Kais Gadhoumi1, Jean-Marc Lina, Jean Gotman. 1. Montreal Neurological Institute, McGill University, Montréal, Québec, Canada. kais.gadhoumi@mail.mcgill.ca
Abstract
OBJECTIVES: In patients with intractable epilepsy, predicting seizures above chance and with clinically acceptable performance has yet to be demonstrated. In this study, an intracranial EEG-based seizure prediction method using measures of similarity with a reference state is proposed. METHODS: 1565 h of continuous intracranial EEG data from 17 patients with mesial temporal lobe epilepsy were investigated. The recordings included 175 seizures. In each patient the data was split into a training set and a testing set. EEG segments were analyzed using continuous wavelet transform. During training, a reference state was defined in the immediate preictal data and used to derive three features quantifying the discrimination between preictal and interictal states. A classifier was then trained in the feature space. Its performance was assessed using testing set and compared with a random predictor for statistical validation. RESULTS: Better than random prediction performance was achieved in 7 patients. The sensitivity was higher than 85%, the warning rate was less than 0.35/h and the proportion of time under warning was less than 30%. CONCLUSION: Seizures are predicted above chance in 41% of patients using measures of state similarity. SIGNIFICANCE: Sensitivity and specificity levels are potentially interesting for closed-loop seizure control applications.
OBJECTIVES: In patients with intractable epilepsy, predicting seizures above chance and with clinically acceptable performance has yet to be demonstrated. In this study, an intracranial EEG-based seizure prediction method using measures of similarity with a reference state is proposed. METHODS: 1565 h of continuous intracranial EEG data from 17 patients with mesial temporal lobe epilepsy were investigated. The recordings included 175 seizures. In each patient the data was split into a training set and a testing set. EEG segments were analyzed using continuous wavelet transform. During training, a reference state was defined in the immediate preictal data and used to derive three features quantifying the discrimination between preictal and interictal states. A classifier was then trained in the feature space. Its performance was assessed using testing set and compared with a random predictor for statistical validation. RESULTS: Better than random prediction performance was achieved in 7 patients. The sensitivity was higher than 85%, the warning rate was less than 0.35/h and the proportion of time under warning was less than 30%. CONCLUSION:Seizures are predicted above chance in 41% of patients using measures of state similarity. SIGNIFICANCE: Sensitivity and specificity levels are potentially interesting for closed-loop seizure control applications.
Authors: Robert Fisher; Vicenta Salanova; Thomas Witt; Robert Worth; Thomas Henry; Robert Gross; Kalarickal Oommen; Ivan Osorio; Jules Nazzaro; Douglas Labar; Michael Kaplitt; Michael Sperling; Evan Sandok; John Neal; Adrian Handforth; John Stern; Antonio DeSalles; Steve Chung; Andrew Shetter; Donna Bergen; Roy Bakay; Jaimie Henderson; Jacqueline French; Gordon Baltuch; William Rosenfeld; Andrew Youkilis; William Marks; Paul Garcia; Nicolas Barbaro; Nathan Fountain; Carl Bazil; Robert Goodman; Guy McKhann; K Babu Krishnamurthy; Steven Papavassiliou; Charles Epstein; John Pollard; Lisa Tonder; Joan Grebin; Robert Coffey; Nina Graves Journal: Epilepsia Date: 2010-03-17 Impact factor: 5.864
Authors: Bettina Gomer; Kathrin Wagner; Lars Frings; Josef Saar; Astrid Carius; Markus Härle; Bernhard J Steinhoff; Andreas Schulze-Bonhage Journal: Epilepsy Behav Date: 2007-04-03 Impact factor: 2.937
Authors: M Le Van Quyen; J Martinerie; V Navarro; P Boon; M D'Havé; C Adam; B Renault; F Varela; M Baulac Journal: Lancet Date: 2001-01-20 Impact factor: 79.321
Authors: Florian Mormann; Thomas Kreuz; Ralph G Andrzejak; Peter David; Klaus Lehnertz; Christian E Elger Journal: Epilepsy Res Date: 2003-03 Impact factor: 3.045
Authors: Ralph G Andrzejak; Florian Mormann; Thomas Kreuz; Christoph Rieke; Alexander Kraskov; Christian E Elger; Klaus Lehnertz Journal: Phys Rev E Stat Nonlin Soft Matter Phys Date: 2003-01-07
Authors: M Winterhalder; T Maiwald; H U Voss; R Aschenbrenner-Scheibe; J Timmer; A Schulze-Bonhage Journal: Epilepsy Behav Date: 2003-06 Impact factor: 2.937
Authors: Benjamin H Brinkmann; Edward E Patterson; Charles Vite; Vincent M Vasoli; Daniel Crepeau; Matt Stead; J Jeffry Howbert; Vladimir Cherkassky; Joost B Wagenaar; Brian Litt; Gregory A Worrell Journal: PLoS One Date: 2015-08-04 Impact factor: 3.240