A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction

C. A. Teixeira, B. Direito, R. P. Costa, M. Valderrama, H. Feldwisch-Drentrup, S. Nikolopoulos, M. Le Van Quyen, B. Schelter, A. Dourado

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

3 Citations (Scopus)

Abstract

The daily life of epilepsy patients is constrained by the possibility of occurrence of seizures. Until now, seizures cannot be predicted with sufficient sensitivity and specificity. Most of the seizure prediction studies have been focused on a small number of patients, and frequently assuming unrealistic hypothesis.

This paper adopts the view that for an appropriate development of reliable predictors one should consider long-term recordings and several features and algorithms integrated in one software tool. A computational environment, based on Matlab (R), is presented, aiming to be an innovative tool for seizure prediction. It results from the need of a powerful and flexible tool for long-term EEG/ECG analysis by multiple features and algorithms. After being extracted, features can be subjected to several reduction and selection methods, and then used for prediction. The predictions can be conducted based on optimized thresholds or by applying computational intelligence methods. One important aspect is the integrated evaluation of the seizure prediction characteristic of the developed predictors.

Original languageEnglish
Title of host publication2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Place of PublicationNew York
PublisherIEEE Press
Pages6341-6344
Number of pages4
ISBN (Print)978-1-4244-4124-2
Publication statusPublished - 2010
Event32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10) - Buenos Aires
Duration: 30 Aug 20104 Sep 2010

Conference

Conference32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10)
CityBuenos Aires
Period30/08/104/09/10

Cite this

Teixeira, C. A., Direito, B., Costa, R. P., Valderrama, M., Feldwisch-Drentrup, H., Nikolopoulos, S., ... Dourado, A. (2010). A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6341-6344). New York: IEEE Press.

A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction. / Teixeira, C. A.; Direito, B.; Costa, R. P.; Valderrama, M.; Feldwisch-Drentrup, H.; Nikolopoulos, S.; Le Van Quyen, M.; Schelter, B.; Dourado, A.

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). New York : IEEE Press, 2010. p. 6341-6344.

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

Teixeira, CA, Direito, B, Costa, RP, Valderrama, M, Feldwisch-Drentrup, H, Nikolopoulos, S, Le Van Quyen, M, Schelter, B & Dourado, A 2010, A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE Press, New York, pp. 6341-6344, 32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10), Buenos Aires, 30/08/10.
Teixeira CA, Direito B, Costa RP, Valderrama M, Feldwisch-Drentrup H, Nikolopoulos S et al. A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). New York: IEEE Press. 2010. p. 6341-6344
Teixeira, C. A. ; Direito, B. ; Costa, R. P. ; Valderrama, M. ; Feldwisch-Drentrup, H. ; Nikolopoulos, S. ; Le Van Quyen, M. ; Schelter, B. ; Dourado, A. / A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). New York : IEEE Press, 2010. pp. 6341-6344
@inproceedings{0cecf38e962f4277bc7d11edc45bc44a,
title = "A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction",
abstract = "The daily life of epilepsy patients is constrained by the possibility of occurrence of seizures. Until now, seizures cannot be predicted with sufficient sensitivity and specificity. Most of the seizure prediction studies have been focused on a small number of patients, and frequently assuming unrealistic hypothesis.This paper adopts the view that for an appropriate development of reliable predictors one should consider long-term recordings and several features and algorithms integrated in one software tool. A computational environment, based on Matlab (R), is presented, aiming to be an innovative tool for seizure prediction. It results from the need of a powerful and flexible tool for long-term EEG/ECG analysis by multiple features and algorithms. After being extracted, features can be subjected to several reduction and selection methods, and then used for prediction. The predictions can be conducted based on optimized thresholds or by applying computational intelligence methods. One important aspect is the integrated evaluation of the seizure prediction characteristic of the developed predictors.",
author = "Teixeira, {C. A.} and B. Direito and Costa, {R. P.} and M. Valderrama and H. Feldwisch-Drentrup and S. Nikolopoulos and {Le Van Quyen}, M. and B. Schelter and A. Dourado",
year = "2010",
language = "English",
isbn = "978-1-4244-4124-2",
pages = "6341--6344",
booktitle = "2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)",
publisher = "IEEE Press",

}

TY - GEN

T1 - A Computational Environment for Long-Term Multi-Feature and Multi-Algorithm Seizure Prediction

AU - Teixeira, C. A.

AU - Direito, B.

AU - Costa, R. P.

AU - Valderrama, M.

AU - Feldwisch-Drentrup, H.

AU - Nikolopoulos, S.

AU - Le Van Quyen, M.

AU - Schelter, B.

AU - Dourado, A.

PY - 2010

Y1 - 2010

N2 - The daily life of epilepsy patients is constrained by the possibility of occurrence of seizures. Until now, seizures cannot be predicted with sufficient sensitivity and specificity. Most of the seizure prediction studies have been focused on a small number of patients, and frequently assuming unrealistic hypothesis.This paper adopts the view that for an appropriate development of reliable predictors one should consider long-term recordings and several features and algorithms integrated in one software tool. A computational environment, based on Matlab (R), is presented, aiming to be an innovative tool for seizure prediction. It results from the need of a powerful and flexible tool for long-term EEG/ECG analysis by multiple features and algorithms. After being extracted, features can be subjected to several reduction and selection methods, and then used for prediction. The predictions can be conducted based on optimized thresholds or by applying computational intelligence methods. One important aspect is the integrated evaluation of the seizure prediction characteristic of the developed predictors.

AB - The daily life of epilepsy patients is constrained by the possibility of occurrence of seizures. Until now, seizures cannot be predicted with sufficient sensitivity and specificity. Most of the seizure prediction studies have been focused on a small number of patients, and frequently assuming unrealistic hypothesis.This paper adopts the view that for an appropriate development of reliable predictors one should consider long-term recordings and several features and algorithms integrated in one software tool. A computational environment, based on Matlab (R), is presented, aiming to be an innovative tool for seizure prediction. It results from the need of a powerful and flexible tool for long-term EEG/ECG analysis by multiple features and algorithms. After being extracted, features can be subjected to several reduction and selection methods, and then used for prediction. The predictions can be conducted based on optimized thresholds or by applying computational intelligence methods. One important aspect is the integrated evaluation of the seizure prediction characteristic of the developed predictors.

M3 - Conference contribution

SN - 978-1-4244-4124-2

SP - 6341

EP - 6344

BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

PB - IEEE Press

CY - New York

ER -