Information Technology Reference
In-Depth Information
information from several manually identified seizures instead of a single seizure as
in ATSWA.
Analyses of sensitivity, specificity, and predictive power of ATSWA with respect
to various seizure warning horizons as compared to periodic and random warning
schemes has shown that ATSWA performs significantly better.
One disadvantage of SMAS is that the seizure warnings only provide long-term
anticipation of impending seizures in a fixed time interval (i.e., seizure warning
horizon). Although this is valuable information to epileptic patients and clinicians,
there is no information within the warning horizon. Therefore, we are developing
seizure susceptibility indices, probability measures (between 0 and 1) that represent
the likelihood of an impending seizure. Since our seizure algorithms are based on
the dynamical descriptors of EEG, SSI should be generated in real time in a form of
probability index by analyzing the distribution of dynamical descriptors.
20.5 Conclusions
A useful seizure monitoring and alert system is capable of not only generating au-
tomatic warnings of impending seizures from EEG recordings, but also quantifying
and outputting the information on the likelihood of a seizure occurrence. The tech-
niques described in this study appear to be potentially useful in wide range of appli-
cations for brain monitoring, including the ICU, and could potentially revolutionize
the care for patients with neurological disorders.
References
1. Binnie, C. Long term EEG recording and its role in clinical practice. IEE Colloquium on Data
Logging of Physiological Signals, pp. 5/1-5/2 (1995)
2. Elger, C., Lehnertz, K.: Seizure prediction by non-linear time series analysis of brain electrical
activity. Eur J Neurosci
10
, 786-789 (1998)
3. Freeman, W.J. Strange attractors that govern mammalian brain dynamics shown by trajectories
of EEG potentials. IEEE Trans CaS
35
, 781-784 (1988)
4. Griffiths, M., Grainger, P., Cox, M., Preece, A. Recent advances in EEG monitoring for general
anesthesia, altered states of consciousness and sports performance science. In: The 3rd IEE
International Seminar on Medical Applications of Signal Processing, pp. 1-5 (2005)
5. Hirsch, L. Continuous EEG monitoring in the intensive care unit: an overview. J Clin Neuro-
physiol
21
(5), 332-340 (2004)
6. Hoeve, M.J., Jones, R., Carroll, G., Goelz, H. Automated detection of epileptic seizures in
the EEG. In: Engineering in Medicine and Biology Society, Proceedings of the 23rd Annual
International Conference of the IEEE, pp. 943-946 (2001)
7. Horst, R., Pardalos, P., Thoai, N. Introduction to Global Optimization, 2nd edn. Kluwer Aca-
demic Publishers, Boston (2000)
8. Iasemidis, L. On the dynamics of the human brain in temporal lobe epilepsy. Ph.D. thesis,
University of Michigan, Ann Arbor, Ph.D. Dissertation (1991)
