Alpha frequency estimation in patients with epilepsy

Predicting the therapeutic response to valproic acid in childhood absence epilepsy through electroencephalogram analysis using machine learning

Childhood absence epilepsy (CAE) is a common type of idiopathic generalized epilepsy, manifesting as daily multiple absence seizures. Although seizures in most patients can be adequately controlled with first-line antiseizure medication (ASM), approximately 25 % of patients respond poorly to first-line ASM. In addition, an accurate method for predicting first-line medication responsiveness is lacking. We used the quantitative electroencephalogram (QEEG) features of patients with CAE along with machine learning to predict the therapeutic effects of valproic acid in this population. We enrolled 25 patients with CAE from multiple medical centers. Twelve patients who required additional medication for seizure control or who were shifted to another ASM and 13 patients who achieved seizure freedom with valproic acid within 6 months served as the nonresponder and responder groups. Using machine learning, we analyzed the interictal background EEG data without epileptiform discharge before ASM. The following features were analyzed: EEG frequency bands, Hjorth parameters, detrended fluctuation analysis, Higuchi fractal dimension, Lempel-Ziv complexity (LZC), Petrosian fractal dimension, and sample entropy (SE). We applied leave-one-out cross-validation with support vector machine, K-nearest neighbor (KNN), random forest, decision tree, Ada boost, and extreme gradient boosting, and we tested the performance of these models. The responders had significantly higher alpha band power and lower delta band power than the nonresponders. The Hjorth mobility, LZC, and SE values in the temporal, parietal, and occipital lobes were higher in the responders than in the nonresponders. Hjorth complexity was higher in the nonresponders than in the responders in almost all the brain regions, except for the leads FP1 and FP2. Using KNN classification with theta band power in the temporal lobe yielded optimal performance, with sensitivity of 92.31 %, specificity of 76.92 %, accuracy of 84.62 %, and area under the curve of 88.46 %.We used various EEG features along with machine learning to accurately predict whether patients with CAE would respond to valproic acid. Our method could provide valuable assistance for pediatric neurologists in selecting suitable ASM.

Machine-learning for the prediction of one-year seizure recurrence based on routine electroencephalography

Predicting seizure recurrence risk is critical to the diagnosis and management of epilepsy. Routine electroencephalography (EEG) is a cornerstone of the estimation of seizure recurrence risk. However, EEG interpretation relies on the visual identification of interictal epileptiform discharges (IEDs) by neurologists, with limited sensitivity. Automated processing of EEG could increase its diagnostic yield and accessibility. The main objective was to develop a prediction model based on automated EEG processing to predict one-year seizure recurrence in patients undergoing routine EEG. We retrospectively selected a consecutive cohort of 517 patients undergoing routine EEG at our institution (training set) and a separate, temporally shifted cohort of 261 patients (testing set). We developed an automated processing pipeline to extract linear and non-linear features from the EEGs. We trained machine learning algorithms on multichannel EEG segments to predict one-year seizure recurrence. We evaluated the impact of IEDs and clinical confounders on performances and validated the performances on the testing set. The receiver operating characteristic area-under-the-curve for seizure recurrence after EEG in the testing set was 0.63 (95% CI 0.55-0.71). Predictions were still significantly above chance in EEGs with no IEDs. Our findings suggest that there are changes other than IEDs in the EEG signal embodying seizure propensity.

Episodic Memory Dysfunction and Effective Connectivity in Adult Patients With Newly Diagnosed Nonlesional Temporal Lobe Epilepsy

Objective

Epilepsy is associated with both changes in brain connectivity and memory function, usually studied in the chronic patients. The aim of this study was to explore the presence of connectivity alterations measured by EEG in the parietofrontal network in patients with temporal lobe epilepsy (TLE), and to examine episodic memory, at the time point of diagnosis.

Methods

The parietofrontal network of newly diagnosed patients with TLE (N = 21) was assessed through electroencephalography (EEG) effective connectivity and compared with that of matched controls (N = 21). Furthermore, we assessed phenomenological aspects of episodic memory in both groups. Association between effective connectivity and episodic memory were assessed through correlation.

Results

Patients with TLE displayed decreased episodic (p ≤ 0.001, t = −5.18) memory scores compared with controls at the time point of diagnosis. The patients showed a decreased right parietofrontal connectivity (p = 0.03, F = 4.94) compared with controls, and significantly weaker connectivity in their right compared with their left hemisphere (p = 0.008, t = −2.93). There were no significant associations between effective connectivity and episodic memory scores.

Conclusions

We found changes in both memory function and connectivity at the time point of diagnosis, supporting the notion that TLE involves complex memory functions and brain networks beyond the seizure focus to strongly interconnected brain regions, already early in the disease course. Whether the observed connectivity changes can be interpreted as functionally important to the alterations in memory function, it remains speculative.

How Alpha Rhythm Spatiotemporally Acts Upon the Thalamus-Default Mode Circuit in Idiopathic Generalized Epilepsy

GOAL

Idiopathic generalized epilepsy (IGE) represents generalized spike-wave discharges (GSWD) and distributed changes in thalamocortical circuit. The purpose of this study is to investigate how the ongoing alpha oscillation acts upon the local temporal dynamics and spatial hyperconnectivity in epilepsy.

METHODS

We evaluated the spatiotemporal regulation of alpha oscillations in epileptic state based on simultaneous EEG-fMRI recordings in 45 IGE patients. The alpha-BOLD temporal consistency, as well as the effect of alpha power windows on dynamic functional connectivity strength (dFCS) was analyzed. Then, stable synchronization networks during GSWD were constructed, and the spatial covariation with alpha-based network integration was investigated.

RESULTS

Increased temporal covariation was demonstrated between alpha power and BOLD fluctuations in thalamus and distributed cortical regions in IGE. High alpha power had inhibition effect on dFCS in healthy controls, while in epilepsy, high alpha windows arose along with the enhancement of dFCS in thalamus, caudate and some default mode network (DMN) regions. Moreover, synchronization networks in GSWD-before, GSWD-onset and GSWD-after stages were constructed, and the connectivity strength in prominent hub nodes (precuneus, thalamus) was associated with the spatially disturbed alpha-based network integration.

CONCLUSION

The results indicated spatiotemporal regulation of alpha in epilepsy by means of the increased power and decreased coherence communication. It provided links between alpha rhythm and the altered temporal dynamics, as well as the hyperconnectivity in thalamus-default mode circuit.

SIGNIFICANCE

The combination between neural oscillations and epileptic representations may be of clinical importance in terms of seizure prediction and non-invasive interventions.

Photosensitive epilepsy is associated with reduced inhibition of alpha rhythm generating networks

See Hamandi (doi:10.1093/awx049) for a scientific commentary on this article.Photosensitivity is a condition in which lights induce epileptiform activities. This abnormal electroencephalographic response has been associated with hyperexcitability of the visuo-motor system. Here, we evaluate if intrinsic dysfunction of this network is present in brain activity at rest, independently of any stimulus and of any paroxysmal electroencephalographic activity. To address this issue, we investigated the haemodynamic correlates of the spontaneous alpha rhythm, which is considered the hallmark of the brain resting state, in photosensitive patients and in people without photosensitivity. Second, we evaluated the whole-brain functional connectivity of the visual thalamic nuclei in the various populations of subjects under investigation. Forty-four patients with epilepsy and 16 healthy control subjects underwent an electroencephalography-correlated functional magnetic resonance imaging study, during an eyes-closed condition. The following patient groups were included: (i) genetic generalized epilepsy with photosensitivity, 16 subjects (mean age 25 ± 10 years); (ii) genetic generalized epilepsy without photosensitivity, 13 patients (mean age 25 ± 11 years); (iii) focal epilepsy, 15 patients (mean age 25 ± 9 years). For each subject, the posterior alpha power variations were convolved with the standard haemodynamic response function and used as a regressor. Within- and between-groups second level analyses were performed. Whole brain functional connectivity was evaluated for two thalamic regions of interest, based on the haemodynamic findings, which included the posterior thalamus (pulvinar) and the medio-dorsal thalamic nuclei. Genetic generalized epilepsy with photosensitivity demonstrated significantly greater mean alpha-power with respect to controls and other epilepsy groups. In photosensitive epilepsy, alpha-related blood oxygen level-dependent signal changes demonstrated lower decreases relative to all other groups in the occipital, sensory-motor, anterior cingulate and supplementary motor cortices. Coherently, the same brain regions demonstrated abnormal connectivity with the visual thalamus only in epilepsy patients with photosensitivity. As predicted, our findings indicate that the cortical-subcortical network generating the alpha oscillation at rest is different in people with epilepsy and visual sensitivity. This difference consists of a decreased alpha-related inhibition of the visual cortex and sensory-motor networks at rest. These findings represent the substrate of the clinical manifestations (i.e. myoclonus) of the photoparoxysmal response. Moreover, our results provide the first evidence of the existence of a functional link between the circuits that trigger the visual sensitivity phenomenon and those that generate the posterior alpha rhythm.

Interval analysis of interictal EEG: pathology of the alpha rhythm in focal epilepsy

The contemporary use of interictal scalp electroencephalography (EEG) in the context of focal epilepsy workup relies on the visual identification of interictal epileptiform discharges. The high-specificity performance of this marker comes, however, at a cost of only moderate sensitivity. Zero-crossing interval analysis is an alternative to Fourier analysis for the assessment of the rhythmic component of EEG signals. We applied this method to standard EEG recordings of 78 patients divided into 4 subgroups: temporal lobe epilepsy (TLE), frontal lobe epilepsy (FLE), psychogenic nonepileptic seizures (PNES) and nonepileptic patients with headache. Interval-analysis based markers were capable of effectively discriminating patients with epilepsy from those in control subgroups (AUC~0.8) with diagnostic sensitivity potentially exceeding that of visual analysis. The identified putative epilepsy-specific markers were sensitive to the properties of the alpha rhythm and displayed weak or non-significant dependences on the number of antiepileptic drugs (AEDs) taken by the patients. Significant AED-related effects were concentrated in the theta interval range and an associated marker allowed for identification of patients on AED polytherapy (AUC~0.9). Interval analysis may thus, in perspective, increase the diagnostic yield of interictal scalp EEG. Our findings point to the possible existence of alpha rhythm abnormalities in patients with epilepsy.