Deep Learning of Simultaneous Intracranial and Scalp EEG for Prediction, Detection, and Lateralization of Mesial Temporal Lobe Seizures

In people with drug resistant epilepsy (DRE), seizures are unpredictable, often occurring with little or no warning. The unpredictability causes anxiety and much of the morbidity and mortality of seizures. In this work, 102 seizures of mesial temporal lobe onset were analyzed from 19 patients with DRE who had simultaneous intracranial EEG (iEEG) and scalp EEG as part of their surgical evaluation. The first aim of this paper was to develop machine learning models for seizure prediction and detection (i) using iEEG only, (ii) scalp EEG only and (iii) jointly analyzing both iEEG and scalp EEG. The second goal was to test if machine learning could detect a seizure on scalp EEG when that seizure was not detectable by the human eye (surface negative) but was seen in iEEG. The final question was to determine if the deep learning algorithm could correctly lateralize the seizure onset. The seizure detection and prediction problems were addressed jointly by training Deep Neural Networks (DNN) on 4 classes: non-seizure, pre-seizure, left mesial temporal onset seizure and right mesial temporal onset seizure. To address these aims, the classification accuracy was tested using two deep neural networks (DNN) against 3 different types of similarity graphs which used different time series of EEG data. The convolutional neural network (CNN) with the Waxman similarity graph yielded the highest accuracy across all EEG data (iEEG, scalp EEG and combined). Specifically, 1 second epochs of EEG were correctly assigned to their seizure, pre-seizure, or non-seizure category over 98% of the time. Importantly, the pre-seizure state was classified correctly in the vast majority of epochs (>97%). Detection from scalp EEG data alone of surface negative seizures and the seizures with the delayed scalp onset (the surface negative portion) was over 97%. In addition, the model accurately lateralized all of the seizures from scalp data, including the surface negative seizures. This work suggests that highly accurate seizure prediction and detection is feasible using either intracranial or scalp EEG data. Furthermore, surface negative seizures can be accurately predicted, detected and lateralized with machine learning even when they are not visible to the human eye.

CEREBRAL VENOUS THROMBOSIS SECONDARY TO SARS-COV-2 INFECTION

Cerebral venous thrombosis (CVT) is a relatively rare form of neurovascular emergency, and may present as headache, seizure, or focal neurological deficit. It typically has a higher occurrence in younger women. Recently, there are increasingly cases of CVTreported in association with COVID-19, which fall outside the typical demographics, suggesting a hyper-coagulable state attributable to COVID-19. Here, we present a case of CVTin a young gentleman with concomitant COVID-19, who presented with first-onset seizure.

Hippocampal magnetic resonance imaging in focal onset seizure with impaired awareness—descriptive study from tertiary care centre in southern part of India

Background Temporal lobe epilepsy is the most common type of focal onset seizure. Focal onset seizure with impaired awareness, previously known as complex partial seizure (CPS), account for 18–40% of all seizure types. Hippocampal sclerosis (HS) is the most common cause of temporal lobe epilepsy, which produces focal onset seizure with impaired awareness. It may be detected in MRI visually, but bilateral abnormalities are better identified using volumetric analysis. We aimed to compare hippocampal volume in patients with focal onset seizure with impaired awareness visually and quantitatively. Methodology This cross-sectional study includes clinically diagnosed cases of 56 focal onset seizure with impaired awareness undergoing MRI at a tertiary teaching hospital in the southern part of India for a duration of 18 months from February 2018 to August 2019. Results Out of 53 patients studied using 1.5 T MRI brain with seizure protocols, hippocampal atrophy was identified visually in 13 (24.5%) on the right side, 9 (16.98%) on the left side, and in 6 (11.32%) bilaterally. However, with volumetry, hippocampal atrophy (not taking T2 signal change) was detected in 15 (28.30%) on the right side, 10 (18.86%) on the left side, and in 7 (13.20%) bilaterally. Hippocampal volumes between ipsilateral and contralateral seizure focus were found to have no significant difference (p-0.84). Conclusions Though visual analysis is efficient in the diagnosis of pathology, MR volumetry may be used as an expert eye in cases of subtle volume loss.

Validation of the New International League Against Epilepsy (ILAE) 2017 Classification for Determining Seizure Type in Indian Patients

Introduction Epilepsy is a common condition in neurology comprising several electroclinical syndromes and seizure disorders of varying known and unknown etiologies that require variable diagnostic workup, treatment, and have obviously different prognoses. Therefore, for appropriate patient management, the best possible classification system for epilepsy is required. The International League Against Epilepsy (ILAE) is continuously working on this with the latest classification provided in 2017. There is little knowledge about seizure type based on newer classification systems in Indian patients. Aims and Objective To test the applicability of the newer ILAE 2017 classification of epilepsy in determining seizure type in Indian patients, with respect to right patient management, the best classification system for epilepsy is necessary. Materials and Methods Prospective data of 310 consecutive patients with seizures presenting in neurology department was collected from December 2017 to June 2018 and analyzed according to the newer systems of classification of seizures proposed by ILAE in 2017. Results All 310 patients in age ranging from one year to 72 years with seizures could be classified according to the ILAE 2017 classification system. Focal onset seizure was noted in 66 patients (21.3%), while 244 patients (78.7%) had generalized onset based on clinical onset of seizure. Awareness was impaired in 262 (84.5%) patients. Motor onset seizure was observed in 278 patients (89.6%), while nonmotor seizure included absence, sensory, cognitive, and autonomic seizures. Conclusion The present study showed that all patients could be classified using ILAE 2017 classification system. Majority of seizure were generalized onset, predominantly motor type of seizure with impaired awareness using clinical description of classifying seizure, while focal onset seizure was the majority type of seizure when ancillary information was considered.

Seizures and Vaping—A Report of Two Cases

ABSTRACT The purpose of this qualitative study is to describe the clinical course of two patients who presented with new-onset seizures within hours of vaping and to survey neurologists’ screening for vaping in such patients. A 30-subject single-institution survey found that 19 out of 30 neurology providers have not been subjectively qualifying vaping as a potential seizure-provoking factor since the 2019 emergence of literature on this topic. Inquiring about vaping during a new-onset seizure assessment could lead to earlier recognition of a seizure-provoking factor. Further investigations into the epileptogenicity of vaping are needed and the utility of AntiEpileptic Drug (AED) initiation for these patients is currently unknown.

Effects of Pretreatment with Satureja Bachtiarica Essential Oil in Preventing Seizure in Pentylenetetrazol-Kindled Mice

Introduction: Epilepsy is a group of chronic neurological disorders characterized by seizures. The aim of the present study was to investigate the effects of pretreatment with Satureja bachtiarica essential oil in preventing epilepsy. Methods: In this experimental study, 50 mice were randomly assigned to five groups of 10 each. The control group received normal saline plus tween80 and, 30 min later, PTZ. Groups 2 and 3 were treated with S. bachtiarica essential oil at 50 and 100 mg/kg and 30 min later received PTZ, respectively. Group 4 received diazepam and 30 min later received PTZ. Group 5 received flumazenil and 30 min later received PTZ. After the last injection of PTZ, the time of seizure onset, seizure severity and score, the completion time of each seizure (attack episode), and mortality rate in different groups were recorded and compared. Results: The administration of S. bachtiarica essential oil at 50 and 100 mg/kg to PTZ-treated mice caused significant increase in latency to first seizure and survival, and significant decrease in the frequency of the head and upper limbs seizure, total body seizures, tonic seizures, and jumping. S. bachtiarica essential oil at 100 mg/kg caused a significant decrease in the head ticks frequency. The administration of flumazenil significantly inhibited S. bachtiarica essential oil induced effects and increased the head and upper limbs seizures, tonic seizures, and jumping. Conclusion: The present study demonstrated that S. bachtiarica essential oil can prevent PTZ-induced seizure and these findings authenticate the traditional claims about use of Satureja bachtiarica in treatment of epilepsy.