Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning
Epilepsy, a prevalent neurological disorder, profoundly affects patients’ quality of life due to the unpredictable nature of seizures. The development of a reliable and user-friendly wearable EEG system capable of detecting and predicting seizures has the potential to revolutionize epilepsy care. Ho...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/13/5805 |
_version_ | 1797590862849376256 |
---|---|
author | Hagar Gelbard-Sagiv Snir Pardo Nir Getter Miriam Guendelman Felix Benninger Dror Kraus Oren Shriki Shay Ben-Sasson |
author_facet | Hagar Gelbard-Sagiv Snir Pardo Nir Getter Miriam Guendelman Felix Benninger Dror Kraus Oren Shriki Shay Ben-Sasson |
author_sort | Hagar Gelbard-Sagiv |
collection | DOAJ |
description | Epilepsy, a prevalent neurological disorder, profoundly affects patients’ quality of life due to the unpredictable nature of seizures. The development of a reliable and user-friendly wearable EEG system capable of detecting and predicting seizures has the potential to revolutionize epilepsy care. However, optimizing electrode configurations for such systems, which is crucial for balancing accuracy and practicality, remains to be explored. This study addresses this gap by developing a systematic approach to optimize electrode configurations for a seizure detection machine-learning algorithm. Our approach was applied to an extensive database of prolonged annotated EEG recordings from 158 epilepsy patients. Multiple electrode configurations ranging from one to eighteen were assessed to determine the optimal number of electrodes. Results indicated that the performance was initially maintained as the number of electrodes decreased, but a drop in performance was found to have occurred at around eight electrodes. Subsequently, a comprehensive analysis of all eight-electrode configurations was conducted using a computationally intensive workflow to identify the optimal configurations. This approach can inform the mechanical design process of an EEG system that balances seizure detection accuracy with the ease of use and portability. Additionally, this framework holds potential for optimizing hardware in other machine learning applications. The study presents a significant step towards the development of an efficient wearable EEG system for seizure detection. |
first_indexed | 2024-03-11T01:29:30Z |
format | Article |
id | doaj.art-8deb0fd2b6de49728c9b84cd5908ef50 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T01:29:30Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-8deb0fd2b6de49728c9b84cd5908ef502023-11-18T17:26:59ZengMDPI AGSensors1424-82202023-06-012313580510.3390/s23135805Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine LearningHagar Gelbard-Sagiv0Snir Pardo1Nir Getter2Miriam Guendelman3Felix Benninger4Dror Kraus5Oren Shriki6Shay Ben-Sasson7NeuroHelp Ltd., Ramat-Gan 5252181, IsraelNeuroHelp Ltd., Ramat-Gan 5252181, IsraelNeuroHelp Ltd., Ramat-Gan 5252181, IsraelNeuroHelp Ltd., Ramat-Gan 5252181, IsraelDepartment of Neurology, Rabin Medical Center, Beilinson Hospital, Petach Tikva 4941492, IsraelSackler Faculty of Medicine, Tel Aviv University, Tel Aviv 6997801, IsraelNeuroHelp Ltd., Ramat-Gan 5252181, IsraelNeuroHelp Ltd., Ramat-Gan 5252181, IsraelEpilepsy, a prevalent neurological disorder, profoundly affects patients’ quality of life due to the unpredictable nature of seizures. The development of a reliable and user-friendly wearable EEG system capable of detecting and predicting seizures has the potential to revolutionize epilepsy care. However, optimizing electrode configurations for such systems, which is crucial for balancing accuracy and practicality, remains to be explored. This study addresses this gap by developing a systematic approach to optimize electrode configurations for a seizure detection machine-learning algorithm. Our approach was applied to an extensive database of prolonged annotated EEG recordings from 158 epilepsy patients. Multiple electrode configurations ranging from one to eighteen were assessed to determine the optimal number of electrodes. Results indicated that the performance was initially maintained as the number of electrodes decreased, but a drop in performance was found to have occurred at around eight electrodes. Subsequently, a comprehensive analysis of all eight-electrode configurations was conducted using a computationally intensive workflow to identify the optimal configurations. This approach can inform the mechanical design process of an EEG system that balances seizure detection accuracy with the ease of use and portability. Additionally, this framework holds potential for optimizing hardware in other machine learning applications. The study presents a significant step towards the development of an efficient wearable EEG system for seizure detection.https://www.mdpi.com/1424-8220/23/13/5805seizure detectionwearable EEGmachine learningcontinuous EEG monitoringelectrode configuration optimizationcomputational efficient |
spellingShingle | Hagar Gelbard-Sagiv Snir Pardo Nir Getter Miriam Guendelman Felix Benninger Dror Kraus Oren Shriki Shay Ben-Sasson Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning Sensors seizure detection wearable EEG machine learning continuous EEG monitoring electrode configuration optimization computational efficient |
title | Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning |
title_full | Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning |
title_fullStr | Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning |
title_full_unstemmed | Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning |
title_short | Optimizing Electrode Configurations for Wearable EEG Seizure Detection Using Machine Learning |
title_sort | optimizing electrode configurations for wearable eeg seizure detection using machine learning |
topic | seizure detection wearable EEG machine learning continuous EEG monitoring electrode configuration optimization computational efficient |
url | https://www.mdpi.com/1424-8220/23/13/5805 |
work_keys_str_mv | AT hagargelbardsagiv optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT snirpardo optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT nirgetter optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT miriamguendelman optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT felixbenninger optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT drorkraus optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT orenshriki optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning AT shaybensasson optimizingelectrodeconfigurationsforwearableeegseizuredetectionusingmachinelearning |