Epileptic prediction using spatiotemporal information combined with optimal features strategy on EEG

Lisha Zhong; Jiangzhong Wan; Fangji Yi; Shuling He; Jia Wu; Zhiwei Huang; Yi Lu; Jiazhang Yang; Zhangyong Li

doi:10.3389/fnins.2023.1174005

Epileptic prediction using spatiotemporal information combined with optimal features strategy on EEG

Front Neurosci. 2023 Apr 4:17:1174005. doi: 10.3389/fnins.2023.1174005. eCollection 2023.

Authors

Lisha Zhong^{1

2}, Jiangzhong Wan², Fangji Yi³, Shuling He¹, Jia Wu^{1

2}, Zhiwei Huang², Yi Lu^{1

4}, Jiazhang Yang⁵, Zhangyong Li³

Affiliations

¹ School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China.
² School of Medical Information and Engineering, Southwest Medical University, Luzhou, Sichuan, China.
³ Research Center of Biomedical Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China.
⁴ Central Nervous System Drug Key Laboratory of Sichuan Province, Luzhou, Sichuan, China.
⁵ Yongchuan Women and Children Hospital, Chongqing, China.

Abstract

Objective: Epilepsy is the second most common brain neurological disease after stroke, which has the characteristics of sudden and recurrence. Seizure prediction is seriously important for improving the quality of patients' lives.

Methods: From the perspective of multiple dimensions including time-frequency, entropy and brain network, this paper proposed a novel approach by constructing the optimal spatiotemporal feature set to predict seizures. Based on strong independence and large information capabilities, the two-dimensional feature screening algorithm is performed to eliminate unnecessary redundant features. In order to verify the effectiveness of the optimal feature set, support vector machine (SVM) was used to classify the preictal and interictal states on both the Kaggle intracranial EEG and CHB-MIT scalp EEG dataset.

Results: This model achieved an average accuracy of 98.01%, AUC of 0.96, F-Score of 98.3% and FPR of 0.0383/h on the Kaggle dataset; On the CHB-MIT dataset, the average accuracy, AUC, F-score and FPR were 95.93%, 0.92, 94.97% and 0.0473/h, respectively. Further ablation experiments have confirmed that the temporal and spatial features fusion has better performance than the individual temporal or spatial features.

Conclusion: Compared to the state-of-the-art methods, our approach outperforms most of these existing techniques. The results show that our approach can effectively extract the spatiotemporal information of epileptic EEG signals to predict epileptic seizures with high performance.

Keywords: EEG; brain network; epilepsy; fuzzy entropy; power spectral density; spatiotemporal features.

Grants and funding

This work was supported by the National Natural Science Foundation of China (62171073), the Doctoral Training Program of Chongqing University of Posts and Telecommunications (BYJS202103), the Sichuan Science and Technology Program (2022NSFSC0508 and 2022YFS0616), the Open Project of Central Nervous System Drug Key Laboratory of Sichuan Province (200027-01SZ, 210022-01SZ, and 230005-01SZ), and the Project of Southwest Medical University (2021ZKZD019).