Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG

Piotr W. Mirowski, Yann LeCun, Deepak Madhavan, Ruben Kuzniecky

Research output: Chapter in Book/Report/Conference proceedingConference contribution

87 Citations (Scopus)

Abstract

Recent research suggests that electrophysiological changes develop minutes to hours before the actual clinical onset in focal epileptic seizures. Seizure prediction is a major field of neurological research, enabled by statistical analysis methods applied to features derived from intracranial Electroencephalographic (EEG) recordings of brain activity. However, no reliable seizure prediction method is ready for clinical applications. In this study, we use modern machine learning techniques to predict seizures from a number of features proposed in the literature. We concentrate on aggregated features that encode the relationship between pairs of EEG channels, such as cross-correlation, nonlinear interdependence, difference of Lyapunov exponents and wavelet analysis-based synchrony such as phase locking. We compare L1-regularized logistic regression, convolutional networks, and support vector machines. Results are reported on the standard Freiburg EEG dataset which contains data from 21 patients suffering from medically intractable focal epilepsy. For each patient, at least one method predicts 100% of the seizures on average 60 minutes before the onset, with no false alarm. Possible future applications include implantable devices capable of warning the patient of an upcoming seizure as well as implanted drug-delivery devices.

Original languageEnglish (US)
Title of host publicationProceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008
Pages244-249
Number of pages6
DOIs
StatePublished - Dec 1 2008
Event2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008 - Cancun, Mexico
Duration: Oct 16 2008Oct 19 2008

Publication series

NameProceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

Other

Other2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008
CountryMexico
CityCancun
Period10/16/0810/19/08

Fingerprint

Wavelet analysis
Drug delivery
Support vector machines
Learning systems
Logistics
Brain
Statistical methods

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Electrical and Electronic Engineering

Cite this

Mirowski, P. W., LeCun, Y., Madhavan, D., & Kuzniecky, R. (2008). Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. In Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008 (pp. 244-249). [4685487] (Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008). https://doi.org/10.1109/MLSP.2008.4685487

Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. / Mirowski, Piotr W.; LeCun, Yann; Madhavan, Deepak; Kuzniecky, Ruben.

Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. p. 244-249 4685487 (Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mirowski, PW, LeCun, Y, Madhavan, D & Kuzniecky, R 2008, Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. in Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008., 4685487, Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008, pp. 244-249, 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008, Cancun, Mexico, 10/16/08. https://doi.org/10.1109/MLSP.2008.4685487
Mirowski PW, LeCun Y, Madhavan D, Kuzniecky R. Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. In Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. p. 244-249. 4685487. (Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008). https://doi.org/10.1109/MLSP.2008.4685487
Mirowski, Piotr W. ; LeCun, Yann ; Madhavan, Deepak ; Kuzniecky, Ruben. / Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG. Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008. 2008. pp. 244-249 (Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008).
@inproceedings{0a6a2fafdc424df6b74af7ade1f8b9c4,
title = "Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG",
abstract = "Recent research suggests that electrophysiological changes develop minutes to hours before the actual clinical onset in focal epileptic seizures. Seizure prediction is a major field of neurological research, enabled by statistical analysis methods applied to features derived from intracranial Electroencephalographic (EEG) recordings of brain activity. However, no reliable seizure prediction method is ready for clinical applications. In this study, we use modern machine learning techniques to predict seizures from a number of features proposed in the literature. We concentrate on aggregated features that encode the relationship between pairs of EEG channels, such as cross-correlation, nonlinear interdependence, difference of Lyapunov exponents and wavelet analysis-based synchrony such as phase locking. We compare L1-regularized logistic regression, convolutional networks, and support vector machines. Results are reported on the standard Freiburg EEG dataset which contains data from 21 patients suffering from medically intractable focal epilepsy. For each patient, at least one method predicts 100{\%} of the seizures on average 60 minutes before the onset, with no false alarm. Possible future applications include implantable devices capable of warning the patient of an upcoming seizure as well as implanted drug-delivery devices.",
author = "Mirowski, {Piotr W.} and Yann LeCun and Deepak Madhavan and Ruben Kuzniecky",
year = "2008",
month = "12",
day = "1",
doi = "10.1109/MLSP.2008.4685487",
language = "English (US)",
isbn = "9781424423767",
series = "Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008",
pages = "244--249",
booktitle = "Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008",

}

TY - GEN

T1 - Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG

AU - Mirowski, Piotr W.

AU - LeCun, Yann

AU - Madhavan, Deepak

AU - Kuzniecky, Ruben

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Recent research suggests that electrophysiological changes develop minutes to hours before the actual clinical onset in focal epileptic seizures. Seizure prediction is a major field of neurological research, enabled by statistical analysis methods applied to features derived from intracranial Electroencephalographic (EEG) recordings of brain activity. However, no reliable seizure prediction method is ready for clinical applications. In this study, we use modern machine learning techniques to predict seizures from a number of features proposed in the literature. We concentrate on aggregated features that encode the relationship between pairs of EEG channels, such as cross-correlation, nonlinear interdependence, difference of Lyapunov exponents and wavelet analysis-based synchrony such as phase locking. We compare L1-regularized logistic regression, convolutional networks, and support vector machines. Results are reported on the standard Freiburg EEG dataset which contains data from 21 patients suffering from medically intractable focal epilepsy. For each patient, at least one method predicts 100% of the seizures on average 60 minutes before the onset, with no false alarm. Possible future applications include implantable devices capable of warning the patient of an upcoming seizure as well as implanted drug-delivery devices.

AB - Recent research suggests that electrophysiological changes develop minutes to hours before the actual clinical onset in focal epileptic seizures. Seizure prediction is a major field of neurological research, enabled by statistical analysis methods applied to features derived from intracranial Electroencephalographic (EEG) recordings of brain activity. However, no reliable seizure prediction method is ready for clinical applications. In this study, we use modern machine learning techniques to predict seizures from a number of features proposed in the literature. We concentrate on aggregated features that encode the relationship between pairs of EEG channels, such as cross-correlation, nonlinear interdependence, difference of Lyapunov exponents and wavelet analysis-based synchrony such as phase locking. We compare L1-regularized logistic regression, convolutional networks, and support vector machines. Results are reported on the standard Freiburg EEG dataset which contains data from 21 patients suffering from medically intractable focal epilepsy. For each patient, at least one method predicts 100% of the seizures on average 60 minutes before the onset, with no false alarm. Possible future applications include implantable devices capable of warning the patient of an upcoming seizure as well as implanted drug-delivery devices.

UR - http://www.scopus.com/inward/record.url?scp=58049188031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58049188031&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2008.4685487

DO - 10.1109/MLSP.2008.4685487

M3 - Conference contribution

AN - SCOPUS:58049188031

SN - 9781424423767

T3 - Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

SP - 244

EP - 249

BT - Proceedings of the 2008 IEEE Workshop on Machine Learning for Signal Processing, MLSP 2008

ER -