Measure profile surrogates: A method to validate the performance of epileptic seizure prediction algorithms

In a growing number of publications it is claimed that epileptic seizures can be predicted by analyzing theelectroencephalogram (EEG) with different characterizing measures. However, many of these studies sufferfrom a severe lack of statistical validation. Only rarely are results passed to a statistical test and verified againstsome null hypothesis H0 in order to quantify their significance. In this paper we propose a method to statisticallyvalidate the performance of measures used to predict epileptic seizures. From measure profiles renderedby applying a moving-window technique to the electroencephalogram we first generate an ensemble of surrogatesby a constrained randomization using simulated annealing. Subsequently the seizure prediction algorithmis applied to the original measure profile and to the surrogates. If detectable changes before seizure onset exist,highest performance values should be obtained for the original measure profiles and the null hypothesis. "Themeasure is not suited for seizure prediction" can be rejected. We demonstrate our method by applying twomeasures of synchronization to a quasicontinuous EEG recording and by evaluating their predictive performanceusing a straightforward seizure prediction statistics. We would like to stress that the proposed method israther universal and can be applied to many other prediction and detection problems.