Seizures In Epilepsy Patients Research Articles

A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion

Epilepsy, a chronic non-communicable disease is characterized by repeated unprovoked seizures, which are transient episodes of abnormal electrical activity in the brain. While Electroencephalography (EEG) is considered as the gold standard for diagnosis in current clinical practice, manual inspection of EEG is time consuming and biased. This paper presents a novel hybrid 1D CNN-Bi LSTM feature fusion model for automatically detecting seizures. The proposed model leverages spatial features extracted by one dimensional convolutional neural network and temporal features extracted by bi directional long short-term memory network. Ictal and inter ictal data is first acquired from the long multichannel EEG record. The acquired data is segmented and labelled using small fixed windows. Signal features are then extracted from the segments concurrently by the parallel combination of CNN and Bi-LSTM. The spatial and temporal features thus captured are then fused to enhance classification accuracy of model. The approach is validated using benchmark CHB-MIT dataset and 5-fold cross validation which resulted in an average accuracy of 95.90%, with precision 94.78%, F1 score 95.95%. Notably model achieved average sensitivity of 97.18% with false positivity rate at 0.05/hr. The significantly lower false positivity and false negativity rates indicate that the proposed model is a promising tool for detecting seizures in epilepsy patients. The employed parallel path network benefits from memory function of Bi-LSTM and strong feature extraction capabilities of CNN. Moreover, eliminating the need for any domain transformation or additional preprocessing steps, model effectively reduces complexity and enhances efficiency, making it suitable for use by clinicians during the epilepsy diagnostic process.

The impact of omega-3 on recurrent seizures in epileptic patients: A case study with evidence-based approaches

Background: Epileptogenesis is also associated with increased production of excessive pro-inflammatory cytokines” which shows connection between pro-inflammatory cytokines as triggering factor with omega-3 which has anti-inflammatory effect. Omega-3, known for its neuroprotective and anticonvulsant properties, exhibits promising effects on epileptic seizure attacks.
 Objective: This study aimed to evaluate the effect of omega-3 supplementation on the incidence of seizures in epilepsy patients.
 Methods: This study used a literature search using advanced queries in the databases PubMed, Scopus, ProQuest, and Cochrane Library, and combined MeSH terms with Title/Abstract. The collected literature is discarded if there are duplicates, then literature is filtered that meets the eligibility criteria. We used the Oxford Center for Evidence-Based Medicine as a means of critical appraisal and determining the level of evidence of the selected literature.
 Results: Four chosen literatures were critically assessed. Two articles indicating no significant difference between omega-3 and placebo and two articles showed had a significantly higher number of seizure-free days than placebo. The first article, involving 78 adults, reported a 50% reduction in seizure risk with a frequency RR of 0.57, 95% CI 0.19 to 1.75 (IS = 0%) indicating no significant difference between omega-3 and placebo groups after 12 weeks of treatment. The second study, comprising mostly non-significant findings, demonstrated no significant correlation between omega-3 and epilepsy attacks in epilepsy patients. The third literature revealed seizure occurrences per month in the EPA group (9.7±1.2), DHA group (11.7±1.5), and placebo group (16.6±1.5). Incidence rate ratio (IRR) adjusted for seizure type in EPA and DHA groups compared to the placebo group were 0.61 (CI = 0.42–0.88, p = 0.008, a 42% reduction) and 0.67 (CI = 0.46–1.0, p = 0.04, a 39% reduction), respectively. Both treatment groups had a significantly higher number of seizure-free days compared to the placebo group (p < 0.05). The fourth study reported intervention group frequency (4.72 ± 1.6, p= 0.014) and placebo frequency (11.64 ± 1.63, p=0.014) with intervention group seizure duration (6.64 ± 1.39, p=0.009) compared to placebo group (14.36 ± 2.18, p=0.009).
 Conclusion: Omega-3 supplementation may be considered for management in patients with recurrent epileptic seizures, although its effect on reducing seizure frequency remains inconsistent.

Seizure Pathways Changes at the Subject-Specific Level via Dynamic Step Effective Network Analysis.

The variability in the propagation pathway in epilepsy is a main factor contributing to surgical treatment failure. Ways to accurately capture the brain propagation network and quantitatively assess its evolution remain poorly described. This work aims to develop a dynamic step effective network (dSTE) to obtain the propagation path network of multiple seizures in the same patient and explore the degree of dissimilarity. Multichannel stereo-electroencephalography (sEEG) signals were acquired with ictal processes involving continuous changes in information propagation. We utilized high-order dynamic brain networks to obtain propagation networks through different levels of linking steps. We proposed a dissimilarity index based on singular value decomposition to quantitatively compare seizure pathways. Simulated data were generated through The Virtual Brain, and the reliability of this method was verified through ablation experiments. By applying the proposed method to two datasets consisting of 29 patients total, the evolution processes of each patient's seizure networks was obtained, and the within-patient dissimilarities were quantitatively compared. Finally, three types of brain network connectivity patterns were found. Type I patients have a good prognosis, while type III patients are prone to postoperative recurrence. This method captures the evolution of seizure propagation networks and assesses their dissimilarity more reliably than existing methods, demonstrating good robustness for studying the propagation path differences for multiple seizures in epilepsy patients. The three different patterns will be important considerations when planning epilepsy surgery under sEEG guidance.

Epidemiology of focal onset seizures in children aged >1 month to 4 years in Europe, United States, and Canada: A literature review.

The present study aims to report the currently available epidemiology of focal onset seizures in children aged >1 month to 4 years with the help of a literature review. The terms 'seizure*' OR 'epilepsy' combined with pediatric and epidemiology terms were used to search Embase, PubMed, and Web of Science up to November 16, 2021. Due to the scarcity of epidemiology data on focal onset seizures, the incidence and prevalence were estimated using the proportion of focal onset seizures in epilepsy patients from the most recently published articles. The estimated annual incidence per 100,000 children of focal onset seizures in children of 0-4 years of age ranged from 25.1 (95% confidence interval [CI] 18.9-32.7) in the United Kingdom to 111.8 in the United States. The estimated period prevalence of focal onset seizures in children 0-4 years of age ranged from 0.15% (99% CI 0.13-0.18) in Canada to 0.61% in the United States. Neurodevelopmental outcomes and psychiatric disorders were the most commonly reported comorbidities in children with epilepsy of age 0-4 years. Presence of focal onset seizures in children with different epilepsy syndromes needs to be thoroughly considered in the treatment planning of this population of interest.

The Application of Deep Learning to Electroencephalograms, Magnetic Resonance Imaging, and Implants for the Detection of Epileptic Seizures: A Narrative Review.

Epilepsy is a neurological disorder characterized by recurrent seizures affecting millions worldwide. Medically intractable seizures in epilepsy patients are not only detrimental to the quality of life but also pose a significant threat to their safety. Outcomes of epilepsy therapy can be improved by early detection and intervention during the interictal window period. Electroencephalography is the primary diagnostic tool for epilepsy, but accurate interpretation of seizure activity is challenging and highly time-consuming. Machine learning (ML) and deep learning (DL) algorithms enable us to analyze complex EEG data, which can not only help us diagnose but also locate epileptogenic zones and predict medical and surgical treatment outcomes. DL models such as convolutional neural networks (CNNs), inspired by visual processing, can be used to classify EEG activity. By applying preprocessing techniques, signal quality can be enhanced by denoising and artifact removal. DL can also be incorporated into the analysis of magnetic resonance imaging (MRI) data, which can help in the localization of epileptogenic zones in the brain. Proper detection of these zones can help in good neurosurgical outcomes. Recent advancements in DL have facilitated the implementation of these systems in neural implants and wearable devices, allowing for real-time seizure detection. This has the potential to transform the management of drug-refractory epilepsy. This review explores the application of ML and DL techniques to Electroencephalograms (EEGs), MRI, and wearable devices for epileptic seizure detection. This review briefly explains the fundamentals of both artificial intelligence (AI) and DL, highlighting these systems' potential advantages and undeniable limitations.

Evaluation of postictal optic nerve sheath diameter at epileptic patients

IntroductionDuring a seizure, metabolic rate and, consequently, cerebral blood flow increase to provide the required maintenance energy. It is thought that this causes an increase in intracranial pressure, but there is no comprehensive research on this subject. In this study, we aimed to measure and follow optic nerve sheath diameter (ONSD) in patients who applied to the emergency department (ED) after generalized tonic-clonic (GTC) seizures and to gain information about intracranial pressure changes in epilepsy patients in the postictal period. Materials and MethodsThis was a prospective observational study. Patients already diagnosed with epilepsy who applied to the ED within one hour after GTC seizures were included. The ONSD of the patients was measured by the same radiologist three times in both eyes using ultrasonography at the time of admission and the fourth hour of follow-up. The seizure characteristics and measurements of the patients were recorded, and the changes in ONSD over time and correlations between seizure characteristics and ONSD were examined. ResultsSixty-six patients were included in the study. Thirty-four (51.5%) of the patients had seizures with auras. For both eyes, the first-hour ONSD values of the patients [right: 5.90 (5.73–6.16) mm, left: 5.86 (5.73–6.13) mm] were significantly higher than the fourth-hour ONSD values [right: 5.26 (5.19–5.40) mm, left: 5.28 (5.16–5.36) mm)] (p < 0.001 for both eyes). Additionally, the first- and fourth-hour ONSD values of patients with seizures with auras were significantly higher than those with seizures without auras (p < 0.001 for each condition). There was no correlation between other variables related to seizure type and ONSD. ConclusionThis study showed that after GTC seizures in epilepsy patients, ONSD increases in the first hour postictal and decreases over time. Another important result is that the increase in ONSD values in seizures with auras is significantly higher than in seizures without auras.

Electrographic seizure duration and inter-seizure intervals in focal status epilepticus.

To characterize the duration of seizures and inter-seizure intervals in focal status epilepticus (SE). We reviewed consecutive scalp EEG recordings from adult patients who were admitted for a first episode of focal status epilepticus. We identified electrographic seizure duration and inter-seizure intervals in the first diagnostic pretreatment EEG. We also reviewed isolated focal self-limiting seizures in epilepsy patients, as a comparison group for seizure duration. We recorded 307 focal seizures in 100 consecutive focal SE episodes, with a median seizure duration of 107 s (IQR: 54-186), and 134 isolated focal self-limiting seizures in 42 epilepsy patients, with a median duration of 59 s (IQR: 30-90; p < .001). The only clinical feature of SE that significantly increased seizure duration was acute symptomatic etiology. In SE, 15% and 7% of seizures lasted longer than 300 and 600 s, respectively (t1 of the actual definition for tonic-clonic and focal SE), while only 1% of self-limiting seizures lasted longer than 300 s, and none lasted longer than 600 s. The analysis of inter-seizure intervals in SE with multiple seizures showed that 50% of the inter-seizure periods were shorter than 60 s, and 95% were shorter than 540 s (9 min). Patients who had an increase in seizure duration (last versus first) of at least 1.4 times showed an increased 30-day mortality. Focal seizures within a SE episode showed a wide range of duration, partly overlapping with the duration of focal self-limiting seizures but with a longer median duration. Inter-seizure intervals within an episode of SE were shorter than 1 min in 50% of the seizures and never lasted more than 10 min. Finally, an increase in seizure duration could represent an "electrophysiological biomarker" of a more severe SE episode, which may require more aggressive and rapid treatment.

Association of the Meteorological Parameters and Epileptic Seizures

Climate changes may be among the triggering factors in predicting epileptic seizures. In this study, we aimed to investigate the effects of changes in weather conditions and phases of the moon on epileptic seizures in epilepsy patients.

Serum levels of matrix metalloproteinase 2 and its inhibitor after tonic-clonic seizures

Damage to the blood-brain barrier (BBB) may result from on-going neuroinflammation, which can lead to leakage of blood components, such as leukocytes and serum proteins, into the brain, resulting in disturbed brain homeostasis. The aim of the project was to examine the involvement of modulatory proteins in the processes of BBB integration after epileptic seizures. We investigated serum changes in the levels of MMP-2 and MMP-7 and its inhibitors after seizures in epilepsy patients. Concentrations of these proteins were measured by ELISA in 50 patients at 1–3, 24, and 72 h after generalized tonic-clonic seizures and once in participants of the control group. The level of MMP-2 in serum was slightly higher after seizures (at 1–3 h time point), but the difference was not statistically significant. The levels of trombospondine (TSP) − 1 and − 2 were decreased at 1–3 h after seizures. The expression of TIMP-2 was increased 1 and 24 h after seizures. There were no significant changes in the level of α2-macroglobulin and MMP-7. Changes in the expression of both specific and non-specific inhibitors indicate the initiation of repair processes of the blood-brain barrier and improvement of its integrity. Since we performed serum analysis, further studies are necessary to investigate the correlation with the expression of the investigated markers in the brain. Perhaps this will allow for the identification of new biomarkers associated with epileptic seizures.

Interaction between COVID-19 and epilepsy during the omicron surge: A cross-sectional survey conducted in China tertiary hospital.

It is unclear whether patients with epilepsy are more susceptible to SARS-CoV-2 infection, whether they experience more severe manifestations of COVID-19, and whether seizures worsen after SARS-CoV-2 infection. Our study aims to explore these points and provide comprehensive and practical guidance for patients with epilepsy. We designed a questionnaire to collect variables from epilepsy patients. We used the Chi-square test, Fisher's exact test, or Mann-Whitney U test to analyze differences between the two groups. Multiple logistic regressions were employed to determine the risk factors for relevant outcome variables. We identified a total of 181 patients, with 74% (n=134) reporting COVID-19. The patients' educational level was found to be a risk factor for COVID-19 (OR=0.33, 95% CI 0.14-0.80, P=0.013). When comparing seizure frequency changes between epilepsy patients with and without COVID-19, no statistically significant difference was observed (P>0.05). However, an increase in seizure frequency was significantly associated with higher levels of anxiety (P<0.001) and depression (P<0.005). The risk of COVID-19 infection may be increased in patients with epilepsy. COVID-19 infection does not seem to worsen seizures in epilepsy patients. Patients with epilepsy rarely develop more severe clinical manifestations of COVID-19 after SARS-CoV-2 infection. During the COVID-19 pandemic, patients with epilepsy who also suffer from anxiety and depression may experience an increase in the frequency of their seizures.

Effectivity of Pyridoxine as Adjuvant Therapy of Phenytoin in Patients with Epilepsy at Soebandi Regional Hospital Jember

Phenytoin is an antiepileptic drug used as monotherapy for partial and generalized tonic-clonic seizures for more than 50 years. Pyridoxine is a water-soluble vitamin widely used for seizure patients unresponsive to standard treatment regimens. This study was conducted to determine the effect of pyridoxine as adjuvant therapy in epilepsy patients receiving phenytoin and to determine the relationship between age, gender, type of epilepsy, and duration of therapy on the incidence of seizures in epilepsy patients at Soebandi Regional Hospital Jember. This research is an observational analytic study with a cross sectional design. The data was taken from the patient's medical record at Soebandi Hospital Jember. The number of samples in each treatment group was 18 samples so the total number of samples in this study was 36 samples. Samples were taken using total sampling technique. Data analysis was performed using Chi-Square test on bivariate analysis and The Logistic test on multivariate analysis. The sample in this study was dominated by male patients (52.8%), aged 19-59 years (52.8%), had epilepsy with generalized seizure type (86.1%), and received therapy for &lt; 3 years (77.8%). The results of bivariate and multivariate analysis showed correlation between the administration of pyridoxine and the incidence of seizures, indicating that phenytoin therapy with pyridoxine adjuvants was more effective than monotherapy phenytoin. Other factors such as gender, age, type of epilepsy, and duration of therapy were not proven to have a correlation with the incidence of seizures in epilepsy patients at Soebandi Hospital Jember.

Effect of low frequency stimulation of olfactory bulb on seizure severity, learning, and memory in kindled rats

Low frequency deep brain electrical stimulation (LFS) is a potential therapeutic strategy to control seizures in epilepsy patients. Given the functional connection of the olfactory bulb with the hippocampal formation, in this study the effect of applying LFS in the olfactory bulb on seizure severity, and learning and memory was investigated in hippocampal kindling. In male Wistar rats (250–300 g), a tripolar electrode was inserted in the CA1 region of the right hippocampus to apply kindling stimulations and record the afterdischarges (ADs). Two bipolar electrodes were also inserted bilaterally into the olfactory bulbs for applying LFS. In the kindled group, the animals received daily kindling stimulations to produce stage 5 seizures for three consecutive days. In one group of subjects, LFS was administered 2–3 min after the last kindling stimulation. Within this group, subjects were divided into two subgroups: one subgroup received two and the other subgroup received four packages of LFS protocol. Obtained data showed that bilateral LFS application to the left and right olfactory bulb reduced seizure severity. Among the protocols, applying four packages of LFS had a greater anticonvulsant effect compared to applying two packages LFS. Applying LFS in the olfactory bulb of kindled subject restored performance on measures that test short- and long-term memory – the Y maze and Morris water maze test – and applying four packages of LFS was more effective than two. These results indicated that applying LFS to the olfactory bulb had anticonvulsant effects and ameliorated the seizure-induced impairment of working and spatial memory. These effects appear to be depended on the number of applied LFS and were greater by increasing the number of LFS.

Optimal Use of Perampanel in the Treatment of Patients with Epilepsy Based on the Clinical Evidence and Characteristics

Perampanel (PER) has been used clinically as monotherapy and adjunctive therapy for focal seizures and as adjunctive therapy for generalized tonic-clonic seizures in epilepsy patients in Japan. In recent years in Japan and worldwide, clinical studies have been conducted on patients with various seizure types of epilepsy. The results have shown that PER has broad spectrum properties. The pooled analysis of controlled trials (PERMIT study) showed PER efficacy in patients with status epilepticus, myoclonic seizures, and absence seizures. In addition, PER has been shown to be safe and effective in patients with juvenile myoclonic epilepsy, Lennox-Gastaut syndrome, and elderly-onset epilepsy that are often difficult to treat with narrow-spectrum ASM. In this review article, we summarize the latest findings on PER, and overview the broad spectrum characteristics of PER. In addition, we discuss the optimal use of PER for patients with epilepsy, focusing on low-dose initiation and on slow titration of PER to minimize adverse events. (Received December 7, 2021; Accepted March 29, 2022; Published July 1, 2022).

Nocturnal Seizure Detection Using Off-the-Shelf WiFi

The detection of nocturnal seizures in epilepsy patients is essential, both for the quick management of the seizure complications, and for the assessment of the ongoing seizure treatment. Traditional seizure detection products (e.g., wearables), however, are either very costly, uncomfortable, or unreliable. In this article, we then propose to utilize everyday WiFi signals for robust, fast, and noninvasive detection of nocturnal seizures. We first present a new and rigorous mathematical characterization for the spectral content/bandwidth of the WiFi signal, measured on a WiFi device placed near a sleeping patient, during different kinds of sleep motions: seizures, normal movements (e.g., posture adjustments), and breathing. Based on this mathematical modeling, we propose a novel pipeline for processing the received WiFi signals to robustly detect all nocturnal nonbreathing movements, and then classify them into normal body movements or seizures. In order to validate this, we carry out extensive experiments in seven different typical bedroom locations, where a set of 20 actors simulate the state of having seizures (a total of 260 instances), as well as normal sleep movements (a total of 410 instances). Our proposed system detects 93.85&#x0025; of the seizures with a mean response time (MRT) of only 5.69 s since the onset of the seizure. Moreover, our proposed system achieves a probability of false alarm of only 0.0097, when classifying normal sleep movements. Overall, our new mathematical modeling and experimental results show the great potential the ubiquitous WiFi signals have for detecting nocturnal seizures, which can provide better support for epilepsy patients and their caregivers.

Intra- and Inter-Subject Perspectives on the Detection of Focal Onset Motor Seizures in Epilepsy Patients.

Focal onset epileptic seizures are highly heterogeneous in their clinical manifestations, and a robust seizure detection across patient cohorts has to date not been achieved. Here, we assess and discuss the potential of supervised machine learning models for the detection of focal onset motor seizures by means of a wrist-worn wearable device, both in a personalized context as well as across patients. Wearable data were recorded in-hospital from patients with epilepsy at two epilepsy centers. Accelerometry, electrodermal activity, and blood volume pulse data were processed and features for each of the biosignal modalities were calculated. Following a leave-one-out approach, a gradient tree boosting machine learning model was optimized and tested in an intra-subject and inter-subject evaluation. In total, 20 seizures from 9 patients were included and we report sensitivities of 67% to 100% and false alarm rates of down to 0.85 per 24 h in the individualized assessment. Conversely, for an inter-subject seizure detection methodology tested on an out-of-sample data set, an optimized model could only achieve a sensitivity of 75% at a false alarm rate of 13.4 per 24 h. We demonstrate that robustly detecting focal onset motor seizures with tonic or clonic movements from wearable data may be possible for individuals, depending on specific seizure manifestations.

Metabolic Activation of Perampanel Mediated by CYP1A2

Perampanel (PRP), a noncompetitive α-amino-3-hydroxy-5-methyl-4-isoxazolepropanoic acid (AMPA) receptor antagonist with high selectivity, has been used as a new adjuvant for the treatment of fractional seizures with or without primary generalized tonic-clonic seizures and secondary generalized seizures in epilepsy patients over the age of 12. Adverse events such as liver injury have been reported during the clinical application of PRP. The purpose of the study is to explore the in vitro and in vivo metabolic activation of PRP. Two GSH conjugates were detected in rat liver microsomal incubations containing PRP, GSH, and NADPH. The two GSH conjugates were both obtained from the bile of rats and rat primary hepatocytes after exposure to PRP. Similar microsomal incubations complemented with N-acetylcysteine (NAC) in place of GSH offered two NAC conjugates. As expected, the NAC conjugates were detected in the urine of PRP-treated rats. One of the two NAC conjugates was identified as NAC conjugate 12 verified by chemical synthesis. The individual human recombinant P450 enzyme incubation assay demonstrated that CYP1A2 dominated the catalysis for the metabolic activation of PRP. Pretreatment with α-naphthoflavone (NTF) decreased the formation of PRP-derived GSH conjugates in both livers of rats and cultured primary hepatocytes after being treated with PRP. Additionally, NTF was found to decrease the susceptibility of primary hepatocytes to the cytotoxicity of PRP. The findings indicate that PRP was metabolized to the corresponding epoxide, which could participate in PRP-induced cytotoxicity.

Korelasi Tingkat Kepatuhan Konsumsi Obat Antiepilepsi Menggunakan Kuesioner MGLS (Morisky, Green, Levine Adherence Scale) dengan Frekwensi Kejang Pasien Epilepsi

Epilepsy is a chronic non-communicable brain disorder that can affect people of all ages. AED (antiepileptic drug) is the main therapy for most epilepsy patients with the overall goal being to prevent seizures without causing side effects. One measure of management of drug therapy in epilepsy is the decrease / loss of seizures, so that the frequency of seizures is one of the measures to achieve end-outcome. This study was an observational cross sectional study conducted on outpatients in Airlangga University Hospital, which aims to look at the relationship between the level of adherence using antiepileptic drugs with the incidence of seizures in epilepsy patients. The level of adherence with AED consumption in this study used the MGLS questionnaire (Morisky, Green, Levine Adherence Scale). The level of adherence based on the MGLS questionnaire was divided into 3 levels including low, medium or medium obedient and high compliant. The seizure events in epilepsy patients observed were the presence or absence of seizures during the past month, the data of which were obtained from patient or family interviews and from diary seizures. The results of the study of 40 respondents found that there was a moderate positive correlation between the level of adherence measured using the MGLS questionnaire whose majority level of adherence was moderate with the occurrence of seizures in epilepsy patients (r = 0.423 with p = 0.006 &lt;0.05.

Analysis of Brief Potentially Ictal Rhythmic Discharges (BIRDs) and seizures in Epilepsy Patients with Responsive Neurostimulation undergoing Scalp Electroencephalography (2982)

Analysis of Brief Potentially Ictal Rhythmic Discharges (BIRDs) and seizures in Epilepsy Patients with Responsive Neurostimulation undergoing Scalp Electroencephalography (2982)

Deep Convolutional Neural Network Based Interictal-Preictal Electroencephalography Prediction: Application to Focal Cortical Dysplasia Type-II.

We aimed to differentiate between the interictal and preictal states in epilepsy patients with focal cortical dysplasia (FCD) type-II using deep learning-based classifiers based on intracranial electroencephalography (EEG). We also investigated the practical conditions for high interictal-preictal discriminability in terms of spatiotemporal EEG characteristics and data size efficiency. Intracranial EEG recordings of nine epilepsy patients with FCD type-II (four female, five male; mean age: 10.7 years) were analyzed. Seizure onset and channel ranking were annotated by two epileptologists. We performed three consecutive interictal-preictal classification steps by varying the preictal length, number of electrodes, and sampling frequency with convolutional neural networks (CNN) using 30 s time-frequency data matrices. Classification performances were evaluated based on accuracy, F1 score, precision, and recall with respect to the above-mentioned three parameters. We found that (1) a 5 min preictal length provided the best classification performance, showing a remarkable enhancement of >13% on average compared to that with the 120 min preictal length; (2) four electrodes provided considerably high classification performance with a decrease of only approximately 1% on average compared to that with all channels; and (3) there was minimal performance change when quadrupling the sampling frequency from 128 Hz. Patient-specific performance variations were noticeable with respect to the preictal length, and three patients showed above-average performance enhancements of >28%. However, performance enhancements were low with respect to both the number of electrodes and sampling frequencies, and some patients showed at most 1–2% performance change. CNN-based classifiers from intracranial EEG recordings using a small number of electrodes and efficient sampling frequency are feasible for predicting the interictal-preictal state transition preceding seizures in epilepsy patients with FCD type-II. Preictal lengths affect the predictability in a patient-specific manner; therefore, pre-examinations for optimal preictal length will be helpful in seizure prediction.

Living safely with epilepsy: a key learning review.

This review focusses on counselling to reduce the risks of seizures in epilepsy patients. Risk reduction, whilst maximising the independence of persons with epilepsy, is a core element of epilepsy practice. The importance of the issue is reflected by the inclusion of risk assessment and reduction in the recent International League Against Epilepsy Curriculum for epileptology. This article addresses the key elements of epilepsy risk and provides practical guidance for counselling and risk reduction. A review of key publications was performed focusing on: (1) the risk of injury associated with seizures; (2) safety issues related to seizures and lifestyle; (3) SUDEP risk and avoidance; and (4) assessing individual risks. Risk is common in epilepsy and is multifactorial. Clinicians should be aware of the risk factors associated with different epilepsy features, such as seizure type, as well as those related to lifestyle and common indoor and outdoor activities. In addition, transcultural differences should be considered in risk assessment and counselling, e.g. regarding SUDEP or even driving, for which regulations vary across nations. Assessment of individual risk is evolving through a better understanding of risk factors and methodologies which can improve communication and empower patients to help identify and manage their individual risks.