Format

Send to

Choose Destination
Neural Netw. 2018 Sep;105:104-111. doi: 10.1016/j.neunet.2018.04.018. Epub 2018 May 7.

Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram.

Author information

1
School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2006, Australia; Nano-Neuro-inspired Research Laboratory, School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2006, Australia; School of Engineering, Royal Melbourne Institute of Technology, Melbourne, VIC 3000, Australia. Electronic address: duy.truong@sydney.edu.au.
2
Nano-Neuro-inspired Research Laboratory, School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2006, Australia. Electronic address: ngduyanhece@gmail.com.
3
Centre for Human Psychopharmacology, Swinburne University, Hawthorn, VIC 3122, Australia; Neuroengineering Laboratory, Department of Electrical and Electronic Engineering, University of Melbourne, Parkville, VIC 3010, Australia; Department of Medicine, St. Vincent's Hospital Melbourne, University of Melbourne, Parkville, VIC 3010, Australia. Electronic address: lkuhlmann@swin.edu.au.
4
Centre for Advanced Imaging, University of Queensland, St. Lucia, QLD 4072, Australia; Optimization and Logistics Group, University of Adelaide, Adelaide, SA 5005, Australia. Electronic address: reza@cai.uq.edu.au.
5
Nanochap Electronics and Wenzhou Medical University, 268 Xueyuan West Rd., Wenzhou, China. Electronic address: jiaweiy@nanochap.com.
6
School of Engineering, Royal Melbourne Institute of Technology, Melbourne, VIC 3000, Australia. Electronic address: samuel.ippolito@rmit.edu.au.
7
School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2006, Australia; Nano-Neuro-inspired Research Laboratory, School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2006, Australia. Electronic address: omid.kavehei@sydney.edu.au.

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 significant modifications for each new patient within a new dataset. In this article, we apply convolutional neural networks to different intracranial and scalp electroencephalogram (EEG) datasets and propose a generalized retrospective and patient-specific seizure prediction method. We use the short-time Fourier transform on 30-s EEG windows to extract information in both the frequency domain and the time domain. The algorithm automatically generates optimized features for each patient to best classify preictal and interictal segments. The method can be applied to any other patient from any dataset without the need for manual feature extraction. The proposed approach achieves sensitivity of 81.4%, 81.2%, and 75% and a false prediction rate of 0.06/h, 0.16/h, and 0.21/h on the Freiburg Hospital intracranial EEG dataset, the Boston Children's Hospital-MIT scalp EEG dataset, and the American Epilepsy Society Seizure Prediction Challenge dataset, respectively. Our prediction method is also statistically better than an unspecific random predictor for most of the patients in all three datasets.

KEYWORDS:

Convolutional neural network; Intracranial EEG; Machine learning; Scalp EEG; Seizure prediction

PMID:
29793128
DOI:
10.1016/j.neunet.2018.04.018
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center