基于LSTM模型的单导联脑电癫痫发作预测*

针对目前癫痫发作实时自动预测困难的问题,本文将开展以LSTM模型为基础的癫痫发作预测的研究,构建了基于LSTM的神经网络模型对癫痫发作进行预测。首先,将采集到的癫痫脑电数据进行预处理,然后提取单导联脑电小波能量特征,结合构建的基于LSTM的模型来识别癫痫发作前期和发作间期的状态,从而实现癫痫发作的预测。与传统的SVM和MLP相比,本文的方法取得了98.5%的分类精度和零误警的结果,为未来开发癫痫发作预警系统提供了理论基础,在临床应用上具有较大的潜在价值。     

基于脑电多特征融合的癫痫发作预测方法

癫痫的发作会给患者的身体和精神造成极大的创伤,对癫痫发作的准确预测可以及时协助医生对患者采取治疗措施.为了准确预测癫痫发作,提出脑电特征和多通道脑电交互特征相融合的癫痫发作预测方法.首先,提出多尺度符号化排列传递熵对多通道脑电信号交互信息进行分析,生成同步矩阵,并通过显著性分析筛选与癫痫发作相关的重要脑电通道,减少不必要特征对分类的干扰;然后,对筛选通道后的脑电信号生成表征脑电信号特征的功率谱密度能量图(PSDED)和描述脑通道交互特征的同步矩阵图(SMD),将两个特征图融合,采用深度卷积神经网络(DCNN)对癫痫患者脑电信号进行分类识别,提高学习能力和泛化能力,分类准确率可达到96.825%;最后,在分类的基础上采用预测评价系统对癫痫发作预测性能进行评估,癫痫发作预测范围(SPH)为10 min和发作发生期(SOP)为10 min时,预测敏感性达到96.66%,误检率可达到0.03/h;当SPH为30min,SOP为10 min时,预测敏感性达到93.17%,误检率可达到0.05/h.与现有研究结果相比较,所提出方法具有较好的预测敏感度和较低的误检率.     

基于人工智能的癫痫发作预测研究综述

癫痫属于神经系统疾病,反复发作和持久倾向将导致机体损伤,因此提前发现癫痫发作有助提升患者的生活质量。为了全面且深入地探究人工智能在预测癫痫发作方面的研究进展及趋势,首先介绍了目前常用的预测癫痫的脑电公开数据集、评价指标和预处理技术,其次将基于人工智能的癫痫发作预测研究划分为基于机器学习和基于深度学习两类,并分别进行分析。分析结果显示,基于深度学习的癫痫发作预测,准确率能达到95%以上。基于以上研究结果得出人工智能应用于癫痫发作预测具有良好的发展前景。     

癫痫脑电的递归确定性分析

利用排序递归图的分析方法对癫痫脑电进行了确定性(DET)的分析,得出癫痫头皮脑电(EEG)的DET高于健康EEG。DET特征的差异性在局部导联上更明显,局部导联的DET特征可以作为癫痫疾病的自动诊断特征。通过分析发作阶段和发作间隙皮层脑电(ECoG)的DET,得出整个频带的DET差别不大,而在beta频带,发作阶段的确定性明显高于发作间隙的DET。Beta频带的DET特征可以作为癫痫发作的预测特征。研究结果为癫痫疾病的自动诊断和癫痫发作预测提供了理论依据。     

基于脑网络和TSK模糊系统的癫痫脑电识别

脑电检测是癫痫疾病诊断的重要手段,但基于脑电信号特征的人工标记方法,对癫痫发作状态识别的准确度较低。将脑功能网络与TSK模糊系统相结合,提出一种癫痫脑电信号识别的新方法。通过分析多通道脑电信号之间的同步性,构建癫痫患者的脑功能网络,采用复杂网络方法提取特征参数;以脑网络参数为输入特征建立TSK模糊系统模型,通过监督式学习训练分类器,用于识别癫痫发作期的脑电波形。实验结果证明了该方法的有效性,模糊分类器对癫痫发作状态识别的准确度达到98.36%,99.48%敏感度和97.24%特异度。该方法将复杂网络与机器学习算法相融合,为通过脑电检测识别癫痫疾病状态提供了新方法,具有重要的应用价值。     

基于支持向量机的多通道癫痫发作预测

癫痫是一种大脑神经系统疾病,具有突发性和反复性,对患者的生命安全构成极大的威胁,有效预测癫痫对该病的预防和治疗具有重要的意义。为此,提取来自德国弗莱堡大学癫痫预测中心21个病人的公开数据集。利用独立成分分析方法对原始数据进行去冗余操作,自回归模型被用来对癫痫脑电进行特征提取。支持向量机模型和滤波器将预测问题转化为二分类问题。蒙特卡洛统计方法使得最终的结果具有统计学上的意义。实验结果表明,该模型能够提前30 min~70 min预测到癫痫的发生,且误报率将近0,能为临床癫痫预警系统提供较好的理论依据。     

癫痫脑电的互信息和同步性分析

脑电（EEG）分析是研究癫痫的一个重要手段。以临床采集的健康对象和癫痫患者的头皮EEG为研究对象,计算不同导联EEG数据之间的排序互信息,结果表明癫痫患者不同导联之间的互信息明显高于健康对象,因此,排序互信息可以作为癫痫疾病诊断的重要特征。以排序互信息为依据,对癫痫脑电进行了同步性的分析,结果表明癫痫患者左脑区域内、右脑区域内及左右脑区之间的信息交流明显增强,即其同步性强于健康对象。互信息和同步性的分析方法还可对癫痫发作前期和发作阶段的EEG进行分析,对癫痫发作作出预测。     

儿童癫痫综合征智能分析：综述与展望

儿童癫痫综合征智能分析是指通过统计分析、机器学习等数据驱动方法,挖掘临床有效生物标志物,构建相应的专家系统,以解决临床和预后管理问题的研究.文中首先简述儿童癫痫综合征的定义、发作类型和分类等临床基础知识.然后,回顾基于脑电信号的儿童癫痫综合征智能分析框架和各组成部分典型方法存在的优缺点,包括数据收集及预处理、特征提取、决策器系统和专家系统.其中,将专家系统分为特定波形检测系统、诊断分类系统、发作检测系统、发作预测系统和量化评估系统,并进行全面概括与理论解释.最后,结合儿童癫痫综合征智能分析领域现有研究的局限性和挑战,展望未来研究方向,以推动儿童癫痫综合征智能分析系统的研究进展,减轻该病带来的负面影响.     

基于深度神经网络的个性化睡眠癫痫发作预测

现有癫痫发作预测方法存在精度较低、错误报警率较高、癫痫患者睡眠脑电特异性、致痫灶位置和类型不同导致脑电信号存在差异的问题.文中提出基于深度神经网络的个性化睡眠癫痫发作预测方法,帮助医生和患者采取及时有效的治疗措施,降低患者患并发症和猝死的概率.对原始脑电信号滤波和分段以去除噪声,保证短时间内触发警报,利用离散小波变换分解信号并提取统计特征表征脑电信号时频特征.再应用双向长短期记忆网络挖掘最具鉴别能力的特征并结合留一法分类,经过决策过程优化得到预测结果.在不同频带限制条件下的实验表明,与睡眠癫痫相关的δ频带信号是影响发作预测性能的重要因素.相比现有睡眠癫痫预测方法,文中方法性能较优.     

神经网络算法在癫痫预测模型中的应用研究综述

癫痫作为一种大脑神经元异常放电导致的中枢神经系统疾病,给患者的正常生活带来了极大影响,提前预测癫痫发作并及时采取防范措施可以有效提高患者的生活质量。随着数据科学和大数据技术的发展,神经网络算法越来越多地应用于癫痫预测领域,并展现出了巨大的应用潜力。对神经网络算法在癫痫预测领域的应用情况和不足之处进行了综述,按照癫痫预测模型的搭建流程依次从数据集、数据预处理、特征提取、神经网络算法模型几个模块进行论述。在介绍了脑电信号特点和常用数据集类别、常见数据预处理手段、常见的特征提取方法特别是手工设计特征的提取方法后,重点对多层人工神经网络和脉冲神经网络算法原理及其在癫痫预测领域的应用进行分析梳理和归纳总结,系统性地对神经网络算法的缺点进行剖析,并对神经网络算法在癫痫预测领域的进一步应用发展进行了讨论和展望。     

Automatic multi-modal intelligent seizure acquisition (MISA) system for detection of motor seizures from electromyographic data and motion data

The objective is to develop a non-invasive automatic method for detection of epileptic seizures with motor manifestations. Ten healthy subjects who simulated seizures and one patient participated in the study. Surface electromyography (sEMG) and motion sensor features were extracted as energy measures of reconstructed sub-bands from the discrete wavelet transformation (DWT) and the wavelet packet transformation (WPT). Based on the extracted features all data segments were classified using a support vector machine (SVM) algorithm as simulated seizure or normal activity. A case study of the seizure from the patient showed that the simulated seizures were visually similar to the epileptic one. The multi-modal intelligent seizure acquisition (MISA) system showed high sensitivity, short detection latency and low false detection rate. The results showed superiority of the multi-modal detection system compared to the uni-modal one. The presented system has a promising potential for seizure detection based on multi-modal data.     

Abidirectional brain-computer interface for effective epilepsy control

Brain-computer interfaces （BCIs） can provide direct bidirectional communication between the brain and a machine. Recently, the BCI technique has been used in seizure control. UsuMly, a closed-loop system based on BCI is set up which delivers a therapic electrical stimulus only in response to seizure onsets. In this way, the side effects of neurostimulation can be greatly reduced. In this paper, a new BCI-based responsive stimulation system is proposed. With an efficient morphology-based seizure detector, seizure events can be identified in the early stages which trigger electrical stimulations to be sent to the cortex of the brain. The proposed system was tested on rats with penicillin-induced epileptic seizures. Online experiments show that 83% of the seizures could be detected successfully with a short average time delay of 3.11 s. With the therapy of the BCI-based seizure control system, most seizures were suppressed within 10 s. Compared with the control group, the average seizure duration was reduced by 30.7%. Therefore, the proposed system can control epileptic seizures effectively and has potential in clinical applications.     

Electroencephalography‐based feature extraction using complex network for automated epileptic seizure detection

Electroencephalography signals are typically used for analyzing epileptic seizures. These signals are highly nonlinear and nonstationary, and some specific patterns exist for certain disease types that are hard to develop an automatic epileptic seizure detection system. This paper discussed statistical mechanics of complex networks, which inherit the characteristic properties of electroencephalography signals, for feature extraction via a horizontal visibility algorithm in order to reduce processing time and complexity. The algorithm transforms a time series signal into a complex network, which some features are abbreviated. The statistical mechanics are calculated to capture distinctions pertaining to certain diseases to form a feature vector. The feature vector is classified by multiclass classification via a k‐nearest neighbor classifier, a multilayer perceptron neural network, and a support vector machine with a 10‐fold cross‐validation criterion. In performance evaluation of proposed method with healthy, seizure‐free interval, and seizure signals, firstly, input data length is regarded among some practical signal samples by optimizing between accuracy‐processing time, and the proposed method yields outstanding performance on the average classification accuracy for 3‐class problems mainly for detection of seizure‐free interval and seizure signals and acceptable results for 2‐class and 5‐class problems comparing with conventional methods. The proposed method is another tool that can be used for classifying signal patterns, as an alternative to time/frequency analyses.     

Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data.

     

ILP-assisted de novo drug design

The accurate and early detection of epileptic seizures in continuous electroencephalographic (EEG) data has a growing role in the management of patients with epilepsy. Early detection allows for therapy to be delivered at the start of seizures and for caregivers to be notified promptly about potentially debilitating events. The challenge to detecting epileptic seizures, however, is that seizure morphologies exhibit considerable inter-patient and intra-patient variability. While recent work has looked at addressing the issue of variations across different patients (inter-patient variability) and described patient-specific methodologies for seizure detection, there are no examples of systems that can simultaneously address the challenges of inter-patient and intra-patient variations in seizure morphology. In our study, we address this complete goal and describe a multi-task learning approach that trains a classifier to perform well across many kinds of seizures rather than potentially overfitting to the most common seizure types. Our approach increases the generalizability of seizure detection systems and improves the tradeoff between latency and sensitivity versus false positive rates. When compared against the standard approach on the CHB–MIT multi-channel scalp EEG data, our proposed method improved discrimination between seizure and non-seizure EEG for almost 83 % of the patients while reducing false positives on nearly 70 % of the patients studied.     

Epileptic seizure predictors based on computational intelligence techniques: A comparative study with 278 patients

The ability of computational intelligence methods to predict epileptic seizures is evaluated in long-term EEG recordings of 278 patients suffering from pharmaco-resistant partial epilepsy, also known as refractory epilepsy. This extensive study in seizure prediction considers the 278 patients from the European Epilepsy Database, collected in three epilepsy centres: Hôpital Pitié-là-Salpêtrière, Paris, France; Universitätsklinikum Freiburg, Germany; Centro Hospitalar e Universitário de Coimbra, Portugal.     

基于同步压缩和DCGAN的癫痫脑电信号检测方法

脑电信号智能识别是癫痫病检测的重要手段,为更加准确地预测癫痫发作,针对目前的深度学习方法特别是卷积神经网络在脑电信号分类方面存在的一些问题,如算法复杂度过高、样本量太少导致分类效果差等,提出基于傅里叶同步压缩变换和深度卷积生成对抗网络的癫痫脑电信号检测方法。首先同步压缩方法将短时傅里叶变换处理后的信号时频能量进行压缩,使得频谱图像精度更高;其次构建深度卷积生成对抗网络来提取特征;最后实现癫痫发作预测。实验在CHB-MIT脑电数据集上进行,结果表明该方法具有97.9%的检测准确率。使用生成对抗网络有效解决了样本量不足的问题,结合同步压缩处理方法后,具有良好的识别准确性。     

A tunable support vector machine assembly classifier for epileptic seizure detection

Automating the detection of epileptic seizures could reduce the significant human resources necessary for the care of patients suffering from intractable epilepsy and offer improved solutions for closed-loop therapeutic devices such as implantable electrical stimulation systems. While numerous detection algorithms have been published, an effective detector in the clinical setting remains elusive. There are significant challenges facing seizure detection algorithms. The epilepsy EEG morphology can vary widely among the patient population. EEG recordings from the same patient can change over time. EEG recordings can be contaminated with artifacts that often resemble epileptic seizure activity. In order for an epileptic seizure detector to be successful, it must be able to adapt to these different challenges. In this study, a novel detector is proposed based on a support vector machine assembly classifier (SVMA). The SVMA consists of a group of SVMs each trained with a different set of weights between the seizure and non-seizure data and the user can selectively control the output of the SVMA classifier. The algorithm can improve the detection performance compared to traditional methods by providing an effective tuning strategy for specific patients. The proposed algorithm also demonstrates a clear advantage over threshold tuning. When compared with the detection performances reported by other studies using the publicly available epilepsy dataset hosted by the University of BONN, the proposed SVMA detector achieved the best total accuracy of 98.72%. These results demonstrate the efficacy of the proposed SVMA detector and its potential in the clinical setting.