Techniques from nonlinear dynamics are potentially valuable for prediction of epileptic seizures based on preliminary results with reported prediction times of up to several minutes before electrographic onset. These results must be validated using a database containing more subjects and longer time series with more than one seizure per series in order to establish their predictive sensitivity and specificity. Moreover, criteria for prospective inference must be developed at the same time as computational efficiency is improved, in order to be usable in real time. FHS, with proven expertise in epileptic signal analysis and a database containing over 2000 hours of ECoG recordings from 20 subjects with over 100 seizures, is ideally suited for this task. The end product of this proposed research will be a user-friendly software package for the detection, prediction, and quantification of epileptic seizures for use in a portable device or in diagnostic equipment. The introduction of this software will advance the field scientifically, clinically, and commercially. In Phase I, we will demonstrate proof of principle for this concept, assessing the value of the measures for the task of seizure prediction and detection, and quantifying their sensitivity to amplitude and frequency changes.
Thesaurus Terms: brain disorder diagnosis, computer program /software, computer system design /evaluation, disease /disorder proneness /risk, generalized seizure, patient monitoring device computer assisted patient care, computer human interaction, portable biomedical equipment
