M-NIG: mobile network information gain for EEG-based epileptic seizure prediction
Abstract Epilepsy is one of the most common cerebral diseases, the development of which can be divided into four states: interictal state, preictal state, ictal state and postictal state. Hunting for critical states is of great significance to predict seizures. This study seeks to establish a genera...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-97696-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850042066816466944 |
|---|---|
| author | Yuting Meng Yi Liu Guanglei Wang Huipeng Song Yiyu Zhang Jianbo Lu Peiluan Li Xu Ma |
| author_facet | Yuting Meng Yi Liu Guanglei Wang Huipeng Song Yiyu Zhang Jianbo Lu Peiluan Li Xu Ma |
| author_sort | Yuting Meng |
| collection | DOAJ |
| description | Abstract Epilepsy is one of the most common cerebral diseases, the development of which can be divided into four states: interictal state, preictal state, ictal state and postictal state. Hunting for critical states is of great significance to predict seizures. This study seeks to establish a general-purpose method for epileptic seizure prediction by constructing individual-specific correlation networks between multi-channel EEG signals. In this paper, we present the mobile network information gain (M-NIG) method by transforming floating time series datasets into stable network information gain, which reduces the impact of data noise, thereby improving the robustness and effectiveness of the algorithm. The method not only efficiently predicts seizures but also detects their DNB channels. The proposed method attains an average of 97.40% accuracy, 94.32% sensitivity, 97.48% specificity, and FPR = 0.024/h on 22 patients from the public CHB-MIT scalp EEG database, which outperforms most state-of-the-art articles. Additionally, it achieves an average of 95.70% accuracy, 100.00% sensitivity, 95.56% specificity, and FPR = 0.044/h on a dataset collected at Taian Maternity and Child Health Hospital, which outperforms most state-of-the-art articles in terms of sensitivity, accuracy, and FPR. Our experiments show that the parameters of sliding window and the number of nearest neighbor of k-nearest neighbor (KNN) are important factors affecting prediction performance. |
| format | Article |
| id | doaj-art-c41604c181ab434ebaa293c58ed01ff0 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c41604c181ab434ebaa293c58ed01ff02025-08-20T02:55:38ZengNature PortfolioScientific Reports2045-23222025-04-0115111510.1038/s41598-025-97696-8M-NIG: mobile network information gain for EEG-based epileptic seizure predictionYuting Meng0Yi Liu1Guanglei Wang2Huipeng Song3Yiyu Zhang4Jianbo Lu5Peiluan Li6Xu Ma7School of Mathematics and Statistics, Henan University of Science and Technology Department of Pediatrics, Taian Maternal and Child Health Hospital Department of Pediatrics, Taian Maternal and Child Health HospitalSchool of Mathematics and Statistics, Henan University of Science and TechnologyInformation Engineering College, Henan University of Science and TechnologyNational Human Genetics Resource Center, National Research Institute for Family PlanningSchool of Mathematics and Statistics, Henan University of Science and TechnologyNational Human Genetics Resource Center, National Research Institute for Family PlanningAbstract Epilepsy is one of the most common cerebral diseases, the development of which can be divided into four states: interictal state, preictal state, ictal state and postictal state. Hunting for critical states is of great significance to predict seizures. This study seeks to establish a general-purpose method for epileptic seizure prediction by constructing individual-specific correlation networks between multi-channel EEG signals. In this paper, we present the mobile network information gain (M-NIG) method by transforming floating time series datasets into stable network information gain, which reduces the impact of data noise, thereby improving the robustness and effectiveness of the algorithm. The method not only efficiently predicts seizures but also detects their DNB channels. The proposed method attains an average of 97.40% accuracy, 94.32% sensitivity, 97.48% specificity, and FPR = 0.024/h on 22 patients from the public CHB-MIT scalp EEG database, which outperforms most state-of-the-art articles. Additionally, it achieves an average of 95.70% accuracy, 100.00% sensitivity, 95.56% specificity, and FPR = 0.044/h on a dataset collected at Taian Maternity and Child Health Hospital, which outperforms most state-of-the-art articles in terms of sensitivity, accuracy, and FPR. Our experiments show that the parameters of sliding window and the number of nearest neighbor of k-nearest neighbor (KNN) are important factors affecting prediction performance.https://doi.org/10.1038/s41598-025-97696-8EpilepsyMobile network information gainPreictalSeizure predictionSliding window |
| spellingShingle | Yuting Meng Yi Liu Guanglei Wang Huipeng Song Yiyu Zhang Jianbo Lu Peiluan Li Xu Ma M-NIG: mobile network information gain for EEG-based epileptic seizure prediction Scientific Reports Epilepsy Mobile network information gain Preictal Seizure prediction Sliding window |
| title | M-NIG: mobile network information gain for EEG-based epileptic seizure prediction |
| title_full | M-NIG: mobile network information gain for EEG-based epileptic seizure prediction |
| title_fullStr | M-NIG: mobile network information gain for EEG-based epileptic seizure prediction |
| title_full_unstemmed | M-NIG: mobile network information gain for EEG-based epileptic seizure prediction |
| title_short | M-NIG: mobile network information gain for EEG-based epileptic seizure prediction |
| title_sort | m nig mobile network information gain for eeg based epileptic seizure prediction |
| topic | Epilepsy Mobile network information gain Preictal Seizure prediction Sliding window |
| url | https://doi.org/10.1038/s41598-025-97696-8 |
| work_keys_str_mv | AT yutingmeng mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT yiliu mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT guangleiwang mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT huipengsong mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT yiyuzhang mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT jianbolu mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT peiluanli mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction AT xuma mnigmobilenetworkinformationgainforeegbasedepilepticseizureprediction |