Abstract
We present a probabilistic epileptic seizure predictor and an according method for its statistical evaluation. The probabilistic predictor is based on a combination of feature channels, which are derived from the intracranial electroencephalogram (EEG), by a logistic regression map. The evaluation is done by the Brier score, an established assessment method in meteorology, which quantifies the prediction error. From the prediction features, the weights of the logistic regression are learned in a training phase and in a test phase the Brier score is assessed. A test for significance of the probabilistic predictor, based on seizure time surrogates, is computed. For 3 of 5 patients we obtained significant predictive power with the mean phase coherence and with the dynamical similarity index we obtained for 2 of the 5 patients significant results. The concept of probabilistic prediction can be a valuable tool for the development of future seizure intervention systems.
Original language | English |
---|---|
Title of host publication | 4th European Conference of the International Federation for Medical and Biological Engineering |
Editors | J VanderSloten, P Verdonck, M Nyssen, J Haueisen |
Place of Publication | New York |
Publisher | Springer |
Pages | 1701-1705 |
Number of pages | 5 |
ISBN (Print) | 978-3-540-89207-6 |
Publication status | Published - 2009 |
Event | 4th European Conference of the International Federation for Medical and Biological Engineering (ECIFMBE) - Antwerp Duration: 23 Nov 2008 → 27 Nov 2008 |
Publication series
Name | IFMBE Proceedings |
---|---|
Publisher | Springer |
Volume | 22 |
ISSN (Print) | 1680-0737 |
Conference
Conference | 4th European Conference of the International Federation for Medical and Biological Engineering (ECIFMBE) |
---|---|
City | Antwerp |
Period | 23/11/08 → 27/11/08 |
Cite this
Probabilistic Forecasts of Epileptic Seizures and Evaluation by the Brier Score. / Jachan, M.; Drentrup, H. Feldwisch Genannt; Posdziech, F.; Brandt, A.; Altenmueller, D. -M.; Schulze-Bonhage, A.; Timmer, J.; Schelter, B.
4th European Conference of the International Federation for Medical and Biological Engineering. ed. / J VanderSloten; P Verdonck; M Nyssen; J Haueisen. New York : Springer , 2009. p. 1701-1705 (IFMBE Proceedings; Vol. 22).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Probabilistic Forecasts of Epileptic Seizures and Evaluation by the Brier Score
AU - Jachan, M.
AU - Drentrup, H. Feldwisch Genannt
AU - Posdziech, F.
AU - Brandt, A.
AU - Altenmueller, D. -M.
AU - Schulze-Bonhage, A.
AU - Timmer, J.
AU - Schelter, B.
PY - 2009
Y1 - 2009
N2 - We present a probabilistic epileptic seizure predictor and an according method for its statistical evaluation. The probabilistic predictor is based on a combination of feature channels, which are derived from the intracranial electroencephalogram (EEG), by a logistic regression map. The evaluation is done by the Brier score, an established assessment method in meteorology, which quantifies the prediction error. From the prediction features, the weights of the logistic regression are learned in a training phase and in a test phase the Brier score is assessed. A test for significance of the probabilistic predictor, based on seizure time surrogates, is computed. For 3 of 5 patients we obtained significant predictive power with the mean phase coherence and with the dynamical similarity index we obtained for 2 of the 5 patients significant results. The concept of probabilistic prediction can be a valuable tool for the development of future seizure intervention systems.
AB - We present a probabilistic epileptic seizure predictor and an according method for its statistical evaluation. The probabilistic predictor is based on a combination of feature channels, which are derived from the intracranial electroencephalogram (EEG), by a logistic regression map. The evaluation is done by the Brier score, an established assessment method in meteorology, which quantifies the prediction error. From the prediction features, the weights of the logistic regression are learned in a training phase and in a test phase the Brier score is assessed. A test for significance of the probabilistic predictor, based on seizure time surrogates, is computed. For 3 of 5 patients we obtained significant predictive power with the mean phase coherence and with the dynamical similarity index we obtained for 2 of the 5 patients significant results. The concept of probabilistic prediction can be a valuable tool for the development of future seizure intervention systems.
M3 - Conference contribution
SN - 978-3-540-89207-6
T3 - IFMBE Proceedings
SP - 1701
EP - 1705
BT - 4th European Conference of the International Federation for Medical and Biological Engineering
A2 - VanderSloten, J
A2 - Verdonck, P
A2 - Nyssen, M
A2 - Haueisen, J
PB - Springer
CY - New York
ER -