Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram

ND Truong; AD Nguyen; L Kuhlmann; MR Bonyadi; J Yang; S Ippolito; O Kavehei

Journal article

Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram

ND Truong, AD Nguyen, L Kuhlmann, MR Bonyadi, J Yang, S Ippolito, O Kavehei

Neural Networks | Published : 2018

DOI: 10.1016/j.neunet.2018.04.018

Abstract

Seizure prediction has attracted growing attention as one of the most challenging predictive data analysis efforts to improve the life of patients with drug-resistant epilepsy and tonic seizures. Many outstanding studies have reported great results in providing sensible indirect (warning systems) or direct (interactive neural stimulation) control over refractory seizures, some of which achieved high performance. However, to achieve high sensitivity and a low false prediction rate, many of these studies relied on handcraft feature extraction and/or tailored feature extraction, which is performed for each patient independently. This approach, however, is not generalizable, and requires signifi..

View full abstract

University of Melbourne Researchers

Levin Kuhlmann Author

Related Projects (2)

ADVANCED EPILEPTIC SEIZURE WARNING METHODS

Epilepsy is a debilitating neurological disorder characterised by spontaneous seizures. For a third of epilepsy patients, drugs cannot preve..

CRITICAL SLOWING IN EPILEPSY

Seizures appear unpredictable and greatly affect the quality of all aspects of life for patients with epilepsy and their carers. New advance..

Grants

Awarded by National Health and Medical Research Council

Funding Acknowledgements

This research was supported by Sydney Informatics Hub, funded by the University of Sydney via Core Research Facilities. The authors appreciate Benjamin H. Brinkmann from Mayo Systems Electrophysiology Laboratory for providing information on some unlabeled datasets. O. Kavehei acknowledges support provided by a 2018 Early Career Research grant from the Faculty of Engineering and Information Technology, University of Sydney (Grant no ECR2018Kavehei). L. Kuhlmann acknowledges support from National Health and Medical Research Council project grants APP1065638 and APP1130468. J. Yang acknowledges the National Natural Science Foundation of China for financial support under grant 61501332.