Adaptive epileptic seizure prediction system

被引:287
作者
Iasemidis, LD [1 ]
Shiau, DS
Chaovalitwongse, W
Sackellares, JC
Pardalos, PM
Principe, JC
Carney, PR
Prasad, A
Veeramani, B
Tsakalis, K
机构
[1] Arizona State Univ, Ctr Syst Sci & Engn Res, Harrington Dept Bioengn, Tempe, AZ 85287 USA
[2] Univ Florida, Dept Stat, Gainesville, FL 32611 USA
[3] Univ Florida, Dept Neurosci, Gainesville, FL 32611 USA
[4] Malcolm Randall VA Med Ctr, Gainesville, FL USA
[5] Univ Florida, Dept Ind & Syst Engn, Ctr Appl Optimizat, Gainesville, FL 32611 USA
[6] Univ Florida, Dept Neurol, Gainesville, FL 32611 USA
[7] Univ Florida, Dept Biomed Engn, Gainesville, FL 32611 USA
[8] Univ Florida, Dept Elect & Comp Engn, Gainesville, FL 32611 USA
[9] Univ Florida, Dept Pediat, Gainesville, FL 32611 USA
[10] Arizona State Univ, Dept Elect Engn, Tempe, AZ 85287 USA
关键词
dynamical entrainment; human epilepsy; prediction of seizures; short-term maximum Lyapunov exponents; spatiotemporal transitions;
D O I
10.1109/TBME.2003.810689
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Current epileptic seizure "prediction" algorithms are generally based on the knowledge of seizure occurring time and analyze the electroencephalogram, (EEG) recordings retrospectively. It is then obvious that, although these analyses provide evidence of brain activity changes prior to epileptic seizures, they cannot be applied to develop implantable devices for diagnostic and therapeutic purposes. In this paper, we describe an adaptive procedure to prospectively analyze continuous, long-term EEG, recordings when only the occurring time of the first seizure is known. The algorithm is based on the convergence and divergence of short-term maximum Lyapunov exponents (STLmax) among critical electrode sites selected adaptively. A warning of an impending seizure is then issued. Global optimization techniques are applied for selecting the critical groups of electrode sites. The adaptive seizure prediction algorithm (ASPA) was tested in continuous 0.76 to 5.84 days intracranial EEG recordings from a group of five patients with refractory temporal lobe epilepsy. A fixed parameter setting applied to all cases predicted 82% of seizures with a false prediction rate of 0.16/h. Seizure warnings occurred an average of 71.7 min before ictal onset. Similar results were produced by dividing the available EEG recordings into half training and testing portions. Optimizing the parameters for individual patients improved sensitivity (84% overall) and reduced false prediction rate (0.12/h overall). These results indicate that ASPA can be applied to implantable devices for diagnostic and therapeutic purposes.
引用
收藏
页码:616 / 627
页数:12
相关论文
共 44 条
[1]  
Box G. E. P., 1970, J. Amer. Stat. Assoc., V65, P1509, DOI DOI 10.1080/01621459.1970.10481180
[2]  
Carney Paul R., 2001, Epilepsia, V42, P225
[3]   Characterizing nonlinearity in invasive EEG recordings from temporal lobe epilepsy [J].
Casdagli, MC ;
Iasemidis, LD ;
Sackellares, JC ;
Roper, SN ;
Gilmore, RL ;
Savit, RS .
PHYSICA D, 1996, 99 (2-3) :381-399
[4]   Seizure prediction by non-linear time series analysis of brain electrical activity [J].
Elger, CE ;
Lehnertz, K .
EUROPEAN JOURNAL OF NEUROSCIENCE, 1998, 10 (02) :786-789
[5]  
Iaseemidis Leon D., 1996, Epilepsia, V37, P90
[6]  
IASEMIDIS L D, 1990, Brain Topography, V2, P187, DOI 10.1007/BF01140588
[7]  
Iasemidis L. D., 1988, J CLIN NEUROPHYSIOL, V5, P339, DOI DOI 10.1097/00004691-198810000-00042
[8]   Chaos theory and epilepsy [J].
Iasemidis, LD ;
Sackellares, JC .
NEUROSCIENTIST, 1996, 2 (02) :118-126
[9]   Global optimization approaches to reconstruction of dynamical systems related to epileptic seizures [J].
Iasemidis, LD ;
Pardalos, PM ;
Sackellares, JC ;
Yatsenko, VA .
Scattering and Biomedical Engineering: Modeling and Applications, 2002, :308-318
[10]  
Iasemidis LD, 2002, BIOCOMP SER, V1, P59