Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization
Power spectrum analysis is one of the effective tools for classifying epileptic signals based on electroencephalography (EEG) recordings. However, the conflation of periodic and aperiodic components within the EEG may presents an obstacle to epilepsy detection or prediction. In this paper, we explor...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10255642/ |
| _version_ | 1797661545502605312 |
|---|---|
| author | Shan Liu Jiang Wang Shanshan Li Lihui Cai |
| author_facet | Shan Liu Jiang Wang Shanshan Li Lihui Cai |
| author_sort | Shan Liu |
| collection | DOAJ |
| description | Power spectrum analysis is one of the effective tools for classifying epileptic signals based on electroencephalography (EEG) recordings. However, the conflation of periodic and aperiodic components within the EEG may presents an obstacle to epilepsy detection or prediction. In this paper, we explored the significance of the periodic and aperiodic components of the EEG power spectrum for the detection and prediction of epilepsy respectively. We use a power spectrum density parameterization method to separate the periodic and aperiodic components of the signals, and validate their roles in epilepsy detection and prediction on two public datasets. The average classification accuracy of the periodic and aperiodic components for 10 clinical tasks on the Bonn EEG database were 73.9% and 96.68%, respectively, and increases to 98.88% when combined. For 22 patients on the CHB-MIT Long-term EEG database, the combined features achieve an average detection accuracy of 99.95% and successfully predict all seizures with low false prediction rates. We conclude that both the periodic and aperiodic components of the EEG power spectrum contributed to discriminating different stages of epilepsy, but the aperiodic neural activity played a decisive role in classification. This discovery has significant implications for diagnosing epileptic seizures and providing personalized brain activity information to improve the accuracy and efficiency of epilepsy detection. |
| first_indexed | 2024-03-11T18:46:07Z |
| format | Article |
| id | doaj.art-e515f4cccc904d93b0c75e84a9539845 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-11T18:46:07Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-e515f4cccc904d93b0c75e84a95398452023-10-11T23:00:04ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01313884389410.1109/TNSRE.2023.331709310255642Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density ParameterizationShan Liu0https://orcid.org/0009-0003-1846-7653Jiang Wang1https://orcid.org/0000-0002-2189-8003Shanshan Li2https://orcid.org/0000-0002-5991-1824Lihui Cai3https://orcid.org/0000-0002-3466-8573School of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin, ChinaSchool of Information Technology Engineering, Tianjin University of Technology and Education, Tianjin, ChinaSchool of Life Sciences, Tiangong University, Tianjin, ChinaPower spectrum analysis is one of the effective tools for classifying epileptic signals based on electroencephalography (EEG) recordings. However, the conflation of periodic and aperiodic components within the EEG may presents an obstacle to epilepsy detection or prediction. In this paper, we explored the significance of the periodic and aperiodic components of the EEG power spectrum for the detection and prediction of epilepsy respectively. We use a power spectrum density parameterization method to separate the periodic and aperiodic components of the signals, and validate their roles in epilepsy detection and prediction on two public datasets. The average classification accuracy of the periodic and aperiodic components for 10 clinical tasks on the Bonn EEG database were 73.9% and 96.68%, respectively, and increases to 98.88% when combined. For 22 patients on the CHB-MIT Long-term EEG database, the combined features achieve an average detection accuracy of 99.95% and successfully predict all seizures with low false prediction rates. We conclude that both the periodic and aperiodic components of the EEG power spectrum contributed to discriminating different stages of epilepsy, but the aperiodic neural activity played a decisive role in classification. This discovery has significant implications for diagnosing epileptic seizures and providing personalized brain activity information to improve the accuracy and efficiency of epilepsy detection.https://ieeexplore.ieee.org/document/10255642/Electroencephalography (EEG)power spectral density (PSD)parameterizationepileptic detectionepileptic prediction |
| spellingShingle | Shan Liu Jiang Wang Shanshan Li Lihui Cai Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization IEEE Transactions on Neural Systems and Rehabilitation Engineering Electroencephalography (EEG) power spectral density (PSD) parameterization epileptic detection epileptic prediction |
| title | Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization |
| title_full | Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization |
| title_fullStr | Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization |
| title_full_unstemmed | Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization |
| title_short | Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization |
| title_sort | epileptic seizure detection and prediction in eegs using power spectra density parameterization |
| topic | Electroencephalography (EEG) power spectral density (PSD) parameterization epileptic detection epileptic prediction |
| url | https://ieeexplore.ieee.org/document/10255642/ |
| work_keys_str_mv | AT shanliu epilepticseizuredetectionandpredictionineegsusingpowerspectradensityparameterization AT jiangwang epilepticseizuredetectionandpredictionineegsusingpowerspectradensityparameterization AT shanshanli epilepticseizuredetectionandpredictionineegsusingpowerspectradensityparameterization AT lihuicai epilepticseizuredetectionandpredictionineegsusingpowerspectradensityparameterization |