Abstract

1. Introduction

2. Materials and Methods

3. Proposed Epilepsy Classification Method

4. Results and Discussion

5. Conclusions

Data Availability

Conflicts of Interest

References

Abstract

     The precise detection of epileptic seizure helps to prevent the serious consequences of seizures. As the electroencephalogram (EEG) reflects the brain activity of patients effectively, it has been widely used in epileptic seizure detection in the past decades. Recently, deep learning-based detection methods which automatically learn features from the EEG signals have attracted much attention. However, with deep learning-based detection methods, different input formats of EEG signals will lead to different detection performances. In this paper, we propose a deep learning-based epileptic seizure detection method with hybrid input formats of EEG signals, i.e., original EEG, Fourier transform of EEG, short-time Fourier transform of EEG, and wavelet transform of EEG. Convolutional neural networks (CNNs) are designed for extracting latent features from these inputs. A feature fusion mechanism is applied to integrate the learned features to generate a more stable syncretic feature for seizure detection. The experimental results show that our proposed hybrid method is effective to improve the seizure detection performance in few-shot scenarios.

Introduction

     Approximately one percent of the world’s population, 65 million people, suffer from epilepsy, more than Parkinson’s disease, Alzheimer’s disease, and multiple sclerosis combined [1]. About two-thirds of people with epilepsy can be treated with medication, and the rest may require surgical intervention. Epilepsy has the characteristics of sudden and recurrent seizures, which may lead to falls, asphyxia, and even death. Therefore, seizure detection is very important for early warning and treatment of epilepsy.

     Epileptic seizure detection is mainly based on electroencephalogram (EEG) [2–4]. Single-channel EEG acquisition equipment improves the practicability of EEG in epileptic detection due to its simplicity in implementation. However, the provided information by signal-channel EEG signal is limited because of the small number of channels. Therefore, it is worth studying to establish a model with high accuracy and high robustness for single-channel EEG epileptic detection.

     The traditional methods are mainly based on feature engineering techniques which extract the corresponding features from EEG signals and then complete the detection based on the extracted features [5–9]. These features include time-domain features [10–12], frequency-domain features [8, 9], and time-frequency-domain features [13–15]. Once the features are extracted, EEG signals can be classified using a variety of classifiers. No matter what classifier is used, the quality of designed features will greatly affect the performance of epilepsy detection. In recent years, with the development of deep learning technology, many works have applied deep learning to perform epilepsy detection [16, 17]. Different from traditional feature engineering, deep learning methods automatically learn features from EEG signals and further complete detection tasks with an end-to-end manner without complicated manual feature design process and can achieve better performance than traditional methods in many scenarios.

Conclusions

     In this paper, we focus on epileptic classification in few-shot scenarios. In order to make the classification accuracy higher and more stable, we propose a deep learning method with hybrid input, i.e., original EEG signal, FFT, STFT, and DWT of EEG signal. In order to alleviate the tendency of overfitting, two means are applied. The first is that we replace the traditional convolution by depthwise separable convolution for reducing the parameters in network and then 2 regularization is applied, whose function is decreasing the complexity of the model. We conduct several experiments to distinguish normal and epileptic EEG, and the results show the proposed method with hybrid input has strong advantages in epileptic classification. It benefits from the complementarity of time-domain properties, frequency-domain properties, and time-frequency-domain properties. Our proposed method provides a new perspective to enrich the input information to make improvements for deep learning-based epileptic diagnosis.

1- Introduction

2- Methodology

3- Results and discussion

4- Conclusions

References

Abstract

Epilepsy is the fourth most common neurological disorder that manifests itself through unprovoked seizures, detection of which is the very first step of proper diagnosis and treatment of this severe disease. In this paper, an automated seizure detection method has been proposed based on the statistical and spectral features of max normalized intrinsic mode functions or IMFs that were extracted using complete ensemble empirical mode decomposition with adaptive noise method. First, a publicly available dataset of EEG signals was used to generate the IMFs and noise or outliers were discarded. Then IMFs were max normalized which was shown to improve the separability of features. Statistical and spectral features were extracted from the normalized IMFs which offered better separation of seizure and seizure-free data. Finally, Quadratic Discriminant classifier was used for the classification purpose and 10-fold cross validation was performed to validate the trained model. The proposed scheme is numerically efficient and shows a maximum of 100% accuracy which is the highest reported on this data set.

Motivation

The International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE) have defined the terms epileptic seizure and epilepsy as follows: an epileptic seizure is a transient occurrence of signs and/or symptoms due to abnormal excessive or synchronous neuronal activity in the brain and epilepsy is a disorder of the brain characterized by an enduring predisposition to generate epileptic seizures and by the neurobiologic, cognitive, psychological, and social consequences of this condition [1]. The definition of epilepsy requires the occurrence of at least one epileptic seizure. According to World Health Organization (WHO), approximately 50 million people have epilepsy worldwide. Around 80% of epilepsy patients are either from low or middleincome countries, of which around 75% failto get proper treatment. Epilepsy has severe socioeconomic consequences, including high treatment cost,low employment rate, andlow salary among epileptic patients [2]. Epilepsy remains resistant to drug therapy in about one-third of patients and people with pharmacoresistant epilepsy are about 2–10 times more likely to die compared to the general population [3].

1- Introduction

2- Related work

3- Materials and method

4- Experimental results

5- Discussion

6- Conclusion and future direction

References

Abstract

Epilepsy, a common neurological disorder, is generally detected by electroencephalogram (EEG) signals. Visual inspection and interpretation of EEGs is a slow, time consuming process that is vulnerable to error and subjective variability. Consequently, several efforts to develop automatic epileptic seizure detection and classification methods have been made. The present study proposes a novel computer aided diagnostic technique (CAD) based on the discrete wavelet transform (DWT) and arithmetic coding to differentiate epileptic seizure signals from normal (seizure-free) signals. The proposed CAD technique comprises three steps. The first step decomposes EEG signals into approximations and detail coefficients using DWT while discarding non-significant coefficients in view of threshold criteria; thus, limiting the number of significant wavelet coefficients. The second step converts significant wavelet coefficients to bit streams using arithmetic coding to compute the compression ratio. In the final step, the compression feature set is standardized, whereupon machine-learning classifiers detect seizure activity from seizure-free signals. We employed the widely used benchmark database from Bonn University to compare and validate the technique with results from prior approaches. The proposed method achieved a perfect classification performance (100% accuracy) for the detection of epileptic seizure activity from EEG data, using both linear and non-liner machine-learning classifiers. This CAD technique can thus be considered robust with an extraordinary detection capability that discriminates epileptic seizure activity from seizure-free and normal EEG activity with simple linear classifiers. The method has the potential for efficient application as an adjunct for the clinical diagnosis of epilepsy.

Introduction

Epilepsy is a common brain disorder that affects people of all ages. It is a chronic neurological disorder in which recurrent seizures occurs due to abnormal neuronal activities within the human brain and affects the sensorium, mood and/or movement of the human body [1]. World Health Organization statistics indicate that approximately 50 million people currently live with epilepsy worldwide and an estimated 2.4 million people are diagnosed with epilepsy each year [2]. The incidence of the malady is higher in developing countries;i.e., between 7 and 14 per 1000 people. Treatment mostly comprises antiepileptic drugs and/or surgery [3]. The electroencephalogram (EEG) commonly detects seizure activity as it reflects electrophysiological conditions of the brain at a given time [4] and is widely used for diagnostic due to its low cost. EEG signals, enhanced with physiological and pathological data, are employed to evaluate and assess the treatment and progress of epileptic patients. Typically, clinicians evaluate EEG signals for three types of activity: (i) normal EEG activity that records healthy subjects with eyes open or closed; (ii) inter-ictal/seizure-free EEG activity that may contain small spikes and/or subclinical seizures that occur between two clinical episodes in epileptic patients; (iii) and ictal EEG activity containing sudden spikes.

1- Introduction

2- Feature extraction

3- Epileptic seizure detection

4- Methods for feature evaluation

5- Experimental results

6- Conclusions

References

Abstract

Since the manual detection of electrographic seizures in continuous electroencephalogram (EEG) monitoring is very time-consuming and requires a trained expert, attempts to develop automatic seizure detection are diverse and ongoing. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre-screened results for neurologists. Several features, data transformations, and classifiers have been explored to analyze and classify seizures via EEG signals. In the literature, some jointly-applied features used in the classification may have shared similar contributions, making them redundant in the learning process. Therefore, this paper aims to comprehensively summarize feature descriptions and their interpretations in characterizing epileptic seizures using EEG signals, as well as to review classification performance metrics. To provide meaningful information of feature selection, we conducted an experiment to examine the quality of each feature independently. The Bayesian error and non-parametric probability distribution estimation were employed to determine the significance of the individual features. Moreover, a redundancy analysis using a correlation-based feature selection was applied. The results showed that the following features – variance, energy, nonlinear energy, and Shannon entropy computed on a raw EEG signal, as well as variance, energy, kurtosis, and line length calculated on wavelet coefficients – were able to significantly capture the seizures. When compared with a baseline method of classifying all epochs as normal, an improvement of 4.77–13.51% in the Bayesian error was obtained.

Introduction

An epileptic seizure, as defined by the International League Against Epilepsy [1], is a temporary event of symptoms due to synchronization of abnormally excessive activities of neurons in the brain. It has been estimated that approximately 65 million people around the world are affected by epilepsy [2]. Nevertheless, it is still a time-consuming process for neurologists to review continuous electroencephalograms (EEGs) to monitor epileptic patients. Therefore, several researchers have developed differenttechniques that help neurologists to identify an epilepsy occurrence [3–5]. The whole process of automated epileptic seizure analysis primarily consists of data acquisition, signal pre-processing, feature extraction, feature or channel selection, and classification. This paper focuses on a selection of features commonly used in the literature, including statistical parameters (mean, variance, skewness, and kurtosis), amplitude-related parameters (energy, nonlinear energy, line length, maximum and minimum values) and entropyrelated measures. These features can be categorized based on their interpretation or the domain from which the features are calculated. While some studies have considered a particular group of features applicable to their proposed classification method [6–8], others have applied various groups of features extracted from the time, frequency, and time-frequency domains. For example, 55 features were used with a support vector machine (SVM) and postprocessing for neonatal seizure detection, which provided a good detectionrate of 89.2% withone false detectionperhour [9]. Feature redundancy and relevance analysis were applied to 132 features to reduce the vector dimension [10]. Fast correlation based-filter proposed in [11], correlation-based selection (CFS) [12], and ReliefF established in [13], were utilized to select non-redundant features and the filtered features were classified by an artificial neural network (ANN). It turned out that 30-optimal selected features by ReliefF achieved the best result with 91% sensitivity and 95% specificity. These studies showed thatthere is the need to review feature selection as relevant features are directly related to the seizure classification performance.

1- Introduction

2- Proposed approach

3- Techniques

4- Results

5- Conclusion and future scope

References

Abstract

Electroencephalography (EEG) is a non-invasive method for the analysis of neurological disorders. Epilepsy is one of the most widespread neurological disorders and often characterized by repeated seizures. This paper intends to conduct an iterative filtering based decomposition of EEG signals to improve upon the accuracy of seizure detection. The proposed approach is evaluated using All India Institute of Medical Science (AIIMS) Patna EEG database and online CHB-MIT surface EEG database. The iterative filtering decomposition technique is applied to extract sub-components from the EEG signal. The feature set obtained from each segmented intrinsic mode function consists of 2-D power spectral density and time-domain features dynamic mode decomposition power, variance, and Katz fractal dimension. The Hidden Markov Model (HMM) based probabilistic model has been designed using the above-stated features representing the seizure and non-seizure EEG events. The EEG signal is classified based on the maximum score obtained from the individual feature-based classifiers. The maximum score derived from each HMM classifier gives the final class information. The proposed decomposition of EEG signals achieved 99.60% and 99.74% accuracy in seizure detection for the online CHB-MIT surface EEG database and AIIMS Patna EEG database, respectively.

Introduction

EEG has a wide application in the diagnosis of neurological diseases such as dementia, migraine, and epilepsy [1]. Epilepsy is a non-communicable disease that can affect people of different ages. Nearly 70 million people are affected by epilepsy all over the world, and in India alone, 12 million people are suffering from epilepsy [2]. The unexpected simultaneous activity of groups of neurons is called a seizure. The duration of seizure in continuous EEG signals varies from 1 to 10 seconds. Depending on the seizure condition, the recording duration varies from minutes to hours. At present, the seizure detection is manual, and accuracy depends largely on the doctor’s experience. There is an urgent requirement to develop an efficient algorithm which can detect seizure efficiently from continuous EEG signal. There are different state-of-the-art methods proposed for seizure detection. Discrete wavelet transform (DWT) and empirical mode decomposition (EMD) are widely used techniques for data decomposition. EMD time-domain features and frequency domain features with a linear discriminant analysis classifier are used for seizure classification [3]. Multivariate empirical mode decomposition, instantaneous rate, instantaneous amplitude, and artificial neural network are efficient in seizure detection [4]. EMD intrinsic mode function (IMF) and Higher-order moment features are found to be effective in seizure detection [5]. DWT coefficients are found to be efficient in seizure and non-seizure classification [6]. Energy ratio from wavelet coefficients and ant colony classifier achieved good classification accuracy [7]. Stationary wavelet transform has a good application in seizure detection.

Purpose: Amygdala enlargement (AE) has been reported in drug resistant lesional and non-lesional temporal lobe epilepsy (TLE). Its contribution to development of intractability of epilepsy is at best uncertain. Our aim was to study the natural course of AE in a heterogenous group of TLE patients with follow-up imaging and clinical outcomes. Methods: A prospective observational study in patients with TLE with imaging features of AE recruited from epilepsy clinics between 1994 and 2018. Demographic data, details of epilepsy syndrome, outcomes and follow up neuroimaging were extracted. Results: Forty-two patients were recruited including 19 males (45 %). Mean age at onset of epilepsy was 30.6 years and mean duration of epilepsy was 19.9 years. On MRI, 33 patients had isolated unilateral AE and eleven had AE with hippocampal enlargement (HE). Twenty (48 %) underwent temporal resections with most common histopathology being amygdalar gliosis (40 %). Engel Class IA outcome at last follow up (mean, 10 years) was 60 %. Thirty-four patients had neuroimaging follow up of at least 1 year (mean, 5 years). AE resolved in 6, persisted in 25, evolved into bilateral HS in 1, bilateral mesial temporal atrophy in 1 and ipsilateral mesial temporal atrophy in 1. Resolution of AE was associated with better seizure free outcomes (p = 0.013). Conclusions: TLE with AE is associated with favourable prognosis yet not benign. Over 50 % were drug resistant and surgical outcomes were similar to mTLE. Resolution of AE on follow up neuroimaging was associated with better seizure free outcomes.

Introduction

Mesial temporal lobe epilepsy (mTLE) is major contributor to the group of drug resistant epilepsies and is one of the leading indications for epilepsy surgery, the most common pathology being hippocampal sclerosis (HS) [1]. There is a significant group of patients with mTLE that do not have any lesions on MRI, called “non-lesional” or “MRInegative [2]. These patients pose a challenge for treatment in terms of difficult presurgical work-up, frequently warranting intracranial EEG recordings. There is evidence that non-lesional patients fare worse in surgical outcomes in general as compared to lesional ones [3]. Interestingly, there is accumulating evidence that MRI-negative epilepsies are not necessarily non-lesional [4]. The amygdala, which is part of the limbic system, is known to be part of the epileptogenic network of patients with mTLE [5]. Intracranial EEG recordings have revealed interictal epileptiform discharges (IEDs) arising from the amygdala [6]. Structural abnormalities of the amygdala may be difficult to detect by conventional MR techniques [7], and thus may contribute to the so called non-lesional temporal lobe epilepsy (TLE-NL). Imaging studies of TLE-NL patients have identified amygdala enlargement (AE) as an increase in grey matter and amygdalar volume in 12 % of patients [8]. The same authors reported similar proportion (14 %) of AE in patients with mTLE and HS [9]. While the role of the amygdala is functionally defined and evidence of epileptogenicity in the amygdala exists, the significance of AE remains undefined.

Since the manual detection of electrographic seizures in continuous electroencephalogram (EEG) monitoring is very time-consuming and requires a trained expert, attempts to develop automatic seizure detection are diverse and ongoing. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre-screened results for neurologists. Several features, data transformations, and classifiers have been explored to analyze and classify seizures via EEG signals. In the literature, some jointly-applied features used in the classification may have shared similar contributions, making them redundant in the learning process. Therefore, this paper aims to comprehensively summarize feature descriptions and their interpretations in characterizing epileptic seizures using EEG signals, as well as to review classification performance metrics. To provide meaningful information of feature selection, we conducted an experiment to examine the quality of each feature independently. The Bayesian error and non-parametric probability distribution estimation were employed to determine the significance of the individual features. Moreover, a redundancy analysis using a correlation-based feature selection was applied. The results showed that the following features – variance, energy, nonlinear energy, and Shannon entropy computed on a raw EEG signal, as well as variance, energy, kurtosis, and line length calculated on wavelet coefficients – were able to significantly capture the seizures. When compared with a baseline method of classifying all epochs as normal, an improvement of 4.77–13.51% in the Bayesian error was obtained.

Introduction

An epileptic seizure, as defined by the International League Against Epilepsy [1], is a temporary event of symptoms due to synchronization of abnormally excessive activities of neurons in the brain. It has been estimated that approximately 65 million people around the world are affected by epilepsy [2]. Nevertheless, it is still a time-consuming process for neurologists to review continuous electroencephalograms (EEGs) to monitor epileptic patients. Therefore, several researchers have developed differenttechniques that help neurologists to identify an epilepsy occurrence [3–5]. The whole process of automated epileptic seizure analysis primarily consists of data acquisition, signal pre-processing, feature extraction, feature or channel selection, and classification. This paper focuses on a selection of features commonly used in the literature, including statistical parameters (mean, variance, skewness, and kurtosis), amplitude-related parameters (energy, nonlinear energy, line length, maximum and minimum values) and entropyrelated measures. These features can be categorized based on their interpretation or the domain from which the features are calculated. While some studies have considered a particular group of features applicable to their proposed classification method [6–8], others have applied various groups of features extracted from the time, frequency, and time-frequency domains.

1. Introduction

2. Methods

3. Results

4. Discussion

Acknowledgments

References

Abstract

Purpose: The purpose of this study was to evaluate differences in stigma, disclosure management of epilepsy, and knowledge about epilepsy between patients with epilepsy who recognized and did not recognize the new Korean term for epilepsy.

Methods: This was a cross-sectional, multicenter study. The Stigma Scale-Revised, the Disclosure Management Scale, the Patient Health Questionnaire-9, and a questionnaire assessing knowledge about epilepsy were used. The set of questionnaires had two versions, using either the old or new name for epilepsy. Multivariate logistic regression analyses were used.

Results: A total of 341 patients with epilepsy and 509 family members were recruited. Approximately 62% of patients felt some degree of epilepsy-related stigma. Mild stigma, severe concealment of epilepsy diagnosis, and increased knowledge about epilepsy were independently identified as factors associated with recognition of the new term in patients. Recognition of the new term was more prevalent in patients and family members with higher education, female family members, and family members having patients with younger age at seizure onset and shorter duration of epilepsy. There were no significant differences between the two types of questionnaires. About 81% of patients and 93% of family members had a positive attitude about renaming epilepsy

Conclusion: The use of the new Korean term for epilepsy (cerebroelectric disorder) increased knowledge about epilepsy but did not reduce stigma and concealment of epilepsy diagnosis in Korean adults with epilepsy. Higher education may be an important factor for knowing the new term in patients and family members.

Introduction

Epilepsy is one of the first described neurological diseases and is considered a stigmatizing condition [1]. In spite of the teachings of Hippocrates (460–370 BC) that epilepsy is a physical illness, misconceptions regarding the cause of epilepsy became predominant in the Middle Ages [2]. Currently, misconceptions regarding epilepsy have nearly disappeared or are rapidly declining worldwide [3]. However, patients with epilepsy continue to suffer from stigma, as well as social restriction and discrimination, in everyday activities, such as going to school, driving, working, and obtaining insurance [4–6], not only in the developing world but also in the West [4]. In a large European study, half of patients with epilepsy experienced feelings of stigma associated with epilepsy diagnosis [7]. This perception significantly impacts the quality of life of patients with epilepsy [4,7,8].

1- Introduction

2- P-glycoprotein inhibitors

3- Gene therapy

4- Stem cell therapy

5- Traditional and novel antiepileptic devices

6- Precision medicine

7- Advances in the therapy of epileptic encephalopathies in children

References

Abstract

Despite the availability of many antiepileptic drugs (AEDs) (old and newly developed) and, as recently suggested, their optimization in the treatment of patients with uncontrolled seizures, more than 30% of patients with epilepsy continue to experience seizures and have drug-resistant epilepsy; the management of these patients represents a real challenge for epileptologists and researchers. Resective surgery with the best rates of seizure control is not an option for all of them; therefore, research and discovery of new methods of treating resistant epilepsy are of extreme importance. In this article, we will discuss some innovative approaches, such as P-glycoprotein (P-gp) inhibitors, gene therapy, stem cell therapy, traditional and novel antiepileptic devices, precision medicine, as well as therapeutic advances in epileptic encephalopathy in children; these treatment modalities open up new horizons for the treatment of patients with drug-resistant epilepsy.

Introduction

For decades, the epilepsy community has addressed the burden of drug-resistant epilepsy by focusing on the development of new antiepileptic drugs (AEDs) and advancing epilepsy surgery techniques. These approaches have resulted in some success, but the percentage of patients with drug-resistant epilepsy has not changed substantially. More than 30% of individuals with epilepsy have persistent seizures despite the use of appropriate therapies, i.e., they have drug-resistant epilepsy [1–3]. Therefore, investigating and discovering new ways and strategies to treat epilepsy is of paramount significance. There are multiple approaches in the pipeline to treat drug-resistant epilepsy. In this article, we are going to discuss some of the interesting and innovative approaches, which are potentially opening new horizons in treating patients with drug-resistant epilepsy. We have to mention that many of these plausible strategies need to be validated and should be tested in large double-blind randomized clinical trials.

Purpose: To explore whether complement dysregulation occurs in a routinely recruited clinical cohort of epilepsy patients, and whether complement biomarkers have potential to be used as markers of disease severity and seizure control. Methods: Plasma samples from 157 epilepsy cases (106 with focal seizures, 46 generalised seizures, 5 unclassified) and 54 controls were analysed. Concentrations of 10 complement analytes (C1q, C3, C4, factor B [FB], terminal complement complex [TCC], iC3b, factor H [FH], Clusterin [Clu], Properdin, C1 Inhibitor [C1Inh] plus C-reactive protein [CRP]) were measured using enzyme linked immunosorbent assay (ELISA). Univariate and multivariate statistical analysis were used to test whether combinations of complement analytes were predictive of epilepsy diagnoses and seizure occurrence. Correlation between number and type of anti-epileptic drugs (AED) and complement analytes was also performed. Results: We found: 1) significant differences between all epilepsy patients and controls for TCC (p < 0.01) and FH (p < 0.01) after performing univariate analysis. 2) multivariate analysis combining six analytes (C3, C4, Properdin, FH, C1Inh, Clu) to give a predictive value (area under the curve) of 0.80 for differentiating epilepsy from controls. 3) significant differences in complement levels between patients with controlled seizures (n = 65) in comparison with uncontrolled seizures (n = 87). Levels of iC3b, Properdin and Clu were decreased and levels of C4 were increased in patients with uncontrolled seizures. 4) no correlation was found between the level of complement biomarkers and the number of AEDs taken, but an association between some analyte levels and drug therapy was seen in patients taking sodium valproate, clobazam, and perampanel. Conclusion: This study adds to evidence implicating complement in pathogenesis of epilepsy and may allow the development of better therapeutics and prognostic markers in the future. Replication in a larger sample set is needed to validate the findings of the study.

Introduction

Epilepsy is a common disease; in England the prevalence of people with epilepsy who take anti-epileptic medication is 0.43– 1.16% [1]. The 2017 International League Against Epilepsy consensus on epilepsy classification highlights the importance of defining aetiology, including immune causes [2]. Despite contemporary advances in neuroimaging and clinical genetics, the aetiology of epilepsy is stillunknown in over a third ofcases and a third ofpatients have seizures resistantto current antiepileptic drugs (AEDs)[3,4]. In these cases resective surgery is the best current option and can be curative, particularly in temporal lobe epilepsy; however; seizure recurrence occurs inuptohalf of patients within5 years of operation [5]. Thus far precision medicine in epilepsy has been limited to the realm ofthe genetic encephalopathies [6]. A better understanding of aetiology would enable more effective treatment, targeted towards underlying pathogenic mechanisms [7]. Increasing evidence from experimental animal models and resected human brain tissue supports a role of the immune system in epilepsy [8]. At the population level there are prevalence correlations between auto-immune disorders and epilepsy; the risk of epilepsy is 3.8 times greater in people with any one of 12 autoimmune disorders and even higher in children with autoimmunity [9]. Systemic autoimmune disorders, such as systemic lupus erythematosus, have a neurological phenotype that includes a predeliction for seizures [2]. The most studied forms of immune epilepsy are Rasmussen’s encephalitis, and the autoimmune encephalitidies associated with circulating antibodies [10]. Currently, primary immune-mediated epilepsies are recognised as neural autoantibody disorders affecting both cell-surface expressed proteins such as LGI1 and N-methyl-D-aspartate (NMDA) receptor, and intacellular proteins such as GAD [11]. A study of neural auto-antibodies in epilepsies of apparent unknown aetiology suggested that immune activation may explain up to 20% of non-paraneoplastic cases [12].

An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively.

INTRODUCTION

According to the World Health Organization (WHO), nearly 50 million people suffer from epilepsy worldwide [1]. It is estimated that 2.4 million people are diagnosed with epilepsy annually [1]. Seizures are due to the uncontrolled electrical discharges in a group of neurons. [2, 3]. The excessive electrical discharges result in the disruption of brain function. Epilepsy is diagnosed when there is recurrence of at least two unprovoked seizures. It can affect anyone at any age [4]. A timely and accurate diagnosis of epilepsy is essential for patients in order to initiate anti-epileptic drug therapy and subsequently reduce the risk of future seizures and seizurerelated complications [5]. Currently, the diagnosis of epilepsy is made by obtaining a detailed history, performing a neurological exam, and ancillary testing such as neuro-imaging and EEG. The EEG signals can identify inter-ictal (between seizures) and ictal (during seizure) epileptiform abnormalities. Figure 1 shows a graphical representation of the electrical activity in the brain of healthy subjects and seizure patients. Typically, neurons communicate through electrical signals. Therefore, in a regular brain activity, these electrical signals are normally regulated [3] (see the normal activity in Figure 1). However, during seizure, there is an abnormally increased hypersynchronous electrical activity of epileptogenic neural network. This activity may remain localized to one part of the brain, or spread to the entire brain. In either scenario, an individual may experience a clinical seizure (see the seizure activity in Figure 1) [3]. Neurologists scrutinize the EEG via direct visual inspection to investigate for epileptiform abnormalities that may provide valuable information on the type and etiology of a patient’s epilepsy. However, interpretation of the EEG signals by visual assessment is time-consuming particularly with the increased use of out-patient ambulatory EEG’s and in-patient continuous video EEG recordings, where there are hours or days worth of EEG data that needs to be reviewed manually [6]. The majority of EEG software includes some form of automated seizuredetection, however, due to the poor sensitivity and specificity of the pre-determined seizure detection algorithms, the current forms of automated seizure detection are rarely used in clinical practice. In addition, the inherent nature of visual inspection results in varying clinical interpretations based on the EEG reader’s level of expertise in electroencephalography. Complicating matters, the quality of the study may be confounded by interfering artifactual signal limiting the reader’s ability to accurately identify abnormalities. Moreover, the low yield of routine out-patient studies poses another problem. A patient with epilepsy can go for an outpatient EEG and the study may be completely normal. This is because the brains of patients with epilepsy are generally not continually firing off epileptic discharges.

People with epilepsy (PWE) frequently suffer from comorbid mood and anxiety disorders. Depression is one of the major psychiatric comorbidities having a negative impact on the quality of life in people with epilepsy. A review of the literature indicates that the majority of antidepressant-related seizures have been associated with either ultra-high doses or overdosing and, generally, the risk of antidepressant-associated seizures is low. Correspondingly, there is some evidence indicating that antidepressants of most widely used groups may additionally lower the risk of triggering seizures. Four antidepressants are not recommended for patients with epilepsy, i.e.: amoxapine, bupropion, clomipramine and maprotiline. Clinicians applying first line of depression treatment in patients with epilepsy should consider use of SSRIs or SNRIs, particularly sertraline, citalopram, mirtazapine, reboxetine, paroxetine, fluoxetine, escitalopram, fluvoxamine, venlafaxine, duloxetine. Implementation of anticonvulsive drugs in depressed patients should include valproate, carbamazepine, lamotrigine, gabapentin, pregabalin. The paper reviews the evidence for the clinical use of antidepressants in PWE.

Introduction

People with epilepsy (PWE) frequently suffer from comorbid mood disorders. Lifetime prevalence ranges between 11% and 62% [1]. One of the major psychiatric comorbidities having a negative impact on the quality of life in PWE is depression [2]. The relationship between depression and epilepsy may be bidirectional; having depression would increase the risk of epilepsy, and having epilepsy appears to increase the risk of depression [3]. Suicide attempts among depressed PWE are four- to fivefold more frequent than in the general population [4–6]. Depression has also been associated with higher rates of drug resistance in PWE [7]. Considering these issues the successful and safe treatment of depression associated with epilepsy is of utmost clinical importance. Also psychotherapy must be mentioned as effective and safe therapeutic intervention in PWE suffering from depression [8]. Guidelines indicating the choice of psychotropic drugs in PWE are mainly based on studies in patients without epilepsy, as well as risk evaluation of seizures [9,10]. Antidepressants may impact the incidence of seizures in a dose-related manner in line with the animal model of epilepsy [11]. The anticonvulsive effect is noticed at low doses and with the increase of the dose the effect is being reversed [12]. A review of the literature indicates that most antidepressant-related seizures have been associated with either ultrahigh doses or particularly in overdosing [13]. The paper reviews best practice indications for antidepressant treatment in patients with epilepsy.

چکیده

بیماران مبتلا به صرع (به اصطلاح: PWE) غالباً از اختلالات رفتاری و اضطراب به طور همزمان رنج می‌برند. افسردگی یکی از مهم ترین اختلالات روانپزشکی است که به طور مستقیم بر روی کیفیت زندگی بیماران مبتلا به صرع تاثیر منفی می‌گذارد. بررسی‌ها نشانگر آن است که اکثر تشنج‌های ناشی از داروهای ضدافسردگی به دلیل دوزهای بسیار بالا صورت می‌گیرد و بدین ترتیب، خطر تشنج ناشی از مصرف داروهای ضدافسردگی کم می‌باشد.این در حالی است که شواهد نشان می‌دهد داروهای ضدافسردگی مورداستفاده ریسک ابتلا به تشنج را نیز کاهش می‌دهند. چهار داروی ضدافسردگی برای بیماران مبتلا به صرع توصیه نمی‌گردد که از آنها می‌توان به آموکساپین، بوپروپیون، کلومیپرامین و ماپروتیلین اشاره نمود. متخصصان بالینی در وهلۀ نخست باید در خصوص بیماران مبتلا به صرع اس‌اس‌آرآی‌ها و اس‌ان‌آرآی‌ها به ویژه سرتالین، سیتالوپرام، میرتازاپین، ربوکستین، پاروکستین، فلوکستین، اسیتالوپرام، فلووکسامین، ونلافاکسین و دولوکستین را تجویز نمایند.

There is increasing evidence of an association between long-term environmental exposure to pesticides and neurodegenerative disorders; however, the relationship with epilepsy has not been addressed thus far. This study was aimed at determining the prevalence and risk of developing epilepsy among people from South-East Spain living in areas of high vs. low exposure to pesticides based on agronomic data. The study population consisted of 4007 subjects with a diagnosis of epilepsy and 580,077 control subjects adjusted for age, sex and geographical area. Data were collected from hospital records of the Spanish health care system (basic minimum dataset) between the years 1998 and 2010. The prevalence of epilepsy was significantly higher in areas of greater pesticide use relative to areas of lesser use. Overall, an increased risk of epilepsy was observed in the population living in areas of high vs. low use of pesticides (OR:1.65; p <0.001). Although this study was exploratory in nature, the results suggest that environmental exposure to pesticides might increase the risk of having epilepsy.

INTRODUCTION

Epilepsy is the most common severe neurological disorder (Sander, 2003) affecting 0.5–1%, of the world population, with a lifetime incidence of 1–3% (MichaelTitus et al., 2010). It is estimated that 70 million patients around the world are diagnosed with epilepsy at any stage of life (OMS, 2015) as the disease can occur at any age, from birth to childhood and also among adults, including the older age groups (Rados, 2005). However, the occurrence, prevalence, and burden of epilepsy vary widely throughout the world (Banerjee et al., 2009), showing higher rates in developing countries than in developed countries (Perucca et al., 2001; Preux and Druet-Cabanac, 2005) as 90% of patients are thought to live in Africa, Asia, and Latin America (Houinato et al., 2013). In Spain, there are around 400,000 diagnosed epilepsy cases with 12,400 to 22,000 people showing symptoms for the first time every year. The majority of them are children, between 6 and 14 years old, with a rate of 3.7 cases per 1000 inhabitants (SEN, 2009). Risk factors for epilepsy are multiple and include genetic background, trauma, brain tumor, metabolic disturbances, infections, autoimmune reactions, and chemical exposures (Jovel et al., 2018; Pauschek et. al. 2016). Nevertheless, epilepsy likely result from interactions between the genetically-determined seizure threshold, underlying predisposing medical conditions or metabolic disorders, and acute triggers (Guberman and Bruni, 1999). Acquired epilepsy usually develops in three phases: injury (brain insult), epileptogenesis (latency) and chronic epilepsy (spontaneous recurrent seizure) (Raza et al., 2004). A number of chemicals may cause seizures by a variety of molecular mechanisms and pathways. In addition, exposure to some chemicals during critical periods of development can disrupt neurodevelopment and potentiate the response to toxicants later in life (Ramsdell, 2010). In this regard, animals have shown to be more prone to generate seizures when stimulated in critical developmental periods (Stanojlović et al., 2013).