An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model
Epilepsy as a common disease of the nervous system, with high incidence, sudden and recurrent characteristics. Therefore, timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. Epilepsy seizures...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10164022/ |
| _version_ | 1797785137507729408 |
|---|---|
| author | Xiang Lu Anhao Wen Lei Sun Hao Wang Yinjing Guo Yande Ren |
| author_facet | Xiang Lu Anhao Wen Lei Sun Hao Wang Yinjing Guo Yande Ren |
| author_sort | Xiang Lu |
| collection | DOAJ |
| description | Epilepsy as a common disease of the nervous system, with high incidence, sudden and recurrent characteristics. Therefore, timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. Epilepsy seizures is the result of temporal and spatial evolution, Existing deep learning methods often ignore its spatial features, in order to make better use of the temporal and spatial characteristics of epileptic EEG signals. We propose a CBAM-3D CNN-LSTM model to predict epilepsy seizures. First, we apply short-time Fourier transform(STFT) to preprocess EEG signals. Secondly, the 3D CNN model was used to extract the features of preictal stage and interictal stage from the preprocessed signals. Thirdly, Bi-LSTM is connected to 3D CNN for classification. Finally CBAM is introduced into the model. Different attention is given to the data channel and space to extract key information, so that the model can accurately extract interictal and pre-ictal features. Our proposed approach achieved an accuracy of 97.95%, a sensitivity of 98.40%, and a false alarm rate of 0.017 h<sup>−1</sup> on 11 patients from the public CHB-MIT scalp EEG dataset. <italic><bold>Clinical and Translational Impact Statement</bold></italic>—Timely prediction of epileptic seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. |
| first_indexed | 2024-03-13T00:50:48Z |
| format | Article |
| id | doaj.art-e3bb809b7fb641349469afa8668eb408 |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-03-13T00:50:48Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-e3bb809b7fb641349469afa8668eb4082023-07-07T23:00:04ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722023-01-011141742310.1109/JTEHM.2023.329003610164022An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM ModelXiang Lu0https://orcid.org/0000-0001-9483-9365Anhao Wen1https://orcid.org/0000-0002-6559-7341Lei Sun2Hao Wang3Yinjing Guo4https://orcid.org/0000-0003-2774-7879Yande Ren5College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, ChinaTaian Second Hospital of Traditional Chinese Medicine, Qingdao, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, ChinaCollege of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, ChinaThe Affiliated Hospital of Qingdao University, Qingdao, ChinaEpilepsy as a common disease of the nervous system, with high incidence, sudden and recurrent characteristics. Therefore, timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. Epilepsy seizures is the result of temporal and spatial evolution, Existing deep learning methods often ignore its spatial features, in order to make better use of the temporal and spatial characteristics of epileptic EEG signals. We propose a CBAM-3D CNN-LSTM model to predict epilepsy seizures. First, we apply short-time Fourier transform(STFT) to preprocess EEG signals. Secondly, the 3D CNN model was used to extract the features of preictal stage and interictal stage from the preprocessed signals. Thirdly, Bi-LSTM is connected to 3D CNN for classification. Finally CBAM is introduced into the model. Different attention is given to the data channel and space to extract key information, so that the model can accurately extract interictal and pre-ictal features. Our proposed approach achieved an accuracy of 97.95%, a sensitivity of 98.40%, and a false alarm rate of 0.017 h<sup>−1</sup> on 11 patients from the public CHB-MIT scalp EEG dataset. <italic><bold>Clinical and Translational Impact Statement</bold></italic>—Timely prediction of epileptic seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients.https://ieeexplore.ieee.org/document/10164022/CBAMEEGLSTMseizure prediction3DCNN |
| spellingShingle | Xiang Lu Anhao Wen Lei Sun Hao Wang Yinjing Guo Yande Ren An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model IEEE Journal of Translational Engineering in Health and Medicine CBAM EEG LSTM seizure prediction 3DCNN |
| title | An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model |
| title_full | An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model |
| title_fullStr | An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model |
| title_full_unstemmed | An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model |
| title_short | An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model |
| title_sort | epileptic seizure prediction method based on cbam 3d cnn lstm model |
| topic | CBAM EEG LSTM seizure prediction 3DCNN |
| url | https://ieeexplore.ieee.org/document/10164022/ |
| work_keys_str_mv | AT xianglu anepilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT anhaowen anepilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT leisun anepilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT haowang anepilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT yinjingguo anepilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT yanderen anepilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT xianglu epilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT anhaowen epilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT leisun epilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT haowang epilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT yinjingguo epilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel AT yanderen epilepticseizurepredictionmethodbasedoncbam3dcnnlstmmodel |