Principal Components Analysis of EEG Signals for Epileptic Patient Identification

According to the behavior of its neuronal connections, it is possible to determine if the brain suffers from abnormalities such as epilepsy. This disease produces seizures and alters the patient’s behavior and lifestyle. Neurologists employ the electroencephalogram (EEG) to diagnose the disease through brain signals. Neurologists visually analyze these signals, recognizing patterns, to identify some indication of brain disorder that allows for the epilepsy diagnosis. This article proposes a study, based on the Fourier analysis, through fast Fourier transformation and principal component analysis, to quantitatively identify patterns to diagnose and differentiate between healthy patients and those with the disease. Subsequently, principal component analysis can be used to classify patients, employing frequency bands as the signal features. Besides, it is made a classification comparison before and after using principal component analysis. The classification is performed via logistic regression, with a reduction from 5 to 4 dimensions, as well as from 8 to 7, achieving an improvement when there are 7 dimensions in the precision, recall, and F1 score metrics. The best results obtained, without PCA are: precision 0.560, recall 0.690, and F1 score 0.620; meanwhile, the best values obtained using PCA are: precision 0.734, recall 0.787, and F1 score 0.776.

Cognitive Decline Risk Stratification in People with Late-Onset Epilepsy of Unknown Etiology: An Electroencephalographic Connectivity and Graph Theory Pilot Study

Background: Although people with late onset epilepsy of unknown etiology (LOEU) are at higher risk of cognitive decline compared to the general population, we still lack affordable tools to predict and stratify their risk of dementia. Objective: This pilot-study investigates the potential application of electroencephalography (EEG) network small-world (SW) properties in predicting cognitive decline among patients with LOEU. Methods: People diagnosed with LOEU and normal cognitive examination at the time of epilepsy diagnosis were included. Cerebrospinal fluid biomarkers, brain imaging, and neuropsychological assessment were performed at the time of epilepsy diagnosis. Baseline EEG was analyzed for SW properties. Patients were followed-up over time with neuropsychological testing to define the trajectory of cognitive decline. Results: Over 5.1 years of follow-up, among 24 patients diagnosed with LOEU, 62.5% were female, mean age was 65.3 years, thirteen developed mild cognitive impairment (MCI), and four developed dementia. Patients with LOEU developing MCI had lower values of SW coefficients in the delta (p = 0.03) band and higher SW values in the alpha frequency bands (p = 0.02) compared to patients having normal cognition at last follow-up. The two separate ANOVAs, for low and alpha bands, confirmed an interaction between SW and cognitive decline at follow-up. A similar gradient was confirmed for patients developing dementia compared to those with normal cognitive function as well as to those developing MCI. Conclusion: Baseline EEG analysis through SW is worth investigating as an affordable, widely available tool to stratify LOEU patients for their risk of cognitive decline.

WTRPNet: An Explainable Graph Feature Convolutional Neural Network for Epileptic EEG Classification

As one of the important tools of epilepsy diagnosis, the electroencephalogram (EEG) is noninvasive and presents no traumatic injury to patients. It contains a lot of physiological and pathological information that is easy to obtain. The automatic classification of epileptic EEG is important in the diagnosis and therapeutic efficacy of epileptics. In this article, an explainable graph feature convolutional neural network named WTRPNet is proposed for epileptic EEG classification. Since WTRPNet is constructed by a recurrence plot in the wavelet domain, it can fully obtain the graph feature of the EEG signal, which is established by an explainable graph features extracted layer called WTRP block . The proposed method shows superior performance over state-of-the-art methods. Experimental results show that our algorithm has achieved an accuracy of 99.67% in classification of focal and nonfocal epileptic EEG, which proves the effectiveness of the classification and detection of epileptic EEG.

Assess Self-Management and Adherence to Use Antiepileptic Drugs in Epileptic Pediatric Patients: Cross Sectional Study

Background: No adherence to antiepileptic drugs is a considerable problem for epileptic suffered children and their families. Aim: To determine self-management and adherence to antiepileptic drugs among epileptic children. Study Design: Cross sectional study. Methodology: Present study conducted at Children Complex Hospital, Multan. Sample size was 105. Data was collected after taken the informed consent from the study participants. Institutional approval was taken. Data analyzed through latest version of SPSS 25, including mean, percentage and frequency. Results: Majority 6(81.9%) agreed that doctors/nurses fully explained seizures/epilepsy (diagnosis). Significant correlation was seen between gender and dependent variables (transportation available and medications) with p-value of less than 0.05. Conclusion: This study clearly showed that most patients were well aware about their diagnosis told by doctors and had a knowledge about consequences due to non-adherence with their treatment. Keywords: Adherence, Self-Assessment and Anti-Epileptic Drugs.

Evaluation and Management of First-Time Seizure in Adults

First seizures are often perceived as devastating events by patients and their families due to the fear of having a life-long disease. One in 10 people experiences one or more seizures during their lifetime, while 1 in 26 people develops epilepsy. Acute symptomatic seizures are often related to a provoking factor or an acute brain insult and typically do not recur. Careful history and clinical examination should guide clinicians' management plans. Electroencephalography and brain imaging, preferably with epilepsy-specific magnetic resonance imaging, may help characterize both etiology and risk of seizure recurrence. Antiepileptic drugs should be initiated in patients with newly diagnosed epilepsy. In patients without an epilepsy diagnosis, the decision to prescribe drugs depends on individual risk factors for seizure recurrence and possible complications from seizures, which should be discussed with the patient. Counseling about driving and lifestyle modifications should be provided early, often at the first seizure encounter.

CNN for a Connectivity Based Epilepsy Diagnosis with Resting-state EEG

Objective: This study investigates the performance of a CNN algorithm on epilepsy diagnosis. Without pathology, diagnosis involves long and costly electroencephalographic (EEG) monitoring. Novel approaches may overcome this by comparing brain connectivity using graph metrics. This study, however, uses deep learning to learn connectivity patterns directly from easily acquired EEG data. Approach: A convolutional neural network (CNN) algorithm was applied on directed Granger causality (GC) connectivity measures, derived from 50 seconds of resting-state surface EEG recordings from 30 subjects with epilepsy and a 30 subject control group. Main results: The learned CNN filters reflected reduced delta band connectivity in frontal regions and increased left lateralized frontal-posterior gamma band connectivity. A diagnosis accuracy of 85% (F1-score 85%) was achieved by an ensemble of CNN models, each trained on differently prepared data from different electrode combinations. Conclusions: Appropriate preparation of connectivity data enables generic CNN algorithms to be used for detection of multiple discriminative epileptic features. Differential patterns revealed in this study may help to shed light on underlying altered cognitive abilities in epilepsy patients. Significance: The accuracy achieved in this study shows that, in combination with other methods, this approach could prove a valuable clinical decision support system for epilepsy diagnosis.

Applying nonlinear measures to the brain rhythms: an effective method for epilepsy diagnosis

Background Epilepsy is a neurological disorder from which almost 50 million people have been suffering. These statistics indicate the importance of epilepsy diagnosis. Electroencephalogram (EEG) signals analysis is one of the most common methods for epilepsy characterization; hence, various strategies were applied to classify epileptic EEGs. Methods In this paper, four different nonlinear features such as Fractal dimensions including Higuchi method (HFD) and Katz method (KFD), Hurst exponent, and L-Z complexity measure were extracted from EEGs and their frequency sub-bands. The features were ranked later by implementing Relieff algorithm. The ranked features were applied sequentially to three different classifiers (MLPNN, Linear SVM, and RBF SVM). Results According to the dataset used for this study, there are five classification problems named ABCD/E, AB/CD/E, A/D/E, A/E, and D/E. In all cases, MLPNN was the most accurate classifier. Its performances for mentioned classification problems were 99.91%, 98.19%, 98.5%, 100% and 99.84%, respectively. Conclusion The results demonstrate that KFD is the highest-ranking feature; In addition, beta and theta sub-bands are the most important frequency bands because, for all cases, the top features were KFDs extracted from beta and theta sub-bands. Moreover, high levels of accuracy have been obtained just by using these two features which reduce the complexity of the classification.