Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning
Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/14/6578 |
| _version_ | 1797587555356508160 |
|---|---|
| author | Raghdah Saemaldahr Mohammad Ilyas |
| author_facet | Raghdah Saemaldahr Mohammad Ilyas |
| author_sort | Raghdah Saemaldahr |
| collection | DOAJ |
| description | Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity. |
| first_indexed | 2024-03-11T00:40:34Z |
| format | Article |
| id | doaj.art-eda57dd1020449138a44f3a886724758 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T00:40:34Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-eda57dd1020449138a44f3a8867247582023-11-18T21:19:41ZengMDPI AGSensors1424-82202023-07-012314657810.3390/s23146578Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated LearningRaghdah Saemaldahr0Mohammad Ilyas1Department of Computer Science, Taibah University, Medina 42353, Saudi ArabiaDepartment of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USAElectroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.https://www.mdpi.com/1424-8220/23/14/6578epilepsyseizure predictionpreictalfederated learning (FL)spiking encodergraph convolutional neural network (GCNN) |
| spellingShingle | Raghdah Saemaldahr Mohammad Ilyas Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning Sensors epilepsy seizure prediction preictal federated learning (FL) spiking encoder graph convolutional neural network (GCNN) |
| title | Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning |
| title_full | Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning |
| title_fullStr | Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning |
| title_full_unstemmed | Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning |
| title_short | Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning |
| title_sort | patient specific preictal pattern aware epileptic seizure prediction with federated learning |
| topic | epilepsy seizure prediction preictal federated learning (FL) spiking encoder graph convolutional neural network (GCNN) |
| url | https://www.mdpi.com/1424-8220/23/14/6578 |
| work_keys_str_mv | AT raghdahsaemaldahr patientspecificpreictalpatternawareepilepticseizurepredictionwithfederatedlearning AT mohammadilyas patientspecificpreictalpatternawareepilepticseizurepredictionwithfederatedlearning |