SVM-Based System for Prediction of Epileptic Seizures From iEEG Signal

• Published in: IEEE transactions on biomedical engineering Vol. 64; no. 5; pp. 1011 - 1022
• Main Authors: Shiao, Han-Tai, Cherkassky, Vladimir, Lee, Jieun, Veber, Brandon, Patterson, Edward E., Brinkmann, Benjamin H., Worrell, Gregory A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Animals; Brain; Brain models; Convulsions & seizures; Data analysis; Data models; Data processing; Data-analytic modeling; Diagnosis, Computer-Assisted - methods; Dogs; EEG; Electrocorticography - methods; Empirical analysis; Epilepsy; Epilepsy - diagnosis; Epilepsy - physiopathology; feature representation; Humans; intracranial electroencephalogram (iEEG); Mathematical analysis; Mathematical models; Modelling; Pattern Recognition, Automated - methods; postprocessing; Predictive models; Recording; Reproducibility of Results; Seizing; seizure prediction; Seizures; Sensitivity and Specificity; subject-specific modeling; Support Vector Machine; support vector machine (SVM); Support vector machines; Testing; Training; Training data; unbalanced classification
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2016.2586475

Objective: This paper describes a data-analytic modeling approach for the prediction of epileptic seizures from intracranial electroencephalogram (iEEG) recording of brain activity. Even though it is widely accepted that statistical characteristics of iEEG signal change prior to seizures, robust seizure prediction remains a challenging problem due to subject-specific nature of data-analytic modeling. Methods: Our work emphasizes the understanding of clinical considerations important for iEEG-based seizure prediction, and proper translation of these clinical considerations into data-analytic modeling assumptions. Several design choices during preprocessing and postprocessing are considered and investigated for their effect on seizure prediction accuracy. Results: Our empirical results show that the proposed support vector machine-based seizure prediction system can achieve robust prediction of preictal and interictal iEEG segments from dogs with epilepsy. The sensitivity is about 90-100%, and the false-positive rate is about 0-0.3 times per day. The results also suggest that good prediction is subject specific (dog or human), in agreement with earlier studies. Conclusion : Good prediction performance is possible only if the training data contain sufficiently many seizure episodes, i.e., at least 5-7 seizures. Significance: The proposed system uses subject-specific modeling and unbalanced training data. This system also utilizes three different time scales during training and testing stages.