Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals
Electroencephalography is a widely used non-invasive method for monitoring brain electrical activity, critical for diagnosing and managing neurological disorders such as epilepsy. While clinical standards use 21 electrodes to capture comprehensive neural signals, a personalized approach can enhance...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/9/2715 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850155287050190848 |
|---|---|
| author | Rosanna Ferrara Martino Giaquinto Gennaro Percannella Leonardo Rundo Alessia Saggese |
| author_facet | Rosanna Ferrara Martino Giaquinto Gennaro Percannella Leonardo Rundo Alessia Saggese |
| author_sort | Rosanna Ferrara |
| collection | DOAJ |
| description | Electroencephalography is a widely used non-invasive method for monitoring brain electrical activity, critical for diagnosing and managing neurological disorders such as epilepsy. While clinical standards use 21 electrodes to capture comprehensive neural signals, a personalized approach can enhance performance by selecting patient-specific channels, reducing noise and redundancy. This study introduces an innovative, lightweight deep learning system optimized for real-time seizure detection in personalized wearable devices. The system uses an efficient Convolutional Neural Network that processes data from just two channels. These channels are automatically selected using a data-driven mechanism that identifies the most informative scalp regions based on each patient’s unique seizure patterns. The proposed approach ensures high reliability, even with small datasets, and improves interpretability for clinicians by overcoming the limitations of more complex methods. The tailored channel selection boosts detection accuracy and ensures robust performance across different seizure types while reducing the computational burden typical of multi-electrode systems. Validation on the publicly available CHB-MIT dataset achieved an average balanced accuracy of 0.83 and a false-positive rate of approximately 0.1/h. The system’s performance matches, and in some cases outperforms, state-of-the-art systems that use four fixed channels in temporal regions, demonstrating the potential of two-channel wearable solutions, specifically with a non-negligible 30% reduction in the false-positive rate. This interpretable, patient-specific method enables the development of personalized, efficient, and compact wearable devices for reliable seizure detection in everyday life. |
| format | Article |
| id | doaj-art-8edf0dba753344c185bdf35f4a1e68f9 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-8edf0dba753344c185bdf35f4a1e68f92025-08-20T02:24:58ZengMDPI AGSensors1424-82202025-04-01259271510.3390/s25092715Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG SignalsRosanna Ferrara0Martino Giaquinto1Gennaro Percannella2Leonardo Rundo3Alessia Saggese4Department of Information Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, 84084 Fisciano, ItalyDepartment of Information Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, 84084 Fisciano, ItalyDepartment of Information Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, 84084 Fisciano, ItalyDepartment of Information Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, 84084 Fisciano, ItalyDepartment of Information Engineering, Electrical Engineering and Applied Mathematics (DIEM), University of Salerno, 84084 Fisciano, ItalyElectroencephalography is a widely used non-invasive method for monitoring brain electrical activity, critical for diagnosing and managing neurological disorders such as epilepsy. While clinical standards use 21 electrodes to capture comprehensive neural signals, a personalized approach can enhance performance by selecting patient-specific channels, reducing noise and redundancy. This study introduces an innovative, lightweight deep learning system optimized for real-time seizure detection in personalized wearable devices. The system uses an efficient Convolutional Neural Network that processes data from just two channels. These channels are automatically selected using a data-driven mechanism that identifies the most informative scalp regions based on each patient’s unique seizure patterns. The proposed approach ensures high reliability, even with small datasets, and improves interpretability for clinicians by overcoming the limitations of more complex methods. The tailored channel selection boosts detection accuracy and ensures robust performance across different seizure types while reducing the computational burden typical of multi-electrode systems. Validation on the publicly available CHB-MIT dataset achieved an average balanced accuracy of 0.83 and a false-positive rate of approximately 0.1/h. The system’s performance matches, and in some cases outperforms, state-of-the-art systems that use four fixed channels in temporal regions, demonstrating the potential of two-channel wearable solutions, specifically with a non-negligible 30% reduction in the false-positive rate. This interpretable, patient-specific method enables the development of personalized, efficient, and compact wearable devices for reliable seizure detection in everyday life.https://www.mdpi.com/1424-8220/25/9/2715channel selectionEEG analysislightweight CNNpersonalized medicineseizure detectionwearable systems |
| spellingShingle | Rosanna Ferrara Martino Giaquinto Gennaro Percannella Leonardo Rundo Alessia Saggese Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals Sensors channel selection EEG analysis lightweight CNN personalized medicine seizure detection wearable systems |
| title | Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals |
| title_full | Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals |
| title_fullStr | Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals |
| title_full_unstemmed | Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals |
| title_short | Personalizing Seizure Detection for Individual Patients by Optimal Selection of EEG Signals |
| title_sort | personalizing seizure detection for individual patients by optimal selection of eeg signals |
| topic | channel selection EEG analysis lightweight CNN personalized medicine seizure detection wearable systems |
| url | https://www.mdpi.com/1424-8220/25/9/2715 |
| work_keys_str_mv | AT rosannaferrara personalizingseizuredetectionforindividualpatientsbyoptimalselectionofeegsignals AT martinogiaquinto personalizingseizuredetectionforindividualpatientsbyoptimalselectionofeegsignals AT gennaropercannella personalizingseizuredetectionforindividualpatientsbyoptimalselectionofeegsignals AT leonardorundo personalizingseizuredetectionforindividualpatientsbyoptimalselectionofeegsignals AT alessiasaggese personalizingseizuredetectionforindividualpatientsbyoptimalselectionofeegsignals |