Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction
Epilepsy is the second common neurological disorder after headache, accurate and reliable prediction of seizures is of great clinical value. Most epileptic seizure prediction methods consider only the EEG signal or extract and classify the features of EEG and ECG signals separately, the improvement...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2023.1172987/full |
| _version_ | 1827954150588022784 |
|---|---|
| author | Yong Yang Yong Yang Yong Yang Xiaolin Qin Han Wen Feng Li Xiaoguang Lin Xiaoguang Lin |
| author_facet | Yong Yang Yong Yang Yong Yang Xiaolin Qin Han Wen Feng Li Xiaoguang Lin Xiaoguang Lin |
| author_sort | Yong Yang |
| collection | DOAJ |
| description | Epilepsy is the second common neurological disorder after headache, accurate and reliable prediction of seizures is of great clinical value. Most epileptic seizure prediction methods consider only the EEG signal or extract and classify the features of EEG and ECG signals separately, the improvement of prediction performance from multimodal data is not fully considered. In addition, epilepsy data are time-varying, with differences between each episode in a patient, making it difficult for traditional curve-fitting models to achieve high accuracy and reliability. In order to improve the accuracy and reliability of the prediction system, we propose a novel personalized approach based on data fusion and domain adversarial training to predict epileptic seizures using leave-one-out cross-validation, which achieves an average accuracy, sensitivity and specificity of 99.70, 99.76, and 99.61%, respectively, with an average error alarm rate (FAR) of 0.001. Finally, the advantage of this approach is demonstrated by comparison with recent relevant literature. This method will be incorporated into clinical practice to provide personalized reference information for epileptic seizure prediction. |
| first_indexed | 2024-04-09T14:25:41Z |
| format | Article |
| id | doaj.art-0982ad56d33540f58a43adb5948c9edb |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-04-09T14:25:41Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-0982ad56d33540f58a43adb5948c9edb2023-05-04T04:13:23ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882023-05-011710.3389/fncom.2023.11729871172987Patient-specific approach using data fusion and adversarial training for epileptic seizure predictionYong Yang0Yong Yang1Yong Yang2Xiaolin Qin3Han Wen4Feng Li5Xiaoguang Lin6Xiaoguang Lin7Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, Sichuan, ChinaChongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, ChinaChongqing School, University of Chinese Academy of Sciences, Chongqing, ChinaChengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, Sichuan, ChinaChengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu, Sichuan, ChinaDepartment of Neurology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, ChinaChongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, ChinaChongqing School, University of Chinese Academy of Sciences, Chongqing, ChinaEpilepsy is the second common neurological disorder after headache, accurate and reliable prediction of seizures is of great clinical value. Most epileptic seizure prediction methods consider only the EEG signal or extract and classify the features of EEG and ECG signals separately, the improvement of prediction performance from multimodal data is not fully considered. In addition, epilepsy data are time-varying, with differences between each episode in a patient, making it difficult for traditional curve-fitting models to achieve high accuracy and reliability. In order to improve the accuracy and reliability of the prediction system, we propose a novel personalized approach based on data fusion and domain adversarial training to predict epileptic seizures using leave-one-out cross-validation, which achieves an average accuracy, sensitivity and specificity of 99.70, 99.76, and 99.61%, respectively, with an average error alarm rate (FAR) of 0.001. Finally, the advantage of this approach is demonstrated by comparison with recent relevant literature. This method will be incorporated into clinical practice to provide personalized reference information for epileptic seizure prediction.https://www.frontiersin.org/articles/10.3389/fncom.2023.1172987/fullseizure predictionEEGECGdata fusionadversarial training |
| spellingShingle | Yong Yang Yong Yang Yong Yang Xiaolin Qin Han Wen Feng Li Xiaoguang Lin Xiaoguang Lin Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction Frontiers in Computational Neuroscience seizure prediction EEG ECG data fusion adversarial training |
| title | Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction |
| title_full | Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction |
| title_fullStr | Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction |
| title_full_unstemmed | Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction |
| title_short | Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction |
| title_sort | patient specific approach using data fusion and adversarial training for epileptic seizure prediction |
| topic | seizure prediction EEG ECG data fusion adversarial training |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2023.1172987/full |
| work_keys_str_mv | AT yongyang patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT yongyang patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT yongyang patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT xiaolinqin patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT hanwen patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT fengli patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT xiaoguanglin patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction AT xiaoguanglin patientspecificapproachusingdatafusionandadversarialtrainingforepilepticseizureprediction |