Electroencephalographic changes in purified pharmaceutical cannabidiol therapy.

OBJECTIVE: Evaluate electroencephalographic changes in patients receiving purified pharmaceutical cannabidiol (CBD). METHODS: A total of 104 EEG studies from 52 patients with pediatric-onset refractory epilepsy, who were enrolled in the FDA-approved expanded access investigational new drug program, were retrospectively analyzed for electroencephalographic changes in the background, interictal epileptiform discharges (IEDs), ictal findings, and sleep architecture after CBD treatment. RESULTS: Patients were between 18 months and 52 years of age. After CBD treatment, 88.4% (46/52) of patients had EEG changes. Eighty-nine percent of these patients had changes in their background, 74% in IEDs, 46% in ictal findings, and 17% in sleep architecture. Seven out of 52 patients had modified hypsarrhythmia on their pre-treatment EEG. The pattern resolved in 2/7 patients (29%), diminished in prevalence in 4/7 (57%) subjects, and remained unchanged in 1/7 (14%) cases. Electrographic improvement was seen in 70% (32/46) of the patients, and worsening in 7% (3/46) of the cases. At the post-CBD EEG, 83% had a reduction in the frequency of the most predominant seizure type, and 25% reported subjective cognitive improvement. Of these patients, 88% (p = 0.09) and 92% (p = 0.45) had corresponding EEG changes, respectively. CONCLUSION: Our results revealed electrographic changes in association with the CBD treatment. Despite these changes, a substantial association between specific electrographic findings and clinical outcomes was not established.

Clinical presentation, management, and biomarkers of neurotoxicity after adoptive immunotherapy with CAR T cells.

Chimeric antigen receptor (CAR) T cells have emerged as a promising class of cell-based immunotherapy in refractory malignancies. Neurotoxicity represents a common and potentially life-threatening adverse effect of CAR T cells, and clinical experience is limited. Here, we describe the clinical presentation and management of 25 adult patients who presented with neurotoxic syndromes after CAR T-cell therapy at the Massachusetts General Hospital. This cohort includes 24 patients treated with CD19-directed CAR T cells for non-Hodgkin lymphoma (n = 23) and acute lymphoblastic leukemia (n = 1), and 1 patient treated with α-fetoprotein-directed CAR T cells for hepatocellular carcinoma (n = 1). Twelve of the 25 patients (48%) developed grade 1-2 neurotoxicity and 13 patients (52%) presented with grade 3-4 neurotoxicity. We found that lower platelet counts at time of CAR T-cell infusion were associated with more severe neurotoxicity (P = .030). Cytokine release syndrome occurred in 24 of 25 patients (96%). Serum levels of ferritin peaked with onset of neurologic symptoms, and higher ferritin levels were associated with higher neurotoxicity grade. Grade 3-4 neurotoxicity correlated negatively with overall survival (OS) (P = .013). Median OS of the entire cohort was 54.7 weeks. Eight patients (32%) with grade 3-4 neurotoxicity were deceased at database closure, whereas none died with neurotoxicity grade 1-2. High pretreatment lactate dehydrogenase was frequently encountered in lymphoma patients with grade 3-4 neurotoxicity and correlated negatively with progression-free survival (P = .048). We did not find evidence that steroid use ≥7 days altered the patient's outcome when compared with <7 days of steroids. Management of CAR T cell-mediated neurotoxicity warrants evaluation in prospective clinical trials.

Electrographic seizures and ictal-interictal continuum (IIC) patterns in critically ill patients.

Critical care long-term continuous electroencephalogram (cEEG) monitoring has expanded dramatically in the last several decades spurned by technological advances in EEG digitalization and several key clinical findings: 1-Seizures are relatively common in the critically ill-large recent observational studies suggest that around 20% of critically ill patients placed on cEEG have seizures. 2-The majority (~75%) of patients who have seizures have exclusively "electrographic seizures", that is, they have no overt ictal clinical signs. Along with the discovery of the unexpectedly high incidence of seizures was the high prevalence of EEG patterns that share some common features with archetypical electrographic seizures but are not uniformly considered to be "ictal". These EEG patterns include lateralized periodic discharges (LPDs) and generalized periodic discharges (GPDs)-patterns that at times exhibit ictal-like behavior and at other times behave more like an interictal finding. Dr. Hirsch and colleagues proposed a conceptual framework to describe this spectrum of patterns called the ictal-interictal continuum (IIC). In the following years, investigators began to answer some of the key pragmatic clinical concerns such as which patients are at risk of seizures and what is the optimal duration of cEEG use. At the same time, investigators have begun probing the core questions for critical care EEG-what is the underlying pathophysiology of these patterns, at what point do these patterns cause secondary brain injury, what are the optimal treatment strategies, and how do these patterns affect clinical outcomes such as neurological disability and the development of epilepsy. In this review, we cover recent advancements in both practical concerns regarding cEEG use, current treatment strategies, and review the evidence associating IIC/seizures with poor clinical outcomes.

Cannabidiol in treatment of refractory epileptic spasms: An open-label study.

OBJECTIVE: This study aimed to evaluate clinical efficacy and safety of purified pharmaceutical cannabidiol (CBD) as an adjunctive therapy in refractory childhood-onset epileptic spasms (ES). METHODS: Nine patients with ES were enrolled in an Institutional Review Board (IRB)- and Food and Drug Administration (FDA)-approved expanded access investigational new drug trial. Patients received plant-derived highly purified CBD in oral solution in addition to their baseline medications at an initial dosage of 5 mg/kg/day, which was increased by 5 mg/kg/day every week to an initial target dosage of 25 mg/kg/day. Seizure frequency, adverse event, and parents' subjective reports of cognitive and behavioral changes were recorded after 2 weeks and 1, 2, 3, 6, 9, and 12 months of CBD treatment. Responder rates (percent of patients with >50% reduction in ES frequency from baseline) were calculated. Electrographic changes were studied in relation to CBD initiation and clinical response. RESULTS: Overall, the responder rates in 9 patients were 67%, 78%, 67%, 56%, 78%, 78%, and 78% after 2 weeks and 1, 2, 3, 6, 9, and 12 months of CBD treatment, respectively. Three out of nine patients (33%) were ES free after two months of treatment. Parents reported subjective improvements in cognitive and behavioral domains. Side effects, primarily drowsiness, were seen in 89% of patients (n = 8). Eight of the nine (89%) patients had electroencephalographic (EEG) studies prior to and after initiation of CBD. Three out of five patients (60%) had resolution in their hypsarrhythmia pattern. SIGNIFICANCE: Purified pharmaceutical CBD may be an effective and safe adjunctive therapy in refractory ES and may also be associated with improvements in electrographic findings.

Ipilimumab-induced necrotic myelopathy in a patient with metastatic melanoma: A case report and review of literature.

Ipilimumab is a novel humanized monoclonal antibody directed against cytotoxic T lymphocyte antigen 4, a T-cell surface molecule involved in down-regulation and suppression of the T cell response to stimuli. Patients treated with ipilimumab are at risk for immune-related adverse events involving the skin, digestive tract, liver and endocrine organs. Few case reports of immune-related adverse effects involving central or peripheral nervous system due to ipilimumab are published. These include inflammatory myopathy, aseptic meningitis, severe meningo-radiculo-neuritis, temporal arteritis, Guillain-Barre syndrome, and posterior reversible encephalopathy syndrome. We report the first case of ipilimumab-induced progressive necrotic myelopathy.

Ictal asystole in epilepsy patients undergoing inpatient video-EEG monitoring.

Ictal asystole (IA) is uncommonly diagnosed and has been implicated as a potential cause of sudden unexpected death in epilepsy. Sudden unexpected death in epilepsy is an increasingly recognizable condition and is more likely to occur in patients with medically intractable epilepsy and those suffering from convulsive epilepsy. We report 2 cases of recent onset of prolonged syncope and unrevealing cardiac work up. The inpatient video-EEG monitoring recorded left temporal ictal discharges followed by IA. Although the role of cardiac pacing is controversial in these patients, both patients had favorable outcome following cardiac pacemaker insertion. This report demonstrates the variability in IA pathophysiology and clinical manifestations. It also advocates that cardiac pacing might have a role in the management of IA.

Combined neuromodulation and resection for functional cortex epilepsy: a case series.

OBJECTIVE: Medically refractory epilepsy (MRE) often requires resection of the seizure onset zone (SOZ) for effective treatment. However, when the SOZ is in functional cortex (FC), achieving complete and safe resection becomes difficult, due to the seizure network overlap with function. The authors aimed to assess the safety and outcomes of a combined approach involving partial resection combined with focal neuromodulation for FC refractory epilepsy. METHODS: The authors performed a retrospective analysis of individuals diagnosed with MRE who underwent surgical intervention from January 2015 to December 2022. Patients whose SOZ was located in FC and were treated with resection combined with simultaneous implantation of a focal neuromodulation device (responsive neurostimulation [RNS] device) with more than 12 months of follow-up data were included. All patients underwent a standard epilepsy preoperative assessment including intracranial electroencephalography and extraoperative stimulation mapping. Resections were performed under general anesthesia, followed by the concurrent implantation of an RNS device. RESULTS: Seven patients (4 males, median age 32.3 years, all right-handed) were included. The median interval from seizure onset to surgery was 17.4 years. The epileptogenic network included sensorimotor areas (cases 2, 3, and 6), visual cortex (case 1), language areas (cases 4 and 7), and the insula (case 5). The median follow-up was 3 years (range 1-5.8 years). No significant changes in neuropsychological tests were reported. One permanent nondisabling planned neurological deficit (left inferior quadrantanopia) was observed. Six patients had stimulation activated at a median of 4.7 months after resection. All patients achieved good seizure outcomes (5 with Engel class I and 2 with Engel class II outcomes). CONCLUSIONS: Maximal safe resection combined with focal neuromodulation presents a promising alternative to stand-alone resections for MRE epileptogenic zones overlapping with functional brain. This combined approach prioritizes the preservation of function while improving seizure outcomes.

Improving Clinician Performance in Classifying EEG Patterns on the Ictal-Interictal Injury Continuum Using Interpretable Machine Learning.

BACKGROUND: In intensive care units (ICUs), critically ill patients are monitored with electroencephalography (EEG) to prevent serious brain injury. EEG monitoring is constrained by clinician availability, and EEG interpretation can be subjective and prone to interobserver variability. Automated deep-learning systems for EEG could reduce human bias and accelerate the diagnostic process. However, existing uninterpretable (black-box) deep-learning models are untrustworthy, difficult to troubleshoot, and lack accountability in real-world applications, leading to a lack of both trust and adoption by clinicians. METHODS: We developed an interpretable deep-learning system that accurately classifies six patterns of potentially harmful EEG activity - seizure, lateralized periodic discharges (LPDs), generalized periodic discharges (GPDs), lateralized rhythmic delta activity (LRDA), generalized rhythmic delta activity (GRDA), and other patterns - while providing faithful case-based explanations of its predictions. The model was trained on 50,697 total 50-second continuous EEG samples collected from 2711 patients in the ICU between July 2006 and March 2020 at Massachusetts General Hospital. EEG samples were labeled as one of the six EEG patterns by 124 domain experts and trained annotators. To evaluate the model, we asked eight medical professionals with relevant backgrounds to classify 100 EEG samples into the six pattern categories - once with and once without artificial intelligence (AI) assistance - and we assessed the assistive power of this interpretable system by comparing the diagnostic accuracy of the two methods. The model's discriminatory performance was evaluated with area under the receiver-operating characteristic curve (AUROC) and area under the precision-recall curve. The model's interpretability was measured with task-specific neighborhood agreement statistics that interrogated the similarities of samples and features. In a separate analysis, the latent space of the neural network was visualized by using dimension reduction techniques to examine whether the ictal-interictal injury continuum hypothesis, which asserts that seizures and seizure-like patterns of brain activity lie along a spectrum, is supported by data. RESULTS: The performance of all users significantly improved when provided with AI assistance. Mean user diagnostic accuracy improved from 47 to 71% (P<0.04). The model achieved AUROCs of 0.87, 0.93, 0.96, 0.92, 0.93, and 0.80 for the classes seizure, LPD, GPD, LRDA, GRDA, and other patterns, respectively. This performance was significantly higher than that of a corresponding uninterpretable black-box model (with P<0.0001). Videos traversing the ictal-interictal injury manifold from dimension reduction (a two-dimensional representation of the original high-dimensional feature space) give insight into the layout of EEG patterns within the network's latent space and illuminate relationships between EEG patterns that were previously hypothesized but had not yet been shown explicitly. These results indicate that the ictal-interictal injury continuum hypothesis is supported by data. CONCLUSIONS: Users showed significant pattern classification accuracy improvement with the assistance of this interpretable deep-learning model. The interpretable design facilitates effective human-AI collaboration; this system may improve diagnosis and patient care in clinical settings. The model may also provide a better understanding of how EEG patterns relate to each other along the ictal-interictal injury continuum. (Funded by the National Science Foundation, National Institutes of Health, and others.).

On-demand EEG education through competition - A novel, app-based approach to learning to identify interictal epileptiform discharges.

Objective: Misinterpretation of EEGs harms patients, yet few resources exist to help trainees practice interpreting EEGs. We therefore sought to evaluate a novel educational tool to teach trainees how to identify interictal epileptiform discharges (IEDs) on EEG. Methods: We created a public EEG test within the iOS app DiagnosUs using a pool of 13,262 candidate IEDs. Users were shown a candidate IED on EEG and asked to rate it as epileptiform (IED) or not (non-IED). They were given immediate feedback based on a gold standard. Learning was analyzed using a parametric model. We additionally analyzed IED features that best correlated with expert ratings. Results: Our analysis included 901 participants. Users achieved a mean improvement of 13% over 1,000 questions and an ending accuracy of 81%. Users and experts appeared to rely on a similar set of IED morphologic features when analyzing candidate IEDs. We additionally identified particular types of candidate EEGs that remained challenging for most users even after substantial practice. Conclusions: Users improved in their ability to properly classify candidate IEDs through repeated exposure and immediate feedback. Significance: This app-based learning activity has great potential to be an effective supplemental tool to teach neurology trainees how to accurately identify IEDs on EEG.

Development of Expert-Level Classification of Seizures and Rhythmic and Periodic Patterns During EEG Interpretation.

BACKGROUND AND OBJECTIVES: Seizures (SZs) and other SZ-like patterns of brain activity can harm the brain and contribute to in-hospital death, particularly when prolonged. However, experts qualified to interpret EEG data are scarce. Prior attempts to automate this task have been limited by small or inadequately labeled samples and have not convincingly demonstrated generalizable expert-level performance. There exists a critical unmet need for an automated method to classify SZs and other SZ-like events with expert-level reliability. This study was conducted to develop and validate a computer algorithm that matches the reliability and accuracy of experts in identifying SZs and SZ-like events, known as "ictal-interictal-injury continuum" (IIIC) patterns on EEG, including SZs, lateralized and generalized periodic discharges (LPD, GPD), and lateralized and generalized rhythmic delta activity (LRDA, GRDA), and in differentiating these patterns from non-IIIC patterns. METHODS: We used 6,095 scalp EEGs from 2,711 patients with and without IIIC events to train a deep neural network, SPaRCNet, to perform IIIC event classification. Independent training and test data sets were generated from 50,697 EEG segments, independently annotated by 20 fellowship-trained neurophysiologists. We assessed whether SPaRCNet performs at or above the sensitivity, specificity, precision, and calibration of fellowship-trained neurophysiologists for identifying IIIC events. Statistical performance was assessed by the calibration index and by the percentage of experts whose operating points were below the model's receiver operating characteristic curves (ROCs) and precision recall curves (PRCs) for the 6 pattern classes. RESULTS: SPaRCNet matches or exceeds most experts in classifying IIIC events based on both calibration and discrimination metrics. For SZ, LPD, GPD, LRDA, GRDA, and "other" classes, SPaRCNet exceeds the following percentages of 20 experts-ROC: 45%, 20%, 50%, 75%, 55%, and 40%; PRC: 50%, 35%, 50%, 90%, 70%, and 45%; and calibration: 95%, 100%, 95%, 100%, 100%, and 80%, respectively. DISCUSSION: SPaRCNet is the first algorithm to match expert performance in detecting SZs and other SZ-like events in a representative sample of EEGs. With further development, SPaRCNet may thus be a valuable tool for an expedited review of EEGs. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that among patients with epilepsy or critical illness undergoing EEG monitoring, SPaRCNet can differentiate (IIIC) patterns from non-IIIC events and expert neurophysiologists.

Interrater Reliability of Expert Electroencephalographers Identifying Seizures and Rhythmic and Periodic Patterns in EEGs.

BACKGROUND AND OBJECTIVES: The validity of brain monitoring using electroencephalography (EEG), particularly to guide care in patients with acute or critical illness, requires that experts can reliably identify seizures and other potentially harmful rhythmic and periodic brain activity, collectively referred to as "ictal-interictal-injury continuum" (IIIC). Previous interrater reliability (IRR) studies are limited by small samples and selection bias. This study was conducted to assess the reliability of experts in identifying IIIC. METHODS: This prospective analysis included 30 experts with subspecialty clinical neurophysiology training from 18 institutions. Experts independently scored varying numbers of ten-second EEG segments as "seizure (SZ)," "lateralized periodic discharges (LPDs)," "generalized periodic discharges (GPDs)," "lateralized rhythmic delta activity (LRDA)," "generalized rhythmic delta activity (GRDA)," or "other." EEGs were performed for clinical indications at Massachusetts General Hospital between 2006 and 2020. Primary outcome measures were pairwise IRR (average percent agreement [PA] between pairs of experts) and majority IRR (average PA with group consensus) for each class and beyond chance agreement (κ). Secondary outcomes were calibration of expert scoring to group consensus, and latent trait analysis to investigate contributions of bias and noise to scoring variability. RESULTS: Among 2,711 EEGs, 49% were from women, and the median (IQR) age was 55 (41) years. In total, experts scored 50,697 EEG segments; the median [range] number scored by each expert was 6,287.5 [1,002, 45,267]. Overall pairwise IRR was moderate (PA 52%, κ 42%), and majority IRR was substantial (PA 65%, κ 61%). Noise-bias analysis demonstrated that a single underlying receiver operating curve can account for most variation in experts' false-positive vs true-positive characteristics (median [range] of variance explained ([Formula: see text]): 95 [93, 98]%) and for most variation in experts' precision vs sensitivity characteristics ([Formula: see text]: 75 [59, 89]%). Thus, variation between experts is mostly attributable not to differences in expertise but rather to variation in decision thresholds. DISCUSSION: Our results provide precise estimates of expert reliability from a large and diverse sample and a parsimonious theory to explain the origin of disagreements between experts. The results also establish a standard for how well an automated IIIC classifier must perform to match experts. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that an independent expert review reliably identifies ictal-interictal injury continuum patterns on EEG compared with expert consensus.

Epilepsy surgery in a developing country (Lebanon): ten years experience and predictors of outcome.

We present our 10-year experience and preoperative predictors of outcome in 93 adults and children who underwent epilepsy surgery at the American University of Beirut. Presurgical evaluation included video-EEG monitoring, MRI, neuropsychological assessment with invasive monitoring, and other tests (PET, SPECT, Wada). Surgeries included temporal (54%), extratemporal (22%), and multilobar resections (13%), hemispherectomy (4%), vagal nerve stimulation (6%), and corpus callosotomy (1%). Mesial temporal sclerosis was the most common aetiology (37%). After resective surgery, 70% had Engel class I, 9% class II, 14% class III, and 7% class IV. The number of antiepileptic drugs before surgery was the only preoperative factor associated with Engel class I (p=0.005). Despite the presence of financial and philanthropic aid, many patients could not be operated on for financial reasons. We conclude that advanced epilepsy presurgical workups, surgical procedures, and favourable outcomes, comparable to those of developed countries, are achievable in developing countries, but that issues of financial coverage remain to be addressed.

Hemisphere-Dependent Ictal Tachycardia Versus Ictal Bradycardia in a Critically Ill Patient.

SUMMARY: Tachycardia is a common ictal phenomenon; however, ictal bradycardia is less commonly reported and rarely presents as ictal asystole/syncope. In critically ill patients, seizures are much less likely to manifest with overt clinical signs, i.e., are more likely to be subtle or nonconvulsive. In this setting, changes in heart rate may be the only clue that seizures are occurring. The authors report an exemplary case of a 78-year-old right-handed man who presented with spontaneous left frontal intraparenchymal hemorrhages. During standard clinical monitoring in the Neuro-Intensive Care Unit, the patient had discrete paroxysms of relative sinus tachycardia, independent episodes of sinus bradycardia, and 3 to 4 seconds of sinus pause. The cardiac investigation was unrevealing, but continuous EEG revealed the answer. The episodes of mild tachycardia were associated with seizures from the left temporal region, whereas those with bradycardia were associated with independent seizures from the right temporal region. The case stands as a stark reminder to remain vigilant of seizures in high-risk patients, especially as a cause for paroxysmal autonomic changes.

Measuring expertise in identifying interictal epileptiform discharges.

OBJECTIVE: Interictal epileptiform discharges on EEG are integral to diagnosing epilepsy. However, EEGs are interpreted by readers with and without specialty training, and there is no accepted method to assess skill in interpretation. We aimed to develop a test to quantify IED recognition skills. METHODS: A total of 13,262 candidate IEDs were selected from EEGs and scored by eight fellowship-trained reviewers to establish a gold standard. An online test was developed to assess how well readers with different training levels could distinguish candidate waveforms. Sensitivity, false positive rate and calibration were calculated for each reader. A simple mathematical model was developed to estimate each reader's skill and threshold in identifying an IED, and to develop receiver operating characteristics curves for each reader. We investigated the number of IEDs needed to measure skill level with acceptable precision. RESULTS: Twenty-nine raters completed the test; nine experts, seven experienced non-experts and thirteen novices. Median calibration errors for experts, experienced non-experts and novices were -0.056, 0.012, 0.046; median sensitivities were 0.800, 0.811, 0.715; and median false positive rates were 0.177, 0.272, 0.396, respectively. The number of test questions needed to measure those scores was 549. Our analysis identified that novices had a higher noise level (uncertainty) compared to experienced non-experts and experts. Using calculated noise and threshold levels, receiver operating curves were created, showing increasing median area under the curve from novices (0.735), to experienced non-experts (0.852) and experts (0.891). SIGNIFICANCE: Expert and non-expert readers can be distinguished based on ability to identify IEDs. This type of assessment could also be used to identify and correct differences in thresholds in identifying IEDs.

Rapid annotation of seizures and interictal-ictal-injury continuum EEG patterns.

BACKGROUND: Manual annotation of seizures and interictal-ictal-injury continuum (IIIC) patterns in continuous EEG (cEEG) recorded from critically ill patients is a time-intensive process for clinicians and researchers. In this study, we evaluated the accuracy and efficiency of an automated clustering method to accelerate expert annotation of cEEG. NEW METHOD: We learned a local dictionary from 97 ICU patients by applying k-medoids clustering to 592 features in the time and frequency domains. We utilized changepoint detection (CPD) to segment the cEEG recordings. We then computed a bag-of-words (BoW) representation for each segment. We further clustered the segments by affinity propagation. EEG experts scored the resulting clusters for each patient by labeling only the cluster medoids. We trained a random forest classifier to assess validity of the clusters. RESULTS: Mean pairwise agreement of 62.6% using this automated method was not significantly different from interrater agreements using manual labeling (63.8%), demonstrating the validity of the method. We also found that it takes experts using our method 5.31 ±â€¯4.44 min to label the 30.19 ±â€¯3.84 h of cEEG data, more than 45 times faster than unaided manual review, demonstrating efficiency. COMPARISON WITH EXISTING METHODS: Previous studies of EEG data labeling have generally yielded similar human expert interrater agreements, and lower agreements with automated methods. CONCLUSIONS: Our results suggest that long EEG recordings can be rapidly annotated by experts many times faster than unaided manual review through the use of an advanced clustering method.

Continuous EEG Findings in Autoimmune Encephalitis.

PURPOSE: Autoimmune encephalitis (AE) is a cause of new-onset seizures, including new-onset refractory status epilepticus, yet there have been few studies assessing the EEG signature of AE. METHODS: Multicenter retrospective review of patients diagnosed with AE who underwent continuous EEG monitoring. RESULTS: We identified 64 patients (male, 39%; white, 49%; median age, 44 years); of whom, 43 (67%) were antibody-proven AE patients. Of the patients with confirmed antibody AE, the following were identified: N-methyl-D-aspartate receptor (n = 17, 27%), voltage-gated potassium channel (n = 16, 25%), glutamic acid decarboxylase (n = 6, 9%), and other (n = 4, 6%). The remaining patients were classified as probable antibody-negative AE (n = 11, 17%), definite limbic encephalitis (antibody-negative) (n = 2, 3%), and Hashimoto encephalopathy (n = 8, 13%). Fifty-three percent exhibited electrographic seizures. New-onset refractory status epilepticus was identified in 19% of patients. Sixty-three percent had periodic or rhythmic patterns; of which, 38% had plus modifiers. Generalized rhythmic delta activity was identified in 33% of patients. Generalized rhythmic delta activity and generalized rhythmic delta activity plus fast activity were more common in anti-N-methyl-D-aspartate AE (P = 0.0001 and 0.0003, respectively). No other periodic or rhythmic patterns exhibited AE subtype association. Forty-two percent had good outcome on discharge. Periodic or rhythmic patterns, seizures, and new-onset refractory status epilepticus conferred an increased risk of poor outcome (OR, 6.4; P = 0.0012; OR, 3; P = 0.0372; OR, 12.3; P = 0.02, respectively). CONCLUSION: Our study confirms a signature EEG pattern in anti-N-methyl-D-aspartate AE, termed extreme delta brush, identified as generalized rhythmic delta activity plus fast activity in our study. We found no other pattern association with other AE subtypes. We also found a high incidence of seizures among patients with AE. Finally, periodic or rhythmic patterns, seizures, and new-onset refractory status epilepticus conferred an increased risk of poor outcome regardless of AE subtype.

Deep active learning for Interictal Ictal Injury Continuum EEG patterns.

OBJECTIVES: Seizures and seizure-like electroencephalography (EEG) patterns, collectively referred to as "ictal interictal injury continuum" (IIIC) patterns, are commonly encountered in critically ill patients. Automated detection is important for patient care and to enable research. However, training accurate detectors requires a large labeled dataset. Active Learning (AL) may help select informative examples to label, but the optimal AL approach remains unclear. METHODS: We assembled >200,000 h of EEG from 1,454 hospitalized patients. From these, we collected 9,808 labeled and 120,000 unlabeled 10-second EEG segments. Labels included 6 IIIC patterns. In each AL iteration, a Dense-Net Convolutional Neural Network (CNN) learned vector representations for EEG segments using available labels, which were used to create a 2D embedding map. Nearest-neighbor label spreading within the embedding map was used to create additional pseudo-labeled data. A second Dense-Net was trained using real- and pseudo-labels. We evaluated several strategies for selecting candidate points for experts to label next. Finally, we compared two methods for class balancing within queries: standard balanced-based querying (SBBQ), and high confidence spread-based balanced querying (HCSBBQ). RESULTS: Our results show: 1) Label spreading increased convergence speed for AL. 2) All query criteria produced similar results to random sampling. 3) HCSBBQ query balancing performed best. Using label spreading and HCSBBQ query balancing, we were able to train models approaching expert-level performance across all pattern categories after obtaining ∼7000 expert labels. CONCLUSION: Our results provide guidance regarding the use of AL to efficiently label large EEG datasets in critically ill patients.

Extracranial venous stenosis is an unlikely cause of multiple sclerosis.

BACKGROUND: Extracranial venous stenosis (EVS) has recently been implicated as the primary cause of multiple sclerosis (MS). OBJECTIVE: The aim of this study was to determine the presence of EVS in MS patients. METHODS: We performed selective extracranial venography on 42 patients with early MS (EMS): clinically isolated syndrome (CIS) or relapsing-remitting MS (RRMS) of less than 5 years duration, and late MS (LMS): RRMS of more than 10 years duration. Magnetic resonance imaging (MRI) and clinical relapse data were reviewed for all patients with EVS. RESULTS: EVS was present in 7/29 patients with EMS and 12/13 patients with LMS, a highly significant statistical difference (p< 0.001). Only 3/42 patients (all in the LMS group) had two vessel stenoses, while the rest had only one vessel involved. EVS was seen in 1/11 patients with CIS compared with 6/18 RRMS patients of less than 5 years duration. Disease duration was greater in patients with EVS overall (p < 0.005). LMS remained an independent predictor of EVS following multivariate adjustment for gender, age at disease onset and Expanded Disability Status Scale (EDSS) (Adjusted Odds Ratio = 29 (3-298); p = 0.005]. Within the EMS group, patients with (n = 7) and without (n = 22) EVS had similar EDSS and disease duration, suggesting similar disease severity. No clear correlation could be found between site of EVS and anatomic localization of either clinical relapses or MRI gadolinium-enhancing lesions. CONCLUSIONS: We conclude that EVS is an unlikely cause of MS since it is not present in most patients early in the disease and rarely involves more than one extracranial vein. It is likely to be a late secondary phenomenon.

Language dysfunction-associated EEG findings in patients with CAR-T related neurotoxicity.

Chimeric antigen receptor-modified T cells (CAR-T) have emerged as a promising immunotherapeutic approach in relapsed/refractory haematolgical malignancies. Broader application is limited by unique toxicities, notably, neurotoxicity (NTX). Language dysfunction is among the most frequent symptoms of NTX, the underlying mechanisms of which remain to be elucidated. Electroencephalogram (EEG) is an important tool to monitor for NTX and may provide insights into language dysfunction. AIM: We aimed to characterise language dysfunction and define electroencephalographic signatures after CAR-T cell therapy. METHODS: We reviewed the clinical presentation and EEG findings of 20 adult patients presenting with language dysfunction after CAR-T cell infusion. The cohort included a subset of patients treated with investigational CD19-directed CAR-T cells for non-Hodgkin's lymphoma (n=17), acute lymphoblastic leukaemia (n=1), follicular lymphoma (n=1) and chronic lymphocytic leukaemia (n=1). RESULTS: Language dysfunction presented within 14 days of CAR-T cell infusion in 16 (84%) patients. Ten (50%) patients had mild word-finding difficulties and 10 (50%) had marked dysphasia with profound word-finding difficulties; the latter were all associated with generalised rhythmic delta activity or generalised periodic discharges on EEG. CONCLUSIONS: Language dysfunction after CAR-T cell therapy is associated with generalised EEG abnormalities.

Development of Expert-Level Automated Detection of Epileptiform Discharges During Electroencephalogram Interpretation.

Importance: Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are a biomarker of epilepsy, seizure risk, and clinical decline. However, there is a scarcity of experts qualified to interpret EEG results. Prior attempts to automate IED detection have been limited by small samples and have not demonstrated expert-level performance. There is a need for a validated automated method to detect IEDs with expert-level reliability. Objective: To develop and validate a computer algorithm with the ability to identify IEDs as reliably as experts and classify an EEG recording as containing IEDs vs no IEDs. Design, Setting, and Participants: A total of 9571 scalp EEG records with and without IEDs were used to train a deep neural network (SpikeNet) to perform IED detection. Independent training and testing data sets were generated from 13 262 IED candidates, independently annotated by 8 fellowship-trained clinical neurophysiologists, and 8520 EEG records containing no IEDs based on clinical EEG reports. Using the estimated spike probability, a classifier designating the whole EEG recording as positive or negative was also built. Main Outcomes and Measures: SpikeNet accuracy, sensitivity, and specificity compared with fellowship-trained neurophysiology experts for identifying IEDs and classifying EEGs as positive or negative or negative for IEDs. Statistical performance was assessed via calibration error and area under the receiver operating characteristic curve (AUC). All performance statistics were estimated using 10-fold cross-validation. Results: SpikeNet surpassed both expert interpretation and an industry standard commercial IED detector, based on calibration error (SpikeNet, 0.041; 95% CI, 0.033-0.049; vs industry standard, 0.066; 95% CI, 0.060-0.078; vs experts, mean, 0.183; range, 0.081-0.364) and binary classification performance based on AUC (SpikeNet, 0.980; 95% CI, 0.977-0.984; vs industry standard, 0.882; 95% CI, 0.872-0.893). Whole EEG classification had a mean calibration error of 0.126 (range, 0.109-0.1444) vs experts (mean, 0.197; range, 0.099-0.372) and AUC of 0.847 (95% CI, 0.830-0.865). Conclusions and Relevance: In this study, SpikeNet automatically detected IEDs and classified whole EEGs as IED-positive or IED-negative. This may be the first time an algorithm has been shown to exceed expert performance for IED detection in a representative sample of EEGs and may thus be a valuable tool for expedited review of EEGs.