Generalizable Epileptic Seizures Prediction Based on Deep Transfer Learning

Overview

Journal Cogn Neurodyn

Publisher Springer

Specialty Neurology

Date 2023 Jan 27

PMID 36704623

Authors

Bahram Sarvi Zargar

Mohammad Reza Karami Mollaei

Farideh Ebrahimi

Jalil Rasekhi

Affiliations

Soon will be listed here.

Abstract

Predicting seizures before they happen can help prevent them through medication. In this research, first, a total of 22 features were extracted from 5-s segmented EEG signals. Second, tensors were developed as inputs for different deep transfer learning models to find the best model for predicting epileptic seizures. The effect of Pre-ictal state duration was also investigated by selecting four different intervals of 10, 20, 30, and 40 min. Then, nine models were created by combining three ImageNet convolutional networks with three classifiers and were examined for predicting seizures patient-dependently. The Xception convolutional network with a Fully Connected (FC) classifier achieved an average sensitivity of 98.47% and a False Prediction Rate (FPR) of 0.031 h in a 40-min Pre-ictal state for ten patients from the European database. The most promising result of this study was the patient-independent prediction of epileptic seizures; the MobileNet-V2 model with an FC classifier was trained with one patient's data and tested on six other patients, achieving a sensitivity rate of 98.39% and an FPR of 0.029 h for a 40-min Pre-ictal scheme.

Citing Articles

Cross-patient seizure prediction via continuous domain adaptation and similar sample replay.

Zhang Z, Liu A, Gao Y, Qian R, Chen X Cogn Neurodyn. 2025; 19(1):26.

PMID: 39830598 PMC: 11735696. DOI: 10.1007/s11571-024-10216-8.

Privacy-preserving multi-source semi-supervised domain adaptation for seizure prediction.

Liang D, Liu A, Wu L, Li C, Qian R, Chen X Cogn Neurodyn. 2024; 18(6):3521-3534.

PMID: 39712093 PMC: 11655995. DOI: 10.1007/s11571-023-10026-4.

Intertumoral and intratumoral barriers as approaches for drug delivery and theranostics to solid tumors using stimuli-responsive materials.

Chenab K, Malektaj H, Nadinlooie A, Mohammadi S, Zamani-Meymian M Mikrochim Acta. 2024; 191(9):541.

PMID: 39150483 DOI: 10.1007/s00604-024-06583-y.

Cross-Domain Transfer of EEG to EEG or ECG Learning for CNN Classification Models.

Yang C, Chen P, Huang W Sensors (Basel). 2023; 23(5).

PMID: 36904661 PMC: 10007254. DOI: 10.3390/s23052458.

References

Bandarabadi M, Teixeira C, Rasekhi J, Dourado A . Epileptic seizure prediction using relative spectral power features. Clin Neurophysiol. 2014; 126(2):237-48. DOI: 10.1016/j.clinph.2014.05.022. View

Hjorth B . EEG analysis based on time domain properties. Electroencephalogr Clin Neurophysiol. 1970; 29(3):306-10. DOI: 10.1016/0013-4694(70)90143-4. View

Cetin M . Model-based robust suppression of epileptic seizures without sensory measurements. Cogn Neurodyn. 2020; 14(1):51-67. PMC: 6974245. DOI: 10.1007/s11571-019-09555-8. View

Klatt J, Feldwisch-Drentrup H, Ihle M, Navarro V, Neufang M, Teixeira C . The EPILEPSIAE database: an extensive electroencephalography database of epilepsy patients. Epilepsia. 2012; 53(9):1669-76. DOI: 10.1111/j.1528-1167.2012.03564.x. View

Khan H, Marcuse L, Fields M, Swann K, Yener B . Focal Onset Seizure Prediction Using Convolutional Networks. IEEE Trans Biomed Eng. 2018; 65(9):2109-2118. DOI: 10.1109/TBME.2017.2785401. View

Mirowski P, Madhavan D, LeCun Y, Kuzniecky R . Classification of patterns of EEG synchronization for seizure prediction. Clin Neurophysiol. 2009; 120(11):1927-1940. DOI: 10.1016/j.clinph.2009.09.002. View

Rasekhi J, Karami Mollaei M, Bandarabadi M, Teixeira C, Dourado A . Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods. J Neurosci Methods. 2013; 217(1-2):9-16. DOI: 10.1016/j.jneumeth.2013.03.019. View

Li S, Zhou W, Yuan Q, Liu Y . Seizure prediction using spike rate of intracranial EEG. IEEE Trans Neural Syst Rehabil Eng. 2013; 21(6):880-6. DOI: 10.1109/TNSRE.2013.2282153. View

Mormann F, Kreuz T, Rieke C, Andrzejak R, Kraskov A, David P . On the predictability of epileptic seizures. Clin Neurophysiol. 2005; 116(3):569-87. DOI: 10.1016/j.clinph.2004.08.025. View

10.

Zhang Z, Parhi K . Low-Complexity Seizure Prediction From iEEG/sEEG Using Spectral Power and Ratios of Spectral Power. IEEE Trans Biomed Circuits Syst. 2015; 10(3):693-706. DOI: 10.1109/TBCAS.2015.2477264. View

11.

Litt B, Esteller R, Echauz J, dAlessandro M, Shor R, Henry T . Epileptic seizures may begin hours in advance of clinical onset: a report of five patients. Neuron. 2001; 30(1):51-64. DOI: 10.1016/s0896-6273(01)00262-8. View

12.

Dissanayake T, Fernando T, Denman S, Sridharan S, Fookes C . Geometric Deep Learning for Subject Independent Epileptic Seizure Prediction Using Scalp EEG Signals. IEEE J Biomed Health Inform. 2021; 26(2):527-538. DOI: 10.1109/JBHI.2021.3100297. View

13.

Rajdev P, Ward M, Rickus J, Worth R, Irazoqui P . Real-time seizure prediction from local field potentials using an adaptive Wiener algorithm. Comput Biol Med. 2009; 40(1):97-108. DOI: 10.1016/j.compbiomed.2009.11.006. View

14.

Lehnertz K, Mormann F, Osterhage H, Muller A, Prusseit J, Chernihovskyi A . State-of-the-art of seizure prediction. J Clin Neurophysiol. 2007; 24(2):147-53. DOI: 10.1097/WNP.0b013e3180336f16. View

15.

Truong N, Nguyen A, Kuhlmann L, Bonyadi M, Yang J, Ippolito S . Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw. 2018; 105:104-111. DOI: 10.1016/j.neunet.2018.04.018. View

16.

Daoud H, Bayoumi M . Efficient Epileptic Seizure Prediction Based on Deep Learning. IEEE Trans Biomed Circuits Syst. 2019; 13(5):804-813. DOI: 10.1109/TBCAS.2019.2929053. View

17.

Aarabi A, He B . Seizure prediction in patients with focal hippocampal epilepsy. Clin Neurophysiol. 2017; 128(7):1299-1307. PMC: 5513720. DOI: 10.1016/j.clinph.2017.04.026. View