A fuzzy rule-based system for epileptic seizure detection in intracranial EEG

被引:126
作者
Aarabi, A. [1 ]
Fazel-Rezai, R. [2 ]
Aghakhani, Y. [3 ]
机构
[1] Univ Manitoba, Dept Elect & Comp Engn, Winnipeg, MB R3T 2N2, Canada
[2] Univ N Dakota, Dept Elect Engn, Grand Forks, ND 58201 USA
[3] Univ Manitoba, Dept Internal Med, Neurol Sect, Winnipeg, MB R3T 2N2, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Intracranial EEG; Seizure detection; Epilepsy; Fuzzy logic; Ruled-based system; APPROXIMATE ENTROPY; NEURAL-NETWORKS; WARNING SYSTEM; ONSET; COMPLEXITY; PREDICTION; PATIENT;
D O I
10.1016/j.clinph.2009.07.002
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
Objective: We present a method for automatic detection of seizures in intracranial EEG recordings from patients suffering from medically intractable focal epilepsy. Methods: We designed a fuzzy rule-based seizure detection system based on knowledge obtained from experts' reasoning. Temporal, spectral, and complexity features were extracted from IEEG segments, and spatio-temporally integrated using the fuzzy rule-based system for seizure detection. A total of 302.7 h of intracranial EEG recordings from 21 patients having 78 seizures was used for evaluation of the system. Results: The system yielded a sensitivity of 98.7%, a false detection rate of 0.27/h, and an average detection latency of 11 s. There was only one missed seizure. Most of false detections were caused by high-amplitude rhythmic activities. The results from the system correlate well with those from expert visual analysis. Conclusion: The fuzzy rule-based seizure detection system enabled us to deal with imprecise boundaries between interictal and ictal IEEG patterns. Significance: This system may serve as a good seizure detection tool with high sensitivity and low false detection rate for monitoring long-term IEEG. (C) 2009 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.
引用
收藏
页码:1648 / 1657
页数:10
相关论文
共 39 条
[1]   Automated neonatal seizure detection: A multistage classification system through feature selection basedon relevance and redundancy analysis [J].
Aarabi, A ;
Wallois, F ;
Grebe, R .
CLINICAL NEUROPHYSIOLOGY, 2006, 117 (02) :328-340
[2]   A multistage knowledge-based system for EEG seizure detection in newborn infants [J].
Aarabi, Ardalan ;
Grebe, Reinhard ;
Wallois, Fabrice .
CLINICAL NEUROPHYSIOLOGY, 2007, 118 (12) :2781-2797
[3]  
[Anonymous], 1975, MAXIMUM ENTROPY SPEC
[5]  
BASSEL F, 2003, DIS MON, V49, P426
[6]   Multistage epilepsy surgery: Safety, efficacy, and utility of a novel approach in pediatric extratemporal epilepsy [J].
Bauman, JA ;
Feoli, E ;
Romanelli, P ;
Doyle, WK ;
Devinsky, O ;
Weiner, HL .
NEUROSURGERY, 2005, 56 (02) :318-332
[7]  
Bezdek J.C., 1981, PATTERN RECOGNITION
[8]   A goodness-of-fit test for normality based on polynomial regression [J].
Coin, Daniele .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (04) :2185-2198
[9]  
DEMUTH H, 1992, NEURAL NETWORK SIGNA
[10]  
Gardner AB, 2006, J MACH LEARN RES, V7, P1025