Analysis of background EEG activity in patients with juvenile myoclonic epilepsy

Diagnosing Epilepsy with Normal Interictal EEG Using Dynamic Network Models

OBJECTIVE

Whereas a scalp electroencephalogram (EEG) is important for diagnosing epilepsy, a single routine EEG is limited in its diagnostic value. Only a small percentage of routine EEGs show interictal epileptiform discharges (IEDs) and overall misdiagnosis rates of epilepsy are 20% to 30%. We aim to demonstrate how network properties in EEG recordings can be used to improve the speed and accuracy differentiating epilepsy from mimics, such as functional seizures - even in the absence of IEDs.

METHODS

In this multicenter study, we analyzed routine scalp EEGs from 218 patients with suspected epilepsy and normal initial EEGs. The patients' diagnoses were later confirmed based on an epilepsy monitoring unit (EMU) admission. About 46% ultimately being diagnosed with epilepsy and 54% with non-epileptic conditions. A logistic regression model was trained using spectral and network-derived EEG features to differentiate between epilepsy and non-epilepsy. Of the 218 patients, 90% were used for training and 10% were held out for testing. Within the training set, 10-fold cross validation was performed. The resulting tool was named "EpiScalp."

RESULTS

EpiScalp achieved an area under the curve (AUC) of 0.940, an accuracy of 0.904, a sensitivity of 0.835, and a specificity of 0.963 in classifying patients as having epilepsy or not.

INTERPRETATION

EpiScalp provides an accurate diagnostic aid from a single initial EEG recording, even in more challenging epilepsy cases with normal initial EEGs. This may represent a paradigm shift in epilepsy diagnosis by deriving an objective measure of epilepsy likelihood from previously uninformative EEGs. ANN NEUROL 2025;97:907-918.

A diagnosis and prediction algorithm for juvenile myoclonic epilepsy based on clinical and quantitative EEG features

OBJECTIVE

To develop an objective ensemble machine learning model combining clinical features and quantitative EEG metrics (phase locking value [PLV] and multiscale sample entropy [MSE]) to support accurate diagnosis of juvenile myoclonic epilepsy (JME).

METHODS

A total of 75 JME patients, 51 frontal lobe epilepsy (FLE) patients, and 30 normal controls were included. Eight clinical features, along with 684 PLV and 152 MSE features derived from EEG data, were extracted. Four models were constructed using ensemble XGBoost and GBDT classifiers, with performance evaluated through accuracy, precision, recall, F1-score, and AUC. The performance of these models was assessed using a five-fold cross-validation method. The Fisher Score method ranked the most influential features in the best-performing model.

RESULTS

The combined model (clinical, PLV, and MSE features) achieved an accuracy of 85.26 % and an AUC of 0.97. Key features included specific PLV metrics and family history of epilepsy. Notably, the PLV of Fp2-O1 in the δ band (δ-PLV_Fp2-O1) significantly differed among JME, FLE, and normal controls.

CONCLUSION

The ensemble model effectively distinguished JME, and highlighted δ-PLV_Fp2-O1 as a potential distinguishing feature, paving the way for more objective diagnostic approaches.

The predicative value of early quantitative electroencephalograph in epilepsy after severe traumatic brain injury in children

Objective

To explore whether early quantitative electroencephalograph (EEG) can predict the development of epilepsy in pediatric patients with severe traumatic brain injury (TBI).

Methods

A total of 78 children with severe TBI who were admitted to our hospital were divided into post-traumatic epilepsy (PTE) and non-PTE groups according to whether or not they developed PTE. EEGs of frontal, central and parietal lobes were recorded at the time of their admission. The power values of each frequency band, odds ratio and peak envelope power values of each brain region were statistically analyzed. In addition, the patients were followed up for two years, and the occurrence of PTE was documented.

Results

During the follow-up period, PTE occurred in 8 patients. Analysis of EEG signals across different brain regions (frontal, central, and parietal lobes) revealed significant differences between the PTE and non-PTE groups. Patients with PTE exhibited significantly higher δ and θ power values (P < 0.01), lower α/θ ratios (P < 0.01), and elevated θ/β, (δ + θ)/(α + β), and peak envelope power (P < 0.01) compared to those in the non-PTE group.

Conclusion

In children with severe TBI, the parameter characterization of early quantitative EEG has potential application in predicting PTE.

Connectivity Disturbances in Self-Limited Epilepsy with Centrotemporal Spikes: A Partial Directed Coherence Analysis of Electroencephalogram

Although the remission of self-limited epilepsy with centrotemporal spikes (SeLECTS) usually occurs by adolescence, deficits in cognition and behavior are not uncommon. Several functional magnetic resonance imaging (fMRI) studies have revealed connectivity disturbances in patients with SeLECTS associated with cognitive impairment. However, the disadvantages of fMRI are expensive, time-consuming, and motion sensitive. In the current study, we used a partial directed coherence (PDC) method to analyze electroencephalogram (EEG) for exploring brain connectivity in patients with SeLECTS. This study enrolled 38 participants (19 patients with SeLECTS and 19 healthy controls) for PDC analysis. Our results demonstrated that the controls had significantly higher PDC inflow connectivity in the F7, T3, FP1, and F8 channels than patients with SeLECTS. By contrast, the patients with SeLECTS demonstrated significantly higher PDC inflow connectivity than did the controls in the T5, Pz, and P4 channels. We also compared the PDC connectivity in different Brodmann areas between the patients with SeLECTS and the controls. The results revealed that the inflow connectivity in the BA9_46_L area was significantly higher in the controls than in the patients with SeLECTS, whereas the inflow connectivity in the MIF_L area 4 was significantly higher in the patients with SeLECTS than in the controls. Our proposed approach of combining EEG with PDC provides a convenient and useful tool for investigating functional connectivity in patients with SeLECTS. This approach is time-saving and inexpensive compared with fMRI, but it achieves similar results to fMRI.

Neurophysiology of Juvenile and Progressive Myoclonic Epilepsy

SUMMARY

Myoclonus can be epileptic or nonepileptic. Epileptic myoclonus has been defined in clinical, neurophysiological, and neuroanatomical terms. Juvenile myoclonic epilepsy (JME) is typically considered to be an adolescent-onset idiopathic generalized epilepsy with a combination of myoclonic, generalized tonic-clonic, and absence seizures and normal cognitive status that responds well to anti-seizure medications but requires lifelong treatment. EEG shows generalized epileptiform discharges and photosensitivity. Recent observations indicate that the clinical picture of JME is heterogeneous and a number of neuropsychological and imaging studies have shown structural and functional abnormalities in the frontal lobes and thalamus. Advances in neurophysiology and imaging suggest that JME may not be a truly generalized epilepsy, in that restricted cortical and subcortical networks appear to be involved rather than the entire brain. Some patients with JME may be refractory to anti-seizure medications and attempts have been made to identify neurophysiological biomarkers predicting resistance. Progressive myoclonic epilepsy is a syndrome with multiple specific causes. It is distinct from JME because of the occurrence of progressive neurologic dysfunction in addition to myoclonus and generalized tonic-clonic seizures but may sometimes be difficult to distinguish from JME or misdiagnosed as drug-resistant JME. This article provides an overview of progressive myoclonic epilepsy and focuses on the clinical and neurophysiological findings in the two most commonly recognized forms of progressive myoclonic epilepsy-Unverricht-Lundborg disease (EPM1) and Lafora disease (EPM2). A variety of neurophysiological tests can be used to distinguish between JME and progressive myoclonic epilepsy and between EPM1 and EPM2.

Seizure classification with selected frequency bands and EEG montages: a Natural Language Processing approach

Individualized treatment is crucial for epileptic patients with different types of seizures. The differences among patients impact the drug choice as well as the surgery procedure. With the advance in machine learning, automatic seizure detection can ease the manual time-consuming and labor-intensive procedure for diagnose seizure in the clinical setting. In this paper, we present an electroencephalography (EEG) frequency bands (sub-bands) and montages selection (sub-zones) method for classifier training that exploits Natural Language Processing from individual patients' clinical report. The proposed approach is targeting for individualized treatment. We integrated the prior knowledge from patient's reports into the classifier-building process, mimicking the authentic thinking process of experienced neurologist's when diagnosing seizure using EEG. The keywords from clinical documents are mapped to the EEG data in terms of frequency bands and scalp EEG electrodes. The data of experiments are from the Temple University Hospital EEG seizure corpus, and the dataset is divided based on each group of patients with same seizure type and same recording electrode references. The classifier includes Random Forest, Support Vector Machine and Multi-Layer Perceptron. The classification performance indicates that competitive results can be achieve with a small portion of EEG the data. Using the sub-zones selection for Generalized Seizures (GNSZ) on all three electrodes, data are reduced by nearly 50% while the performance metrics remain at the same level with the whole frequency and zones. Moreover, when selecting by sub-zones and sub-bands together for GNSZ with Linked Ears reference, the data range reduced to 0.3% of whole range, and the performance deviates less than 3% from the results with whole range of data. Results show that using proposed approach may lead to more efficient implementations of the seizure classifier to be executed on power-efficient devices for long lasting real-time seizures detection.

Brivaracetam Modulates Short-Term Synaptic Activity and Low-Frequency Spontaneous Brain Activity by Delaying Synaptic Vesicle Recycling in Two Distinct Rodent Models of Epileptic Seizures

Brivaracetam (BRV) is an anti-seizure drug for the treatment of focal and generalized epileptic seizures shown to augment short-term synaptic fatigue by slowing down synaptic vesicle recycling rates in control animals. In this study, we sought to investigate whether altered short-term synaptic activities could be a pathological hallmark during the interictal periods of epileptic seizures in two well-established rodent models, as well as to reveal BRV's therapeutic roles in altered short-term synaptic activities and low-frequency band spontaneous brain hyperactivity in these models. In our study, the electrophysiological field excitatory post-synaptic potential (fEPSP) recordings were performed in rat hippocampal brain slices from the CA1 region by stimulation of the Schaffer collateral/commissural pathway with or without BRV (30 μM for 3 h) in control or epileptic seizure (induced by pilocarpine (PILO) or high potassium (h-K⁺)) models. Short-term synaptic activities were induced by 5, 10, 20, and 40-Hz stimulation sequences. The effects of BRV on pre-synaptic vesicle mobilization were visually assessed by staining the synaptic vesicles with FM1-43 dye followed by imaging with a two-photon microscope. In the fEPSP measurements, short-term synaptic fatigue was found in the control group, while short-term synaptic potentiation (STP) was detected in both PILO and h-K⁺ models. STP was decreased after the slices were treated with BRV (30 μM) for 3 h. BRV also exhibited its therapeutic benefits by decreasing abnormal peak power (frequency range of 8-13 Hz, 31% of variation for PILO model, 25% of variation for h-K⁺ model) and trough power (frequency range of 1-4 Hz, 66% of variation for PILO model, 49% of variation for h-K⁺ model), and FM1-43 stained synaptic vesicle mobility (64% of the variation for PILO model, 45% of the variation for h-K⁺ model) in these epileptic seizure models. To the best of our knowledge, this was the first report that BRV decreased the STP and abnormal low-frequency brain activities during the interictal phase of epileptic seizures by slowing down the mobilization of synaptic vesicles in two rodent models. These mechanistic findings would greatly advance our understanding of BRV's pharmacological role in pathomechanisms of epileptic seizures and its treatment strategy optimization to avoid or minimize BRV-induced possible adverse side reactions.

Comparative analysis of background EEG activity in juvenile myoclonic epilepsy during valproic acid treatment: a standardized, low-resolution, brain electromagnetic tomography (sLORETA) study

Background

By definition, the background EEG is normal in juvenile myoclonic epilepsy (JME) patients and not accompanied by other developmental and cognitive problems. However, some recent studies using quantitative EEG (qEEG) reported abnormal changes in the background activity. QEEG investigation in patients undergoing anticonvulsant treatment might be a useful approach to explore the electrophysiology and anticonvulsant effects in JME.

Methods

We investigated background EEG activity changes in patients undergoing valproic acid (VPA) treatment using qEEG analysis in a distributed source model. In 17 children with JME, non-parametric statistical analysis using standardized low-resolution brain electromagnetic tomography was performed to compare the current density distribution of four frequency bands (delta, theta, alpha, and beta) between untreated and treated conditions.

Results

VPA reduced background EEG activity in the low-frequency (delta-theta) bands across the frontal, parieto-occipital, and limbic lobes (threshold log-F-ratio = ±1.414, p < 0.05; threshold log-F-ratio= ±1.465, p < 0.01). In the delta band, comparative analysis revealed significant current density differences in the occipital, parietal, and limbic lobes. In the theta band, the analysis revealed significant differences in the frontal, occipital, and limbic lobes. The maximal difference was found in the delta band in the cuneus of the left occipital lobe (log-F-ratio = −1.840) and the theta band in the medial frontal gyrus of the left frontal lobe (log-F-ratio = −1.610).

Conclusions

This study demonstrated the anticonvulsant effects on the neural networks involved in JME. In addition, these findings suggested the focal features and the possibility of functional deficits in patients with JME.

Analysis of Clinical Characteristics, Background, and Paroxysmal Activity in EEG of Patients with Juvenile Myoclonic Epilepsy

Juvenile myoclonic epilepsy (JME) appears in adolescence with myoclonic, absence, and generalized tonic clonic (GTC) seizures with paroxysmal activity of polyspike and slow wave (PSW), or spike and wave (SW) complexes in EEG. Our aim was to analyze the clinical characteristics, background EEG activity, and paroxysmal events in 41 patients with JME. Background EEG activity was analyzed with visual, quantitative (QEEG), and neurometric parameters. Our JME patients started with absence seizures at 11.4 ± 1.5 years old, myoclonic seizures at 13.6 ± 2.5 years, and GTC seizures at 15.1 ± 0.8 years. The seizures presented in awakening at 7:39 h with sleep deprivation, alcoholic beverage intake, and stress as the most frequent precipitant factors. Paroxysmal activity was of PSW and fast SW complexes with 40.5 ± 62.6 events/hour and a duration of 1.7 s. Right asymmetric paroxysmal activity was present in 68.3% of patients. Background EEG activity was abnormal in 31.7% of patients with visual analysis. With QEEG beta AP (absolute power) increase and AP delta decrease were the most frequent abnormalities found. Spectral analysis showed that 48.7% of patients had normal results, and 26.83% and 24.4% had higher and lower frequencies than 10.156 Hz, respectively. We concluded that, with visual analysis, background EEG activity was abnormal in a few patients and the abnormalities increased when QEEG was used.

Spectral power of interictal EEG in the diagnosis and prognosis of idiopathic generalized epilepsies

INTRODUCTION

Idiopathic generalized epilepsies (IGE) are characterized by generalized interictal epileptiform discharges (IEDs) on a normal background electroencephalography (EEG). However, the yield of IEDs can be low. Approximately 20% of patients with IGE fail to achieve seizure control with antiepileptic drug (AED) treatment. Currently, there are no reliable prognostic markers for early identification of drug-resistant epilepsy (DRE). We examined spectral power of the interictal EEG in patients with IGE and healthy controls, to identify potential diagnostic and prognostic biomarkers of IGE.

METHODS

A 64-channel EEG was recorded under standard conditions in patients with well-controlled IGE (WC-IGE, n = 19), drug-resistant IGE (DR-IGE, n = 18), and age-matched controls (n = 20). After preprocessing, fast Fourier transform was performed to obtain 1D frequency spectra for each EEG channel. The 1D spectra (averaged over channels) and 2D topographic maps (averaged over canonical frequency bands) were computed for each participant. Power spectra in the 3 cohorts were compared using one-way analysis of variance (ANOVA), and power spectra images were compared using T-contrast tests. A post hoc analysis compared peak alpha power between the groups.

RESULTS

Compared with controls, participants with IGE had higher interictal EEG spectral power in the delta band in the midline central region, in the theta band in the midline, in the beta band over the left hemisphere, and in the gamma band over right hemisphere and left central regions. There were no differences in spectral power between cohorts with WC-IGE and DR-IGE. Peak alpha power was lower in WC-IGE and DR-IGE than controls.

CONCLUSIONS

Electroencephalography spectral power analysis could form part of a clinically useful diagnostic biomarker for IGE; however, it did not correlate with response to AED in this study.

Determination of Antiepileptic Drugs Withdrawal Through EEG Hjorth Parameter Analysis

The decision to continue or to stop antiepileptic drug (AED) treatment in patients with prolonged seizure remission is a critical issue. Previous studies have used certain risk factors or electroencephalogram (EEG) findings to predict seizure recurrence after the withdrawal of AEDs. However, validated biomarkers to guide the withdrawal of AEDs are lacking. In this study, we used quantitative EEG analysis to establish a method for predicting seizure recurrence after the withdrawal of AEDs. A total of 34 patients with epilepsy were divided into two groups, 17 patients in the recurrence group and the other 17 patients in the nonrecurrence group. All patients were seizure free for at least two years. Before AED withdrawal, an EEG was performed for each patient that showed no epileptiform discharges. These EEG recordings were classified using Hjorth parameter-based EEG features. We found that the Hjorth complexity values were higher in patients in the recurrence group than in the nonrecurrence group. The extreme gradient boosting classification method achieved the highest performance in terms of accuracy, area under the curve, sensitivity, and specificity (84.76%, 88.77%, 89.67%, and 80.47%, respectively). Our proposed method is a promising tool to help physicians determine AED withdrawal for seizure-free patients.

Alternative Diagnosis of Epilepsy in Children Without Epileptiform Discharges Using Deep Convolutional Neural Networks

Numerous nonepileptic paroxysmal events, such as syncope and psychogenic nonepileptic seizures, may imitate seizures and impede diagnosis. Misdiagnosis can lead to mistreatment, affecting patients’ lives considerably. Electroencephalography is commonly used for diagnosing epilepsy. Although on electroencephalograms (EEGs), epileptiform discharges (ED) specifically indicate epilepsy, only approximately 50% of patients with epilepsy have ED in their first EEG. In this study, we developed a deep convolutional neural network (ConvNet)-based classifier to distinguish EEG between patients with epilepsy without ED and controls. Overall, 25 patients with epilepsy without ED in their EEGs and 25 age-matched patients with Tourette syndrome or syncope were enrolled. Their EEGs were classified using the deep ConvNet. When the EEG data without overlapping were used, the accuracy, sensitivity, and specificity were 65.00%, 48.00%, and 82.00%, respectively. The performance measures improved when the input EEG data were augmented through overlapping. With 95% EEG data overlapping, the accuracy, sensitivity, and specificity increased to 80.00%, 70.00%, and 90.00%, respectively. The proposed method could be regarded as a pilot study to demonstrate a proof of concept of a potential diagnostic value of deep ConvNet in patients with epilepsy without ED. Further studies are needed to assist neurologists in distinguishing nonepileptic paroxysmal events from epilepsy.

Slower alpha rhythm associates with poorer seizure control in epilepsy

Objective

Slowing and frontal spread of the alpha rhythm have been reported in multiple epilepsy syndromes. We investigated whether these phenomena are associated with seizure control.

Methods

We prospectively acquired resting-state electroencephalogram (EEG) in 63 patients with focal and idiopathic generalized epilepsy (FE and IGE) and 39 age- and gender-matched healthy subjects (HS). Patients were divided into good and poor (≥4 seizures/12 months) seizure control groups based on self-reports and clinical records. We computed spectral power from 20-sec EEG segments during eyes-closed wakefulness, free of interictal abnormalities, and quantified power in high- and low-alpha bands. Analysis of covariance and post hoc t-tests were used to assess group differences in alpha-power shift across all EEG channels. Permutation-based statistics were used to assess the topography of this shift across the whole scalp.

Results

Compared to HS, patients showed a statistically significant shift of spectral power from high- to low-alpha frequencies (effect size g = 0.78 [95% confidence interval 0.43, 1.20]). This alpha-power shift was driven by patients with poor seizure control in both FE and IGE (g = 1.14, [0.65, 1.74]), and occurred over midline frontal and bilateral occipital regions. IGE exhibited less alpha power shift compared to FE over bilateral frontal regions (g = -1.16 [-0.68, -1.74]). There was no interaction between syndrome and seizure control. Effects were independent of antiepileptic drug load, time of day, or subgroup definitions.

Interpretation

Alpha slowing and anteriorization are a robust finding in patients with epilepsy and might represent a generic indicator of seizure liability.

Neuronal levels and sequence of tau modulate the power of brain rhythms

Neural network dysfunction may contribute to functional decline and disease progression in neurodegenerative disorders. Diverse lines of evidence suggest that neuronal accumulation of tau promotes network dysfunction and cognitive decline. The A152T-variant of human tau (hTau-A152T) increases the risk of Alzheimer's disease (AD) and several other tauopathies. When overexpressed in neurons of transgenic mice, it causes age-dependent neuronal loss and cognitive decline, as well as non-convulsive epileptic activity, which is also seen in patients with AD. Using intracranial EEG recordings with electrodes implanted over the parietal cortex, we demonstrate that hTau-A152T increases the power of brain oscillations in the 0.5-6 Hz range more than wildtype human tau in transgenic lines with comparable levels of human tau protein in brain, and that genetic ablation of endogenous tau in Mapt^-/- mice decreases the power of these oscillations as compared to wildtype controls. Suppression of hTau-A152T production in doxycycline-regulatable transgenic mice reversed their abnormal network activity. Treatment of hTau-A152T mice with the antiepileptic drug levetiracetam also rapidly and persistently reversed their brain dysrhythmia and network hypersynchrony. These findings suggest that both the level and the sequence of tau modulate the power of specific brain oscillations. The potential of EEG spectral changes as a biomarker deserves to be explored in clinical trials of tau-lowering therapeutics. Our results also suggest that levetiracetam treatment is able to counteract tau-dependent neural network dysfunction. Tau reduction and levetiracetam treatment may be of benefit in AD and other conditions associated with brain dysrhythmias and network hypersynchrony.

Quantitative EEG findings and response to treatment with antiepileptic medications in children with epilepsy

BACKGROUND

Epilepsy is a common chronic disorder in pediatric neurology. Nowadays, a variety of antiepileptic drugs (AEDs) are available. A scientific method designed to evaluate the effectiveness of AEDs in the early stage of treatment has not been reported.

PURPOSE

In this study, we try to use quantitative EEG (QEEG) analysis as a biomarker to evaluate therapeutic effectiveness.

METHODS

20 epileptic children were enrolled in this study. Participants were classified as effective if they achieved a reduction in seizure frequency over 50%. Ineffective was defined as a reduction in seizure frequency less than 50%. Eleven participants were placed in the effective group, the remaining 9 participants were placed in the ineffective group. EEG segments before and after 1-3months of antiepileptic drugs start/change were analyzed and compared by QEEG analysis. The follow-up EEG segments after the 2nd examinations were used to test the accuracy of the analytic results.

RESULTS

Six crucial EEG feature descriptors were selected for classifying the effective and ineffective groups. Significantly increased RelPowAlpha_avg_AVG, RelPowAlpha_snr_AVG, HjorthM_avg_AVG, and DecorrTime_snr_AVG values were found in the effective group as compared to the ineffective group. On the contrary, there were significantly decreases in DecorrTime_std_AVG, and Wavelet_db4_EnergyBand_5_avg_AVG values in the effective group as compared to the ineffective group. The analyses yielded a precision rate of 100%. When the follow-up EEG segments were used to test the analytic results, the accuracy was 83.3%.

CONCLUSION

The developed method is a useful tool in analyzing the effectiveness of antiepileptic drugs. This method may assist pediatric neurologists in evaluating the efficacy of AEDs and making antiepileptic drug adjustments when managing epileptic patients in the early stage.

Early prediction of medication refractoriness in children with idiopathic epilepsy based on scalp EEG analysis

Refractory epilepsy often has deleterious effects on an individual's health and quality of life. Early identification of patients whose seizures are refractory to antiepileptic drugs is important in considering the use of alternative treatments. Although idiopathic epilepsy is regarded as having a significantly lower risk factor of developing refractory epilepsy, still a subset of patients with idiopathic epilepsy might be refractory to medical treatment. In this study, we developed an effective method to predict the refractoriness of idiopathic epilepsy. Sixteen EEG segments from 12 well-controlled patients and 14 EEG segments from 11 refractory patients were analyzed at the time of first EEG recordings before antiepileptic drug treatment. Ten crucial EEG feature descriptors were selected for classification. Three of 10 were related to decorrelation time, and four of 10 were related to relative power of delta/gamma. There were significantly higher values in these seven feature descriptors in the well-controlled group as compared to the refractory group. On the contrary, the remaining three feature descriptors related to spectral edge frequency, kurtosis, and energy of wavelet coefficients demonstrated significantly lower values in the well-controlled group as compared to the refractory group. The analyses yielded a weighted precision rate of 94.2%, and a 93.3% recall rate. Therefore, the developed method is a useful tool in identifying the possibility of developing refractory epilepsy in patients with idiopathic epilepsy.

Neurophysiology of juvenile myoclonic epilepsy

Juvenile myclonic epilepsy (JME) can be firmly diagnosed by a careful interview of the patient focusing on the seizures and by the EEG with the help, if necessary, of long-term video-EEG monitoring using sleep and/or sleep deprivation. Background activity is normal. The interictal EEG shows diffuse or generalized spike-wave (SW) and polyspike-wave (PSW) discharges. In some patients, non-specific changes or misleading features such as focal changes are found. Changes are mostly seen at sleep onset and at awakening. Provoked awakenings are more likely to activate interictal paroxysmal abnormalities than spontaneous awakenings. The presence of a photoparoxysmal response with or without myoclonic jerks (MJ) is common (30% of the cases). Myoclonic jerks are associated with a discharge of fast, irregular, generalized PSWs that predominate anteriorly. Myoclonic jerks appear to be associated with rhythmic EEG (spike) potentials at around 20Hz. These frequencies are in the range of movement-related fast sensorimotor cortex physiological rhythms. The application of jerk-locked averaging technique has provided findings consistent with a cortical origin of MJ. Paired TMS (transcranial magnetic stimulation) studies showed a defective intracortical inhibition, due to impaired GABA-A mediated mechanisms. In this review, we present the EEG characteristics of JME with particular emphasis on the pathophysiology of MJ and on the role of sleep deprivation on interictal and ictal changes.

Balancing Clinical and Pathologic Relevence in the Machine Learning Diagnosis of Epilepsy

The application of machine learning to epilepsy can be used both to develop clinically useful computer-aided diagnostic tools, and to reveal pathologically relevant insights into the disease. Such studies most frequently use neurologically normal patients as the control group to maximize the pathologic insight yielded from the model. This practice yields potentially inflated accuracy because the groups are quite dissimilar. A few manuscripts, however, opt to mimic the clinical comparison of epilepsy to non-epileptic seizures, an approach we believe to be more clinically realistic. In this manuscript, we describe the relative merits of each control group. We demonstrate that in our clinical quality FDG-PET database the performance achieved was similar using each control group. Based on these results, we find that the choice of control group likely does not hinder the reported performance. We argue that clinically applicable computer-aided diagnostic tools for epilepsy must directly address the clinical challenge of distinguishing patients with epilepsy from those with non-epileptic seizures.