Seizure Prediction in Epilepsy: From Circadian Concepts via Probabilistic Forecasting to Statistical Evaluation

Bjoern Schelter; Hinnerk Feldwisch-Drentrup; Matthias Ihle; Andreas Schulze-Bonhage; Jens Timmer

Seizure Prediction in Epilepsy: From Circadian Concepts via Probabilistic Forecasting to Statistical Evaluation

Bjoern Schelter, Hinnerk Feldwisch-Drentrup, Matthias Ihle, Andreas Schulze-Bonhage, Jens Timmer

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Abstract

Seizure prediction performance is hampered by high numbers of false predictions. Here we present an approach to reduce the number of false predictions based on circadian concepts. Based on eight representative patients we demonstrate that this approach increases the performance considerably. The fraction of patients for whom we found a significant seizure prediction performance was increased from 25% to 38% by accounting for circadian dependencies.

Original language	English
Title of host publication	2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC)
Place of Publication	New York
Publisher	IEEE Press
Pages	1624-1627
Number of pages	4
ISBN (Print)	978-1-4244-4122-8
Publication status	Published - 2011
Event	33rd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBS) - Boston Duration: 30 Aug 2011 → 3 Sep 2011

Conference

Conference	33rd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBS)
City	Boston
Period	30/08/11 → 3/09/11

Cite this

Seizure Prediction in Epilepsy: From Circadian Concepts via Probabilistic Forecasting to Statistical Evaluation. / Schelter, Bjoern; Feldwisch-Drentrup, Hinnerk; Ihle, Matthias et al.

2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC). New York : IEEE Press, 2011. p. 1624-1627.

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Schelter, B, Feldwisch-Drentrup, H, Ihle, M, Schulze-Bonhage, A & Timmer, J 2011, Seizure Prediction in Epilepsy: From Circadian Concepts via Probabilistic Forecasting to Statistical Evaluation. in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC). IEEE Press, New York, pp. 1624-1627, 33rd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBS), Boston, 30/08/11.

@inproceedings{5186056b67854f7bb7436f6f0ef6123b,

title = "Seizure Prediction in Epilepsy: From Circadian Concepts via Probabilistic Forecasting to Statistical Evaluation",

abstract = "Seizure prediction performance is hampered by high numbers of false predictions. Here we present an approach to reduce the number of false predictions based on circadian concepts. Based on eight representative patients we demonstrate that this approach increases the performance considerably. The fraction of patients for whom we found a significant seizure prediction performance was increased from 25% to 38% by accounting for circadian dependencies.",

author = "Bjoern Schelter and Hinnerk Feldwisch-Drentrup and Matthias Ihle and Andreas Schulze-Bonhage and Jens Timmer",

year = "2011",

language = "English",

isbn = "978-1-4244-4122-8",

pages = "1624--1627",

booktitle = "2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC)",

publisher = "IEEE Press",

note = "33rd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBS) ; Conference date: 30-08-2011 Through 03-09-2011",

}

TY - GEN

T1 - Seizure Prediction in Epilepsy: From Circadian Concepts via Probabilistic Forecasting to Statistical Evaluation

AU - Schelter, Bjoern

AU - Feldwisch-Drentrup, Hinnerk

AU - Ihle, Matthias

AU - Schulze-Bonhage, Andreas

AU - Timmer, Jens

PY - 2011

Y1 - 2011

N2 - Seizure prediction performance is hampered by high numbers of false predictions. Here we present an approach to reduce the number of false predictions based on circadian concepts. Based on eight representative patients we demonstrate that this approach increases the performance considerably. The fraction of patients for whom we found a significant seizure prediction performance was increased from 25% to 38% by accounting for circadian dependencies.

AB - Seizure prediction performance is hampered by high numbers of false predictions. Here we present an approach to reduce the number of false predictions based on circadian concepts. Based on eight representative patients we demonstrate that this approach increases the performance considerably. The fraction of patients for whom we found a significant seizure prediction performance was increased from 25% to 38% by accounting for circadian dependencies.

M3 - Published conference contribution

SN - 978-1-4244-4122-8

SP - 1624

EP - 1627

BT - 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC)

PB - IEEE Press

CY - New York

T2 - 33rd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBS)

Y2 - 30 August 2011 through 3 September 2011

ER -