may still be acceptable. Recording artefacts had a limited effect on detection accuracy. |
first_indexed | 2024-04-10T05:40:58Z |
format | Article |
id | doaj.art-59223ab74d9d4934a960ced40df8b099 |
institution | Directory Open Access Journal |
issn | 2364-5504 |
language | English |
last_indexed | 2024-04-10T05:40:58Z |
publishDate | 2022-09-01 |
publisher | De Gruyter |
record_format | Article |
series | Current Directions in Biomedical Engineering |
spelling | doaj.art-59223ab74d9d4934a960ced40df8b0992023-03-06T10:24:52ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042022-09-018260460710.1515/cdbme-2022-1154Neonatal seizure detection algorithms: The effect of channel countBorovac Ana0Runarsson Thomas Philip1Thorvardsson Gardar2Gudmundsson Steinn3University of Iceland and Kvikna Medical ehf.,Reykjavik, IcelandUniversity of Iceland,Reykjavik, IcelandKvikna Medical ehf.,Reykjavik, IcelandUniversity of Iceland,Reykjavik, IcelandThe number of electrodes used to acquire neonatal EEG signals varies between institutions. Therefore, tools for automatic EEG analysis, such as neonatal seizure detection algorithms, need to be able to handle different electrode montages in order to find widespread use. The aim of this study was to analyse the effect of montage on neonatal seizure detector performance. A full 18-channel montage was compared to reduced 3- and 8-channel montages using a convolutional neural network for seizure detection. Sensitivity decreased by 10 - 18 % for the reduced montages while specificity was mostly unaffected. Electrode artefacts and artefacts associated with biological rhythms caused incorrect classification of nonseizure activity in some cases, but these artefacts were filtered out in the 3-channel montage. Other types of artefacts had little effect. Reduced montages result in some reduction in classifier accuracy, but the performance may still be acceptable. Recording artefacts had a limited effect on detection accuracy.https://doi.org/10.1515/cdbme-2022-1154seizure detectionneonatal eegreduced montage |
spellingShingle | Borovac Ana Runarsson Thomas Philip Thorvardsson Gardar Gudmundsson Steinn Neonatal seizure detection algorithms: The effect of channel count Current Directions in Biomedical Engineering seizure detection neonatal eeg reduced montage |
title | Neonatal seizure detection algorithms: The effect of channel count |
title_full | Neonatal seizure detection algorithms: The effect of channel count |
title_fullStr | Neonatal seizure detection algorithms: The effect of channel count |
title_full_unstemmed | Neonatal seizure detection algorithms: The effect of channel count |
title_short | Neonatal seizure detection algorithms: The effect of channel count |
title_sort | neonatal seizure detection algorithms the effect of channel count |
topic | seizure detection neonatal eeg reduced montage |
url | https://doi.org/10.1515/cdbme-2022-1154 |
work_keys_str_mv | AT borovacana neonatalseizuredetectionalgorithmstheeffectofchannelcount AT runarssonthomasphilip neonatalseizuredetectionalgorithmstheeffectofchannelcount AT thorvardssongardar neonatalseizuredetectionalgorithmstheeffectofchannelcount AT gudmundssonsteinn neonatalseizuredetectionalgorithmstheeffectofchannelcount |