Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks
Epileptic seizures affect around 1% of people worldwide and have an enormous impact on the quality of life as well as the health of each patient. Electroencephalography (EEG) is widely used to diagnose epilepsy and detect seizures. Automatic detection and documentation of epileptic seizures using EE...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/1/20 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588370236145664 |
|---|---|
| author | Nadine El-Dajani Tim Friedrich Lutz Wilhelm Jan Baumann Rainer Surges Bernd T. Meyer |
| author_facet | Nadine El-Dajani Tim Friedrich Lutz Wilhelm Jan Baumann Rainer Surges Bernd T. Meyer |
| author_sort | Nadine El-Dajani |
| collection | DOAJ |
| description | Epileptic seizures affect around 1% of people worldwide and have an enormous impact on the quality of life as well as the health of each patient. Electroencephalography (EEG) is widely used to diagnose epilepsy and detect seizures. Automatic detection and documentation of epileptic seizures using EEG signals would help neurologists evaluate the course of disease of each patient individually. As scalp EEG systems are not suited to be worn in everyday life situations, there is a need for mobile EEG systems to permanently record EEG signals. An approach for such mobile devices consists of using behind-the-ear (BTE) electrodes, leading to a reduction in electrode channels. To address this reduction, we investigated the influence of different scalp EEG channel arrangements on the detection of epileptic seizures. Raw EEG signals have been used as input for a long short-term memory (LSTM) recurrent neural network (RNN), as well as a combination of a convolutional neural network (CNN) and LSTM to classify ictal and inter-ictal phases. When using all channels of the 10–20 EEG cap system, the CNN-LSTM model achieved a sensitivity of 73%, with fewer than two seizures being falsely detected per hour. The usage of BTE channels as input to the proposed epileptic seizure detection produced a promising sensitivity of 68% with around 10 false alarms per hour. |
| format | Article |
| id | doaj-art-be0bba9a778549bda29ce180dee5e405 |
| institution | Kabale University |
| issn | 2078-2489 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-be0bba9a778549bda29ce180dee5e4052025-01-24T13:35:10ZengMDPI AGInformation2078-24892025-01-011612010.3390/info16010020Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural NetworksNadine El-Dajani0Tim Friedrich Lutz Wilhelm1Jan Baumann2Rainer Surges3Bernd T. Meyer4Communication Acoustics, Department for Medical Physics and Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky Universität Oldenburg, 26129 Oldenburg, GermanyCommunication Acoustics, Department for Medical Physics and Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky Universität Oldenburg, 26129 Oldenburg, GermanyKlinik und Polyklinik für Epileptologie, University Clinic, 53127 Bonn, GermanyKlinik und Polyklinik für Epileptologie, University Clinic, 53127 Bonn, GermanyCommunication Acoustics, Department for Medical Physics and Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky Universität Oldenburg, 26129 Oldenburg, GermanyEpileptic seizures affect around 1% of people worldwide and have an enormous impact on the quality of life as well as the health of each patient. Electroencephalography (EEG) is widely used to diagnose epilepsy and detect seizures. Automatic detection and documentation of epileptic seizures using EEG signals would help neurologists evaluate the course of disease of each patient individually. As scalp EEG systems are not suited to be worn in everyday life situations, there is a need for mobile EEG systems to permanently record EEG signals. An approach for such mobile devices consists of using behind-the-ear (BTE) electrodes, leading to a reduction in electrode channels. To address this reduction, we investigated the influence of different scalp EEG channel arrangements on the detection of epileptic seizures. Raw EEG signals have been used as input for a long short-term memory (LSTM) recurrent neural network (RNN), as well as a combination of a convolutional neural network (CNN) and LSTM to classify ictal and inter-ictal phases. When using all channels of the 10–20 EEG cap system, the CNN-LSTM model achieved a sensitivity of 73%, with fewer than two seizures being falsely detected per hour. The usage of BTE channels as input to the proposed epileptic seizure detection produced a promising sensitivity of 68% with around 10 false alarms per hour.https://www.mdpi.com/2078-2489/16/1/20epileptic seizure detectiondeep learningbiomedical dataEEGsignal processingmobile devices |
| spellingShingle | Nadine El-Dajani Tim Friedrich Lutz Wilhelm Jan Baumann Rainer Surges Bernd T. Meyer Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks Information epileptic seizure detection deep learning biomedical data EEG signal processing mobile devices |
| title | Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks |
| title_full | Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks |
| title_fullStr | Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks |
| title_full_unstemmed | Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks |
| title_short | Patient-Independent Epileptic Seizure Detection with Reduced EEG Channels and Deep Recurrent Neural Networks |
| title_sort | patient independent epileptic seizure detection with reduced eeg channels and deep recurrent neural networks |
| topic | epileptic seizure detection deep learning biomedical data EEG signal processing mobile devices |
| url | https://www.mdpi.com/2078-2489/16/1/20 |
| work_keys_str_mv | AT nadineeldajani patientindependentepilepticseizuredetectionwithreducedeegchannelsanddeeprecurrentneuralnetworks AT timfriedrichlutzwilhelm patientindependentepilepticseizuredetectionwithreducedeegchannelsanddeeprecurrentneuralnetworks AT janbaumann patientindependentepilepticseizuredetectionwithreducedeegchannelsanddeeprecurrentneuralnetworks AT rainersurges patientindependentepilepticseizuredetectionwithreducedeegchannelsanddeeprecurrentneuralnetworks AT berndtmeyer patientindependentepilepticseizuredetectionwithreducedeegchannelsanddeeprecurrentneuralnetworks |