生物医学工程学杂志

生物医学工程学杂志

基于功率谱的睡眠中癫痫发作预测

查看全文

睡眠中如果癫痫发作会增加患者并发症发作和猝死的概率,有效预测患者睡眠中的癫痫发作可让医患及时采取措施,降低上述概率。现有癫痫发作预测方法多是基于脑电信号设计的,但并未在睡眠时期进行针对性研究,而该时期脑电信号相比其他时期有其特殊性,因此为提高灵敏度、降低错误报警率,本文将挖掘睡眠脑电信号的特点,研究睡眠中癫痫发作的预测方法。本文提出的方法中首先构建特征向量,包括不同波段的绝对功率谱、相对功率谱和功率谱比值;其次应用分离性判据和分支定界法进行特征选择;最后训练支持向量机分类器并实现预测。相比于不针对睡眠脑电信号特点的癫痫预测方法(灵敏度 91.67%,错误报警率 9.19%),本文方法的灵敏度(100%)有所提高,而错误报警率(2.11%)则有所降低。本文方法是对现有癫痫预测方法的补充,具有一定的临床价值。

Seizures during sleep increase the probability of complication and sudden death. Effective prediction of seizures in sleep allows doctors and patients to take timely treatments to reduce the aforementioned probability. Most of the existing methods make use of electroencephalogram (EEG) to predict seizures, which are not specific developed for the sleep. However, EEG during sleep has its characteristics compared with EEG during other states. Therefore, in order to improve the sensitivity and reduce the false alarm rate, this paper utilized the characteristics of EEG to predict seizures during sleep. We firstly constructed the feature vector including the absolute power spectrum, the relative power spectrum and the power spectrum ratio in different frequencies. Secondly, the separation criterion and branch-and-bound method were applied to select features. Finally, support vector machine classifier were trained, which is then employed for online prediction. Compared with the existing method that do not consider the characteristics of sleeping EEG (sensitivity 91.67%, false alarm rate 9.19%), the proposed method was superior in terms of sensitivity (100%) and false alarm rate (2.11%). This method can improve the existing epilepsy prediction methods and has important clinical value.

关键词: 癫痫预测; 脑电信号; 功率谱; 支持向量机

Key words: seizure prediction; electroencephalogram signals; power spectrum; support vector machine

引用本文: 刘伟楠, 刘燕, 佟宝同, 赵凌霄, 杨莹雪, 王玉平, 戴亚康. 基于功率谱的睡眠中癫痫发作预测. 生物医学工程学杂志, 2018, 35(3): 329-336. doi: 10.7507/1001-5515.201708062 复制

登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. Langan Y, Nashef L, Sander J W. Case-control study of SUDEP. Neurology, 2005, 64(7): 1131-1133.
2. Cuppens K, Lagae L, Ceulemans B, et al. Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy. Med Biol Eng Comput, 2010, 48(9): 923-931.
3. Salem O, Rebhi Y, Boumaza A, et al. Detection of nocturnal epileptic seizures using wireless 3-D accelerometer sensors//IEEE 16th International Conference on E-Health Networking, Applications and Services. Natal, 2014: 237-242.
4. Fulton S, Poppel K V, Mcgregor A, et al. Prospective study of 2 bed alarms for detection of nocturnal seizures. J Child Neurol, 2013, 28(11): 1430-1433.
5. 刘晓燕. 临床脑电图学. 北京: 人民卫生出版社, 2006: 126-127.
6. Giannakakis G, Sakkalis V, Pediaditis M, et al. Methods for seizure detection and prediction: an overview. Sakkalis V. Modern Electroencephalographic Assessment Techniques, New York, Hymana Press, 2014: 131-157.
7. Shoeb A, Edwards H, Connolly J, et al. Patient-specific seizure onset detection. Epilepsy Behav, 2004, 5(4): 483-498.
8. Fathima T, Bedeeuzzaman M, Farooq O, et al. Wavelet based features for epileptic seizure detection. MES Journal of Technology and Management, 2011, 2(1): 108-112.
9. Park Y, Luo Lan, Parhi K K, et al. Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia, 2011, 52(10): 1761-1770.
10. Alarcon G, Binnie C D, Elwes R D, et al. Power spectrum and intracranial EEG patterns at seizure onset in partial epilepsy. Electroencephalogr Clin Neurophysiol, 1995, 94(5): 326-337.
11. Bandarabadi M, Teixeira C A, Rasekhi J, et al. Epileptic seizure prediction using relative spectral power features. Clin Neurophysiol, 2015, 126(2): 237-248.
12. Fergus P, Hussain A, Hignett D, et al. A machine learning system for automated whole-brain seizure detection. Applied Computing & Informatics, 2016, 12(1): 70-89.
13. Lyu M R, Wang N. Exploration of instantaneous amplitude and frequency features for epileptic seizure prediction// IEEE 12th International Conference on Bioinformatics & Bioengineering, Larnaca, 2012: 292-297.
14. Goldberger A L, Amaral L A, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): E215-E220.
15. Worrell G A, Parish L, Cranstoun S D, et al. High-frequency oscillations and seizure generation in neocortical epilepsy. Brain, 2004, 127(Pt 7): 1496-1506.
16. Bandarabadi M, Teixeira C A, Netoff T I, et al. Robust and low complexity algorithms for seizure detection//36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago,2014: 4447-4450.
17. Kariwala V, Ye Lingjian, Cao Yi. Branch and bound method for regression-based controlled variable selection. Comput Chem Eng, 2013, 54: 1-7.