Cargando…
Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach
Deep learning (DL) is emerging as a successful technique for automatic detection and differentiation of spontaneous seizures that may otherwise be missed or misclassified. Herein, we propose a system architecture based on top-performing DL models for binary and multigroup classifications with the no...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10525492/ https://www.ncbi.nlm.nih.gov/pubmed/37760815 http://dx.doi.org/10.3390/biomedicines11092370 |
_version_ | 1785110797336182784 |
---|---|
author | Statsenko, Yauhen Babushkin, Vladimir Talako, Tatsiana Kurbatova, Tetiana Smetanina, Darya Simiyu, Gillian Lylian Habuza, Tetiana Ismail, Fatima Almansoori, Taleb M. Gorkom, Klaus N.-V. Szólics, Miklós Hassan, Ali Ljubisavljevic, Milos |
author_facet | Statsenko, Yauhen Babushkin, Vladimir Talako, Tatsiana Kurbatova, Tetiana Smetanina, Darya Simiyu, Gillian Lylian Habuza, Tetiana Ismail, Fatima Almansoori, Taleb M. Gorkom, Klaus N.-V. Szólics, Miklós Hassan, Ali Ljubisavljevic, Milos |
author_sort | Statsenko, Yauhen |
collection | PubMed |
description | Deep learning (DL) is emerging as a successful technique for automatic detection and differentiation of spontaneous seizures that may otherwise be missed or misclassified. Herein, we propose a system architecture based on top-performing DL models for binary and multigroup classifications with the non-overlapping window technique, which we tested on the TUSZ dataset. The system accurately detects seizure episodes (87.7% Sn, 91.16% Sp) and carefully distinguishes eight seizure types (95–100% Acc). An increase in EEG sampling rate from 50 to 250 Hz boosted model performance: the precision of seizure detection rose by 5%, and seizure differentiation by 7%. A low sampling rate is a reasonable solution for training reliable models with EEG data. Decreasing the number of EEG electrodes from 21 to 8 did not affect seizure detection but worsened seizure differentiation significantly: 98.24 ± 0.17 vs. 85.14 ± 3.14% recall. In detecting epileptic episodes, all electrodes provided equally informative input, but in seizure differentiation, their informative value varied. We improved model explainability with interpretable ML. Activation maximization highlighted the presence of EEG patterns specific to eight seizure types. Cortical projection of epileptic sources depicted differences between generalized and focal seizures. Interpretable ML techniques confirmed that our system recognizes biologically meaningful features as indicators of epileptic activity in EEG. |
format | Online Article Text |
id | pubmed-10525492 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-105254922023-09-28 Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach Statsenko, Yauhen Babushkin, Vladimir Talako, Tatsiana Kurbatova, Tetiana Smetanina, Darya Simiyu, Gillian Lylian Habuza, Tetiana Ismail, Fatima Almansoori, Taleb M. Gorkom, Klaus N.-V. Szólics, Miklós Hassan, Ali Ljubisavljevic, Milos Biomedicines Article Deep learning (DL) is emerging as a successful technique for automatic detection and differentiation of spontaneous seizures that may otherwise be missed or misclassified. Herein, we propose a system architecture based on top-performing DL models for binary and multigroup classifications with the non-overlapping window technique, which we tested on the TUSZ dataset. The system accurately detects seizure episodes (87.7% Sn, 91.16% Sp) and carefully distinguishes eight seizure types (95–100% Acc). An increase in EEG sampling rate from 50 to 250 Hz boosted model performance: the precision of seizure detection rose by 5%, and seizure differentiation by 7%. A low sampling rate is a reasonable solution for training reliable models with EEG data. Decreasing the number of EEG electrodes from 21 to 8 did not affect seizure detection but worsened seizure differentiation significantly: 98.24 ± 0.17 vs. 85.14 ± 3.14% recall. In detecting epileptic episodes, all electrodes provided equally informative input, but in seizure differentiation, their informative value varied. We improved model explainability with interpretable ML. Activation maximization highlighted the presence of EEG patterns specific to eight seizure types. Cortical projection of epileptic sources depicted differences between generalized and focal seizures. Interpretable ML techniques confirmed that our system recognizes biologically meaningful features as indicators of epileptic activity in EEG. MDPI 2023-08-24 /pmc/articles/PMC10525492/ /pubmed/37760815 http://dx.doi.org/10.3390/biomedicines11092370 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Statsenko, Yauhen Babushkin, Vladimir Talako, Tatsiana Kurbatova, Tetiana Smetanina, Darya Simiyu, Gillian Lylian Habuza, Tetiana Ismail, Fatima Almansoori, Taleb M. Gorkom, Klaus N.-V. Szólics, Miklós Hassan, Ali Ljubisavljevic, Milos Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach |
title | Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach |
title_full | Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach |
title_fullStr | Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach |
title_full_unstemmed | Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach |
title_short | Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach |
title_sort | automatic detection and classification of epileptic seizures from eeg data: finding optimal acquisition settings and testing interpretable machine learning approach |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10525492/ https://www.ncbi.nlm.nih.gov/pubmed/37760815 http://dx.doi.org/10.3390/biomedicines11092370 |
work_keys_str_mv | AT statsenkoyauhen automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT babushkinvladimir automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT talakotatsiana automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT kurbatovatetiana automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT smetaninadarya automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT simiyugillianlylian automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT habuzatetiana automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT ismailfatima automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT almansooritalebm automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT gorkomklausnv automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT szolicsmiklos automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT hassanali automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach AT ljubisavljevicmilos automaticdetectionandclassificationofepilepticseizuresfromeegdatafindingoptimalacquisitionsettingsandtestinginterpretablemachinelearningapproach |