Search

Objective: Add‐on cannabidiol (CBD) reduced seizures associated with Dravet syndrome (DS) in two randomized, double‐blind, placebo‐controlled trials: GWPCARE1 Part B (NCT02091375) and GWPCARE2 (NCT02224703). Patients who completed GWPCARE1 Part A (NCT02091206) or Part B, or GWPCARE2, were enrolled in a long‐term open‐label extension trial, GWPCARE5 (NCT02224573). We present an interim analysis of the safety, efficacy, and patient‐reported outcomes from GWPCARE5. Methods: Patients received a pharmaceutical formulation of highly purified CBD in oral solution (100 mg/ml), titrated from 2.5 to 20 mg/kg/day over a 2‐week period, added to their existing medications. Based on response and tolerance, CBD could be reduced or increased to 30 mg/kg/day. Results: Of the 330 patients who completed the original randomized trials, 315 (95%) enrolled in this open‐label extension. Median treatment duration was 444 days (range = 18–1535), with a mean modal dose of 22 mg/kg/day; patients received a median of three concomitant antiseizure medications. Adverse events (AEs) occurred in 97% patients (mild, 23%; moderate, 50%; severe, 25%). Commonly reported AEs were diarrhea (43%), pyrexia (39%), decreased appetite (31%), and somnolence (28%). Twenty‐eight (9%) patients discontinued due to AEs. Sixty‐nine (22%) patients had liver transaminase elevations >3 × upper limit of normal; 84% were on concomitant valproic acid. In patients from GWPCARE1 Part B and GWPCARE2, the median reduction from baseline in monthly seizure frequency assessed in 12‐week periods up to Week 156 was 45%–74% for convulsive seizures and 49%–84% for total seizures. Across all visit windows, ≥83% patients/caregivers completing a Subject/Caregiver Global Impression of Change scale reported improvement in overall condition. Significance: We show that long‐term CBD treatment had an acceptable safety profile and led to sustained, clinically meaningful reductions in seizure frequency in patients with treatment‐resistant DS. [ABSTRACT FROM AUTHOR]

• A common neurophysiology data format is needed to improving long-term storage and data exchange in clinical practice and research. • The DICOM standard is widely adopted and offers a unique environment to accomplish neurophysiology format standardization. • DICOM Working Group 32 (WG-32) has created an initial set of standards for routine EEG, PSG, EMG and EOG. A standard format for neurophysiology data is urgently needed to improve clinical care and promote research data exchange. Previous neurophysiology format standardization projects have provided valuable insights into how to accomplish the project. In medical imaging, the Digital Imaging and Communication in Medicine (DICOM) standard is widely adopted. DICOM offers a unique environment to accomplish neurophysiology format standardization because neurophysiology data can be easily integrated with existing DICOM-supported elements such as video, ECG, and images and also because it provides easy integration into hospital Picture Archiving and Communication Systems (PACS) long-term storage systems. Through the support of the International Federation of Clinical Neurophysiology (IFCN) and partners in industry, DICOM Working Group 32 (WG-32) has created an initial set of standards for routine electroencephalography (EEG), polysomnography (PSG), electromyography (EMG), and electrooculography (EOG). Longer and more complex neurophysiology data types such as high-definition EEG, long-term monitoring EEG, intracranial EEG, magnetoencephalography, advanced EMG, and evoked potentials will be added later. In order to provide for efficient data compression, a DICOM neurophysiology codec design competition will be held by the IFCN and this is currently being planned. We look forward to a future when a common DICOM neurophysiology data format makes data sharing and storage much simpler and more efficient. [ABSTRACT FROM AUTHOR]

Seizure freedom is recognized as the goal of epilepsy treatment by patients, families, and in treatment guidelines and is associated with notably improved quality of life. However, many studies of epilepsy treatments (including antiseizure medications/antiepileptic drugs, neurostimulation, and dietary therapies) fail to report data on seizure freedom. Even among studies that include this outcome, methods for defining and analyzing seizure freedom vary considerably. Thus, the available data are often difficult to interpret and comparisons between studies are particularly challenging. Although these issues had been identified over a decade ago, there remains a lack of clarity and standardized methods used in analyzing and reporting seizure freedom outcomes in studies of epilepsy treatments. In addition, it remains unclear whether short‐term seizure freedom outcomes from pivotal clinical trials are predictive of longer‐term seizure freedom outcomes for patients with treatment‐refractory epilepsy. Ultimately, the limitations of the available data lead to the potential for misinterpretation and misunderstanding of seizure freedom outcomes associated with the spectrum of available treatments when examining treatment options for patients. Clearly defined outcome analyses of seizure freedom attainment and duration are essential in future clinical studies of treatment for seizures to guide treatment selection and modification for patients. [ABSTRACT FROM AUTHOR]

Objective A prospective multicenter phase III trial was undertaken to evaluate the performance and tolerability in the epilepsy monitoring unit ( EMU) of an investigational wearable surface electromyographic ( sEMG) monitoring system for the detection of generalized tonic-clonic seizures ( GTCSs). Methods One hundred ninety-nine patients with a history of GTCSs who were admitted to the EMU in 11 level IV epilepsy centers for clinically indicated video-electroencephalographic monitoring also received sEMG monitoring with a wearable device that was worn on the arm over the biceps muscle. All recorded sEMG data were processed at a central site using a previously developed detection algorithm. Detected GTCSs were compared to events verified by a majority of three expert reviewers. Results For all subjects, the detection algorithm detected 35 of 46 (76%, 95% confidence interval [CI] = 0.61-0.87) of the GTCSs, with a positive predictive value ( PPV) of 0.03 and a mean false alarm rate ( FAR) of 2.52 per 24 h. For data recorded while the device was placed over the midline of the biceps muscle, the system detected 29 of 29 GTCSs (100%, 95% CI = 0.88-1.00), with a detection delay averaging 7.70 s, a PPV of 6.2%, and a mean FAR of 1.44 per 24 h. Mild to moderate adverse events were reported in 28% (55 of 199) of subjects and led to study withdrawal in 9% (17 of 199). These adverse events consisted mostly of skin irritation caused by the electrode patch that resolved without treatment. No serious adverse events were reported. Significance Detection of GTCSs using an sEMG monitoring device on the biceps is feasible. Proper positioning of this device is important for accuracy, and for some patients, minimizing the number of false positives may be challenging. [ABSTRACT FROM AUTHOR]

The article presents the guideline of the American Clinical Neurophysiology Society (ACNS) on recording Clinical Electroencephalography (EEG) on digital media. Topics include the need for compliance with the Health Insurance Portability and Accountability Act (HIPAA), the digital signal acquisition parameters during the recording of information, and the capability of clinical recording systems to review recorded EEG data.

• Minimum standards are needed to improve the accuracy, efficacy, and reliability of recording routine and sleep electroencephalography (EEG). • The overall quality of research evidence was low, leading to conditional recommendations based on consensus. • We formulated 16 recommendations for minimum standards for recording routine and sleep EEG. • Implementation strategies need to be tailored by local organizations or chapters. This article provides recommendations on the minimum standards for recording routine ("standard") and sleep electroencephalography (EEG). The joint working group of the International Federation of Clinical Neurophysiology (IFCN) and the International League Against Epilepsy (ILAE) developed the standards according to the methodology suggested for epilepsy-related clinical practice guidelines by the Epilepsy Guidelines Working Group. We reviewed the published evidence using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement. The quality of evidence for sleep induction methods was assessed by the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) method. A tool for Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) was used to assess the risk of bias in technical and methodological studies. Where high-quality published evidence was lacking, we used modified Delphi technique to reach expert consensus. The GRADE system was used to formulate the recommendations. The quality of evidence was low or moderate. We formulated 16 consensus-based recommendations for minimum standards for recording routine and sleep EEG. The recommendations comprise the following aspects: indications, technical standards, recording duration, sleep induction, and provocative methods. [ABSTRACT FROM AUTHOR]

This article provides recommendations on the minimum standards for recording routine ("standard") and sleep electroencephalography (EEG). The joint working group of the International Federation of Clinical Neurophysiology (IFCN) and the International League Against Epilepsy (ILAE) developed the standards according to the methodology suggested for epilepsy‐related clinical practice guidelines by the Epilepsy Guidelines Working Group. We reviewed the published evidence using the Preferred Reporting Items for Systematic Review and Meta‐Analysis (PRISMA) statement. The quality of evidence for sleep induction methods was assessed by the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) method. A tool for Quality Assessment of Diagnostic Studies (QUADAS‐2) was used to assess the risk of bias in technical and methodological studies. Where high‐quality published evidence was lacking, we used modified Delphi technique to reach expert consensus. The GRADE system was used to formulate the recommendations. The quality of evidence was low or moderate. We formulated 16 consensus‐based recommendations for minimum standards for recording routine and sleep EEG. The recommendations comprise the following aspects: indications, technical standards, recording duration, sleep induction, and provocative methods. [ABSTRACT FROM AUTHOR]

Abstract: The routine scalp electroencephalogram (rsEEG) is the most common clinical neurophysiology procedure. The most important role of rsEEG is to detect evidence of epilepsy, in the form of epileptiform transients (ETs), also known as spike or sharp wave discharges. Due to the wide variety of morphologies of ETs and their similarity to artifacts and waves that are part of the normal background activity, the task of ET detection is difficult and mistakes are frequently made. The development of reliable computerized detection of ETs in the EEG could assist physicians in interpreting rsEEGs. We report progress in developing a standardized database for testing and training ET detection algorithms. We describe a new version of our EEGnet software system for collecting expert opinion on EEG datasets, a completely web-browser based system. We report results of EEG scoring from a group of 11 board-certified academic clinical neurophysiologists who annotated 30-s excepts from rsEEG recordings from 100 different patients. The scorers had moderate inter-scorer reliability and low to moderate intra-scorer reliability. In order to measure the optimal size of this standardized rsEEG database, we used machine learning models to classify paroxysmal EEG activity in our database into ET and non-ET classes. Based on our results, it appears that our database will need to be larger than its current size. Also, our non-parametric classifier, an artificial neural network, performed better than our parametric Bayesian classifier. Of our feature sets, the wavelet feature set proved most useful for classification. [Copyright &y& Elsevier]

To assess the efficacy, safety, and tolerability of adjunctive carisbamate treatment at 800 mg/day and 1,200 mg/day in patients with partial-onset seizures (POS). Patients ≥16 years of age with an established diagnosis of POS for ≥1 year and uncontrolled on one to three antiepileptic drugs were enrolled. Eligible patients remained on stable doses of prescribed antiepileptic drugs for an 8-week pretreatment baseline phase and were then randomized (1:1:1) to receive carisbamate (800 mg/day or 1,200 mg/day), or placebo, for a 14-week double-blind phase. Primary efficacy endpoints were percentage reduction in POS frequency and responder rate (patients with ≥50% reduction in POS frequency) during the double-blind versus baseline phase. Five hundred forty-seven patients were randomized; 540 composed the intent-to-treat (ITT) analysis. Four hundred thirty-four patients (79%) completed the study. The median percent reduction from baseline to treatment phase in POS frequency was: 21% (placebo); 30% (carisbamate 800 mg); 36% (carisbamate 1,200 mg), and 32% (combined carisbamate doses). The combined carisbamate dose group was not significantly different from placebo for the median percent reduction of POS frequency (p = 0.20) or responder rate (p = 0.18). Therefore, the difference from placebo for the individual carisbamate dose groups was also considered nonsignificant, based on a prespecified step-down analysis. Dizziness was the most common treatment-emergent adverse event, with a higher incidence (≥5% difference) in the combined carisbamate group (31%) than placebo (9%); the incidence was higher with carisbamate 1,200 mg (32%, n = 58) than with carisbamate 800 mg (30%, n = 53). Adjunctive carisbamate therapy in patients with POS did not demonstrate efficacy across the dose range assessed versus placebo. No new safety findings were observed. [ABSTRACT FROM AUTHOR]

It is widely recognized that visual screening of long-term EEG recordings can be time-consuming and labor-intensive due to the large volume of patient data produced daily in most Epilepsy Monitoring Units (EMUs). As a result, seizures, especially those with only electrographic changes, are sometimes overlooked, which for some patients could result in missed information for diagnosis, an unnecessarily prolonged hospital stay, and unavailable EMU beds for others. In this report, we propose that a better solution for identifying seizures in long-term EEG recording is to combine detection results from a reliable (high sensitivity and low false detection rate) automated detection system with EEG technologists' visual screening process. Using commercially available detection software, we present case studies that demonstrate potential benefits of this method that could help improve detection rates and bring greater efficiency to the seizure identification process in long-term EEG monitoring. [ABSTRACT FROM AUTHOR]

Abstract: Computerized detection of epileptiform transients (ETs), also called spikes and sharp waves, in the electroencephalogram (EEG) has been a research goal for the last 40years. A reliable method for detecting ETs could improve efficiency in reviewing long EEG recordings and assist physicians in interpreting routine EEGs. Computer algorithms developed so far for detecting ETs are not as reliable as human expert interpreters, mostly due to the large number of false positive detections. Typical methods for ET detection include measuring waveform morphology, detecting signal non-stationarity, and power spectrum analysis. Some progress has been made by using more advanced algorithmic approaches including wavelet analysis, artificial neural networks, and dipole analysis. Comparing the performance of different algorithms is difficult since each study uses its own EEG test dataset. In order to overcome this problem, European researchers in the field of computerized electrocardiogram interpretation organized a large multi-center research workgroup to create a standardized dataset of ECG recordings which were interpreted by a large group of cardiologists. EEG researchers need to follow this as a model and seek funding for the creation of a standardized EEG research dataset to develop ET detection algorithms and certify commercial software. [Copyright &y& Elsevier]

Hippocampal sclerosis is frequently associated with hippocampal atrophy (HA), which is often observed on routine magnetic resonance imaging (MRI) of patients with medial temporal lobe epilepsy (MTLE). Manual morphometry of the hippocampus is sensitive to detecting HA, but is time-consuming and prone to operator error. Automated MRI morphometry has the potential to provide rapid and accurate assistance in the clinical detection of HA. We performed a voxel-based morphometry analysis of 23 consecutive subjects with MTLE and 58 matched controls. Images from randomly selected 34 controls were used to create mean and standard deviation images of gray matter volume. Voxel-wise standardized Z-score hippocampal images from patients and the remaining 24 controls were cross-checked with receiver operating characteristic (ROC) curves to evaluate sensitivity versus one-specificity rate for a binary classifier (atrophied versus normal hippocampi). The ipsilateral hippocampi of patients with MTLE displayed a significantly lower mean Z-score compared to the hippocampi of controls [F(2,67)  = 33.014, p < 0.001, Tukey HSD < 0.001]. A classifier using the hippocampal gray matter Z-scores to discriminate between atrophied and normal hippocampi yielded a fitted ROC = 97.3, traditionally considered an excellent discriminator, with a standard error of classification of 1.173 individuals if  100  patients and  100  controls are studied. Automatic morphometry can be potentially used as a clinical tool to assist the detection of HA in patients with MTLE. It can provide a quantifiable estimative of atrophy, which can aid in the decision about the presence of clinically relevant HA. [ABSTRACT FROM AUTHOR]

Despite the advent of new antiepileptic drugs (AEDs) over the past 15 years, the treatment of uncontrolled partial-onset seizures remains a dilemma for clinicians. The most recent AEDs offer new mechanisms of action and more favorable safety profiles than the first generation of AEDs. Lacosamide (LCM) is the latest AED awaiting approval by the FDA for adjunctive use in partial-onset seizures. It differs from all other approved AEDs in that it has two novel mechanisms of action and favorable pharmacokinetic and safety profiles. The purposes of this article are to present the significant parameters for its use in clinical practice, by summarizing the preliminary results of phase II and III clinical trials, and to compare its efficacy data with other second-generation AEDs. [ABSTRACT FROM AUTHOR]

• Soticlestat is a first-in-class inhibitor of cholesterol 24-hydroxylase (CH24H). • Developmental and/or epileptic encephalopathies (DEE) are rare, severe epilepsies. • Soticlestat is being evaluated for treatment of seizures associated with DEEs including Dravet and Lennox–Gastaut syndromes. • Soticlestat was well tolerated with efficacy results that support further studies. • Soticlestat reduced plasma 24HC, a potential biomarker of pharmacodynamic activity. To evaluate the safety, tolerability, and pharmacokinetics of soticlestat, a first-in-class cholesterol 24-hydroxylase inhibitor, in adults with developmental and/or epileptic encephalopathies (DEE). The study comprised a 30-day, randomized, double-blind, placebo-controlled phase (Part A), followed by a 55-day open-label phase (Part B) (ClinicalTrials.gov ID: NCT03166215). In Part A, patients with DEE and at least one bilateral motor seizure during the 4-week prospective baseline period were randomized 4:1 to receive soticlestat or placebo, in addition to their usual antiseizure medication. In Part B, all patients received open-label soticlestat. Soticlestat doses were titrated according to tolerability to a maximum of 300 mg twice daily (BID). Safety evaluations included the incidence of treatment-emergent adverse events (TEAEs). Plasma soticlestat concentrations were measured at various times for determination of multiple-dose pharmacokinetics and 24 S -hydroxycholesterol (24HC). Efficacy was assessed by evaluation of changes in seizure frequency from baseline. Eighteen patients (median age, 28.5 years) were enrolled and randomized, and 14 (78 %) completed the study. In Part A, TEAEs occurred in 71.4 % of soticlestat-treated patients and 100 % of placebo-treated patients. In Part B, the overall incidence of TEAEs was 68.8 %. In Part A, TEAEs that occurred in more than one patient in the soticlestat group were dysarthria (n = 3, 21.4 %), lethargy (n = 2, 14.3 %), upper respiratory tract infection (n = 2, 14.3 %), fatigue (n = 2, 14.3 %), and headache (n = 2, 14.3 %). Four patients discontinued treatment because of TEAEs, of whom two reported drug-related seizure clusters as serious TEAEs. There were no deaths. Pharmacokinetic analysis showed dose-dependent increases in systemic exposure and peak plasma soticlestat concentrations. At the end of Part B, the overall mean percent change from baseline in plasma 24HC was −80.97 %. Changes from baseline in median seizure frequency were +16.71 % and +22.16 % in the soticlestat and placebo groups, respectively, in Part A, and −36.38 % in all participants in Part B. Soticlestat was well tolerated at doses of up to 300 mg BID and was associated with a reduction in median seizure frequency over the study duration. Further studies are warranted to assess the possible efficacy of soticlestat as adjunctive therapy in patients with DEEs such as Dravet syndrome and Lennox–Gastaut syndrome. [ABSTRACT FROM AUTHOR]

BACKGROUND:Other conditions that can mimic postpartum depression are rare but must be considered.CASE:A 37-year-old woman developed mood symptoms as well as progressive hyperphagia, hypersexuality, disinhibition, and impairment of judgment after delivery of her third child. She was unresponsive to multiple treatments for depression and was evaluated for frontal lobe syndromes.CONCLUSION:Frontotemporal dementia, formerly known as Pick disease, is a primary degenerative dementia for which no cause is clearly established. Family history or genetic abnormalities are found in about 50% of cases. The diagnosis is frequently missed or delayed, as in this case, because it occurs in a younger age group, presents with unusual signs and symptoms, and is far less prevalent than Alzheimer disease. [Copyright &y& Elsevier]

Background: Other conditions that can mimic postpartum depression are rare but must be considered.Case: A 37-year-old woman developed mood symptoms as well as progressive hyperphagia, hypersexuality, disinhibition, and impairment of judgment after delivery of her third child. She was unresponsive to multiple treatments for depression and was evaluated for frontal lobe syndromes.Conclusion: Frontotemporal dementia, formerly known as Pick disease, is a primary degenerative dementia for which no cause is clearly established. Family history or genetic abnormalities are found in about 50% of cases. The diagnosis is frequently missed or delayed, as in this case, because it occurs in a younger age group, presents with unusual signs and symptoms, and is far less prevalent than Alzheimer disease. [ABSTRACT FROM AUTHOR]

Objective: We determined retention on open‐label cenobamate therapy in the clinical development program to assess the long‐term efficacy and tolerability of adjunctive cenobamate in individuals with uncontrolled focal seizures. Methods: Data from two randomized, controlled cenobamate studies and one open‐label safety and pharmacokinetic study were pooled. Based on the percentage of participants remaining on treatment, retention rates were estimated using Kaplan‐Meier survival analyses. We performed two additional analyses to assess factors contributing to retention, stratifying a robust data set (through 2 years) by cenobamate modal dose and frequently used concomitant anti‐seizure medications. Cenobamate discontinuations and treatment‐emergent adverse events were summarized. Results: Data from 1844 participants were pooled: 149 from a single‐dose randomized trial, 355 from a multi‐dose randomized trial, and 1340 from an open‐label safety and pharmacokinetic study. Most participants from randomized trials continued in open‐label extensions, and pooled data represent >95% of participants exposed to cenobamate. Baseline characteristics and disease and treatment histories were similar across studies. Median duration of cenobamate exposure was 34 months, with a median modal dose of 200 mg/day. Kaplan‐Meier estimates of cumulative cenobamate retention rates were 80% at 1 year and 72% at 2 years. Once participants reached the maintenance phase, retention rates were consistently high in participants receiving ≥100 mg/day cenobamate, and concomitant anti‐seizure medications did not affect long‐term retention. By 2 years, 535 (29%) had actually discontinued cenobamate; the most common reasons for discontinuation were adverse events (37.6%), withdrawal of consent (21.1%), and other (16.8%). Significance: Treatment retention rates provide a proxy measure for long‐term efficacy, safety, tolerability, and adherence. The consistently high retention rates we found suggest that cenobamate may be an effective and well‐tolerated new treatment option for people with drug‐resistant focal seizures. [ABSTRACT FROM AUTHOR]

The article presents information on the revision to the Electroencephalogram (EEG) Guidelines of the American Clinical Neurophsiology Society (ACNS). Topics include the removal of the "Standards of Practice in Clinical Electroencephalography," a summary of the guideline on the minimum technical requirements for performing clinical EEG, and the guidelines for EEG Reporting.

Objective To report tolerability findings and maintenance of seizure control from a pooled analysis of phase I open-label trial OV-1015 ( NCT01079351) and phase III study 13181A ( NCT01128959). Methods Patients receiving a stable oral dosage of carbamazepine were switched to an intravenous ( IV) carbamazepine formulation solubilized in a cyclodextrin matrix (at a 70% dosage conversion) for either a 15- or a 30-min infusion every 6 h for up to 7 days and then switched back. A subset of patients who tolerated 15-min infusions also received 2- to 5-min (rapid) infusions. Assessments included physical and laboratory evaluations, electrocardiography ( ECG) studies, as well as adverse event ( AE) monitoring for tolerability. Convulsion/seizure AE terms and data from seizure diaries were used as proxies for the assessment of consistency of seizure control between formulations. Results Of the 203 patients exposed to IV carbamazepine (30 min, n = 43; 15 min, n = 160), 113 received 149 rapid infusions. During infusion, the most commonly reported AEs (≥5%) were dizziness (19%), somnolence (6%), headache (6%), and blurred vision (5%). IV carbamazepine was not associated with clinically relevant cardiac AEs. The tolerability profile appeared similar between patients who received <1,600 mg/day (n = 174) and ≥1,600 mg/day (n = 29) carbamazepine. Cyclodextrin exposure was not associated with clinically relevant changes in AEs or renal biomarkers. Seizure control was maintained as patients transitioned between oral and IV carbamazepine. Significance IV carbamazepine administered as multiple 30- or 15-min infusions every 6 h, and as a single rapid infusion, was well tolerated as a short-term replacement in adults with epilepsy receiving stable dosages of oral carbamazepine. Infusion site reactions, which were generally mild, were the only unique AEs identified; seizure control was generally unchanged when patients were switching between formulations. [ABSTRACT FROM AUTHOR]

• This clinical practice guideline identified standards with recommendations summarized in Table S1. • Limited high-level evidence addressing standards for LTVEM exist, and further research is needed. • Selected topics for utility of LTVEM exist, although comprehensive criteria addressing minimum standards for performance are needed. • Clinicians, hospital administrators, and insurers benefit from establishing standards for inpatient video-EEG monitoring applied to patient management. The objective of this clinical practice guideline is to provide recommendations on the indications and minimum standards for inpatient long-term video-electroencephalographic monitoring (LTVEM). The Working Group of the International League Against Epilepsy and the International Federation of Clinical Neurophysiology develop guidelines aligned with the Epilepsy Guidelines Task Force. We reviewed published evidence using The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement. We found limited high-level evidence aimed at specific aspects of diagnosis for LTVEM performed to evaluate patients with seizures and nonepileptic events (see Table S1). For classification of evidence, we used the Clinical Practice Guideline Process Manual of the American Academy of Neurology. We formulated recommendations for the indications, technical requirements, and essential practice elements of LTVEM to derive minimum standards used in the evaluation of patients with suspected epilepsy using GRADE (Grading of Recommendations, Assessment, Development, and Evaluation). Further research is needed to obtain evidence about long-term outcome effects of LTVEM and establish its clinical utility. [ABSTRACT FROM AUTHOR]

Summary: The objective of this clinical practice guideline is to provide recommendations on the indications and minimum standards for inpatient long‐term video‐electroencephalographic monitoring (LTVEM). The Working Group of the International League Against Epilepsy and the International Federation of Clinical Neurophysiology develop guidelines aligned with the Epilepsy Guidelines Task Force. We reviewed published evidence using the PRISMA (Preferred Reporting Items for Systematic Review and Meta‐Analysis) statement. We found limited high‐level evidence aimed at specific aspects of diagnosis for LTVEM performed to evaluate patients with seizures and nonepileptic events. For classification of evidence, we used the Clinical Practice Guideline Process Manual of the American Academy of Neurology. We formulated recommendations for the indications, technical requirements, and essential practice elements of LTVEM to derive minimum standards used in the evaluation of patients with suspected epilepsy using GRADE (Grading of Recommendations Assessment, Development, and Evaluation). Further research is needed to obtain evidence about long‐term outcome effects of LTVEM and to establish its clinical utility. [ABSTRACT FROM AUTHOR]

Summary: Objective: Lennox–Gastaut syndrome (LGS) is an epileptic encephalopathy that is often treatment resistant. Efficacy and safety of add‐on cannabidiol (CBD) to treat seizures associated with LGS was demonstrated in two randomized controlled trials (RCTs). Patients who completed the RCTs were invited to enroll in this long‐term open‐label extension (OLE) trial, GWPCARE5 (NCT02224573). We present the final analysis of safety and efficacy outcomes from GWPCARE5. Methods: Patients received plant‐derived highly purified CBD (Epidiolex in the United States; Epidyolex in the European Union; 100 mg/ml oral solution), titrated to a target maintenance dose of 20 mg/kg/day over 2 weeks. Based on response and tolerability, CBD could then be reduced or increased up to 30 mg/kg/day. Results: Of 368 patients with LGS who completed the RCTs, 366 (99.5%) enrolled in this OLE. Median and mean treatment duration were 1090 and 826 days (range = 3–1421), respectively, with a mean modal dose of 24 mg/kg/day. Adverse events (AEs) occurred in 96% of patients, serious AEs in 42%, and AE‐related discontinuations in 12%. Common AEs were convulsion (39%), diarrhea (38%), pyrexia (34%), and somnolence (29%). Fifty‐five (15%) patients experienced liver transaminase elevations more than three times the upper limit of normal; 40 (73%) were taking concomitant valproic acid. Median percent reductions from baseline ranged 48%–71% for drop seizures and 48%–68% for total seizures through 156 weeks. Across all 12‐week visit windows, 87% or more of patients/caregivers reported improvement in the patient's overall condition on the Subject/Caregiver Global Impression of Change scale. Significance: Long‐term add‐on CBD treatment had a similar safety profile as in the original RCTs. Sustained reductions in drop and total seizure frequency were observed for up to 156 weeks, demonstrating long‐term benefits of CBD treatment for patients with LGS. [ABSTRACT FROM AUTHOR]

Visual evaluation of electroencephalogram (EEG) for Interictal Epileptiform Discharges (IEDs) as distinctive biomarkers of epilepsy has various limitations, including time-consuming reviews, steep learning curves, interobserver variability, and the need for specialized experts. The development of an automated IED detector is necessary to provide a faster and reliable diagnosis of epilepsy. In this paper, we propose an automated IED detector based on Convolutional Neural Networks (CNNs). We have evaluated the proposed IED detector on a sizable database of 554 scalp EEG recordings (84 epileptic patients and 461 nonepileptic subjects) recorded at Massachusetts General Hospital (MGH), Boston. The proposed CNN IED detector has achieved superior performance in comparison with conventional methods with a mean cross-validation area under the precision–recall curve (AUPRC) of 0.838 ± 0.040 and false detection rate of 0.2 ± 0.11 per minute for a sensitivity of 80%. We demonstrated the proposed system to be noninferior to 30 neurologists on a dataset from the Medical University of South Carolina (MUSC). Further, we clinically validated the system at National University Hospital (NUH), Singapore, with an agreement accuracy of 81.41% with a clinical expert. Moreover, the proposed system can be applied to EEG recordings with any arbitrary number of channels. [ABSTRACT FROM AUTHOR]

Objective: During the development of cenobamate, an antiseizure medication (ASM) for focal seizures, three cases of drug reaction with eosinophilia and systemic symptoms (DRESS) occurred. To mitigate the rate of DRESS, a start‐low, go‐slow approach was studied in an ongoing, open‐label, multicenter study. Also examined were long‐term safety of cenobamate and a method for managing the pharmacokinetic interaction between cenobamate, a 2C19 inhibitor, and concomitant phenytoin or phenobarbital. Methods: Patients 18‐70 years old with uncontrolled focal seizures taking stable doses of one to three ASMs were enrolled. Cenobamate 12.5 mg/d was initiated and increased at 2‐week intervals to 25, 50, 100, 150, and 200 mg/d. Additional biweekly 50 mg/d increases to 400 mg/d were allowed. During titration, patients taking phenytoin or phenobarbital could not have their cenobamate titration rate or other concomitant ASMs adjusted; phenytoin/phenobarbital doses could be decreased by 25%‐33%. Results: At data cutoff (median treatment duration = 9 months), 1347 patients were enrolled, of whom 269 (20.0%) discontinued, most commonly due to adverse events (n = 137) and consent withdrawn for reason other than adverse event (n = 74); 1339 patients received ≥1 treatment dose (median modal dose = 200 mg). The most common treatment‐emergent adverse events (TEAEs) were somnolence (28.1%), dizziness (23.6%), and fatigue (16.6%). Serious TEAEs occurred in 108 patients (8.1%), most commonly seizure (n = 14), epilepsy (n = 5), and pneumonia, fall, and dizziness (n = 4 each). No cases of DRESS were identified. In the phenytoin/phenobarbital groups, 43.4% (36/114) and 29.7% (11/51) of patients, respectively, had their doses decreased. At the end of titration, mean plasma phenytoin/phenobarbital levels were generally comparable to baseline. Significance: No cases of DRESS were identified in 1339 patients exposed to cenobamate using a start‐low (12.5 mg/d), go‐slow titration approach. Cenobamate was generally well tolerated in the long term, with no new safety issues found. Phenytoin/phenobarbital dose reductions (25%‐33%), when needed during cenobamate titration, maintained stable plasma levels. [ABSTRACT FROM AUTHOR]

More than one third of children with epilepsy have medically intractable seizures. Promising therapies, including targeted neurostimulation and surgery, depend on accurate localization of the epileptogenic zone. Ictal perfusion single-photon emission computed tomography (SPECT) can localize the seizure focus noninvasively, with comparable accuracy to that of invasive EEG. However, multiple factors including seizure dynamics may affect its spatial specificity. Methods: Using subtracted ictal from interictal SPECT and scalp EEG from 118 pediatric epilepsy patients (40 of whom had surgery after the SPECT studies), information theoretic measures of association and advanced statistical models, this study investigated the impact of preictal and ictal brain network dynamics on SPECT focality. Results: Network dynamics significantly impacted the SPECT localization $\sim$ 30 s before to $\sim$ 45 s following ictal onset. Distributed early ictal connectivity changes, indicative of a rapidly evolving seizure, were negatively associated with SPECT focality. Spatially localized connectivity changes later in the seizure, indicating slower seizure propagation, were positively associated with SPECT focality. In the first $\sim$ 60 s of the seizure, significantly higher network connectivity was estimated in an area overlapping with the area of hyperperfusion. Finally, $\sim$ 75% of patients with Engel class 1a/1b outcomes had SPECTs that were concordant with the resected area. Conclusion: Slowly evolving seizures are more likely to be accurately imaged with SPECT, and the identified focus may overlap with brain regions where significant topological changes occur. Significance: Measures of preictal/early ictal network dynamics may help optimize the SPECT localization, leading to improved surgical and neurostimulation outcomes in refractory epilepsy. [ABSTRACT FROM AUTHOR]

Summary: Objective: Patients with Lennox‐Gastaut syndrome (LGS) who completed 1 of 2 randomized, double‐blind, placebo‐controlled trials of add‐on cannabidiol (CBD) (GWPCARE3, NCT02224560 or GWPCARE4, NCT02224690) were invited to enroll in an open‐label extension (OLE) study evaluating the long‐term safety and efficacy of CBD (GWPCARE5, NCT02224573). Herein we present an interim analysis of the safety, efficacy, and patient‐reported outcomes from this trial. Methods: Patients received a pharmaceutical formulation of highly purified CBD oral solution (Epidiolex; 100 mg/mL), titrated from 2.5 to 20 mg/kg/d over a 2‐week titration period, in addition to their existing medications. Doses could be reduced if not tolerated or increased up to 30 mg/kg/d if thought to be of benefit. Results: This interim analysis was based on a November 2016 data cut. Of 368 patients who completed treatment in GWPCARE3 and GWPCARE4, 366 (99.5%) enrolled in the OLE study (GWPCARE5). Median treatment duration was 38 weeks at a mean modal dose of 23 mg/kg/d. Most patients (92.1%) experienced adverse events (AEs), primarily of mild (32.5%) or moderate (43.4%) severity. The most common AEs were diarrhea (26.8%), somnolence (23.5%), and convulsion (21.3%). Thirty‐five patients (9.6%) discontinued treatment due to AEs. Liver transaminase elevations were reported in 37 patients (10.1%), of whom 29 were receiving concomitant valproic acid; 34 cases resolved spontaneously or with dose modification of CBD or concomitant medication. Median reduction from baseline in drop seizure frequency (quantified monthly over 12‐week periods) ranged from 48% to 60% through week 48. Median reduction in monthly total seizure frequency ranged from 48% to 57% across all 12‐week periods through week 48. Eighty‐eight percent of patients/caregivers reported an improvement in the patient's overall condition per the Subject/Caregiver Global Impression of Change scale. Significance: In this study, long‐term add‐on CBD treatment had an acceptable safety profile in patients with LGS and led to sustained reductions in seizures. [ABSTRACT FROM AUTHOR]

Objective: The optimal treatment of nonconvulsive seizures in critically ill patients is uncertain. We evaluated the comparative effectiveness of the antiseizure drugs lacosamide (LCM) and fosphenytoin (fPHT) in this population.Methods: The TRENdS (Treatment of Recurrent Electrographic Nonconvulsive Seizures) study was a noninferiority, prospective, multicenter, randomized treatment trial of patients diagnosed with nonconvulsive seizures (NCSs) by continuous electroencephalography (cEEG). Treatment was randomized to intravenous (IV) LCM 400mg or IV fPHT 20mg phenytoin equivalents/kg. The primary endpoint was absence of electrographic seizures for 24 hours as determined by 1 blinded EEG reviewer. The frequency with which NCS control was achieved in each arm was compared, and the 90% confidence interval (CI) was determined. Noninferiority of LCM to fPHT was to be concluded if the lower bound of the CI for relative risk was >0.8.Results: Seventy-four subjects were enrolled (37 LCM, 37 fPHT) between August 21, 2012 and December 20, 2013. The mean age was 63.6 years; 38 were women. Seizures were controlled in 19 of 30 (63.3%) subjects in the LCM arm and 16 of 32 (50%) subjects in the fPHT arm. LCM was noninferior to fPHT (p = 0.02), with a risk ratio of 1.27 (90% CI = 0.88-1.83). Treatment emergent adverse events (TEAEs) were similar in both arms, occurring in 9 of 35 (25.7%) LCM and 9 of 37 (24.3%) fPHT subjects (p = 1.0).Interpretation: LCM was noninferior to fPHT in controlling NCS, and TEAEs were comparable. LCM can be considered an alternative to fPHT in the treatment of NCSs detected on cEEG. Ann Neurol 2018;83:1174-1185. [ABSTRACT FROM AUTHOR]

Objective The presence of interictal epileptiform discharges (IED) in the electroencephalogram (EEG) is a key finding in the medical workup of a patient with suspected epilepsy. However, inter-rater agreement (IRA) regarding the presence of IED is imperfect, leading to incorrect and delayed diagnoses. An improved understanding of which IED attributes mediate expert IRA might help in developing automatic methods for IED detection able to emulate the abilities of experts. Therefore, using a set of IED scored by a large number of experts, we set out to determine which attributes of IED predict expert agreement regarding the presence of IED. Methods IED were annotated on a 5-point scale by 18 clinical neurophysiologists within 200 30-s EEG segments from recordings of 200 patients. 5538 signal analysis features were extracted from the waveforms, including wavelet coefficients, morphological features, signal energy, nonlinear energy operator response, electrode location, and spectrogram features. Feature selection was performed by applying elastic net regression and support vector regression (SVR) was applied to predict expert opinion, with and without the feature selection procedure and with and without several types of signal normalization. Results Multiple types of features were useful for predicting expert annotations, but particular types of wavelet features performed best. Local EEG normalization also enhanced best model performance. As the size of the group of EEGers used to train the models was increased, the performance of the models leveled off at a group size of around 11. Conclusions The features that best predict inter-rater agreement among experts regarding the presence of IED are wavelet features, using locally standardized EEG. Our models for predicting expert opinion based on EEGer’s scores perform best with a large group of EEGers (more than 10). Significance By examining a large group of EEG signal analysis features we found that wavelet features with certain wavelet basis functions performed best to identify IEDs. Local normalization also improves predictability, suggesting the importance of IED morphology over amplitude-based features. Although most IED detection studies in the past have used opinion from three or fewer experts, our study suggests a “wisdom of the crowd” effect, such that pooling over a larger number of expert opinions produces a better correlation between expert opinion and objectively quantifiable features of the EEG. [ABSTRACT FROM AUTHOR]

• There is a staggering shortage of neurology expertise in both high and low-income countries. • Establishing a correct diagnosis of epilepsy requires neurology expertise and, in some cases, subspecialty interpretation of the electroencephalogram (EEG). • A consecutive analysis of 205 patients who underwent EEG was performed and identified several easily identifiable clinical features that predict a diagnosis of epilepsy. • Important factors were included in a clinical decision tool, which demonstrated strong test performance for diagnosing epilepsy, and could be used by non-experts. • For indeterminate cases, novel artificially intelligent EEG analysis (AI-EEG) was applied: positive AI-EEG helped resolve diagnostic uncertainty. To construct a tool for non-experts to calculate the probability of epilepsy based on easily obtained clinical information combined with an artificial intelligence readout of the electroencephalogram (AI-EEG). We performed a chart review of 205 consecutive patients aged 18 years or older who underwent routine EEG. We created a point system to calculate the pre-EEG probability of epilepsy in a pilot study cohort. We also computed a post-test probability based on AI-EEG results. One hundred and four (50.7%) patients were female, the mean age was 46 years, and 110 (53.7%) were diagnosed with epilepsy. Findings favoring epilepsy included developmental delay (12.6% vs 1.1%), prior neurological injury (51.4% vs 30.9%), childhood febrile seizures (4.6% vs 0.0%), postictal confusion (43.6% vs 20.0%), and witnessed convulsions (63.6% vs 21.1%); findings favoring alternative diagnoses were lightheadedness (3.6% vs 15.8%) or onset after prolonged sitting or standing (0.9% vs 7.4%). The final point system included 6 predictors: Presyncope (−3 points), cardiac history (−1), convulsion or forced head turn (+3), neurological disease history (+2), multiple prior spells (+1), postictal confusion (+2). Total scores of ≤1 point predicted <5% probability of epilepsy, while cumulative scores ≥7 predicted >95%. The model showed excellent discrimination (AUROC: 0.86). A positive AI-EEG substantially increases the probability of epilepsy. The impact is greatest when the pre-EEG probability is near 30%. A decision tool using a small number of historical clinical features accurately predicts the probability of epilepsy. In indeterminate cases, AI-assisted EEG helps resolve uncertainty. This tool holds promise for use by healthcare workers without specialty epilepsy training if validated in an independent cohort. [ABSTRACT FROM AUTHOR]

Objective Ictal SPECT is promising for accurate non-invasive localization of the epileptogenic brain tissue in focal epilepsies. However, high quality ictal scans require meticulous attention to the seizure onset. In a relatively large cohort of pediatric patients, this study investigated the impact of the timing of radiotracer injection, MRI findings and seizure characteristics on ictal SPECT localizations, and the relationship between concordance of ictal SPECT, scalp EEG and resected area with seizure freedom following epilepsy surgery. Methods Scalp EEG and ictal SPECT studies from 95 patients (48 males and 47 females, median age = 11 years, (25th, 75th) quartiles = (6.0, 14.75) years) with pharmacoresistant focal epilepsy and no prior epilepsy surgery were reviewed. The ictal SPECT result was examined as a function of the radiotracer injection delay, seizure duration, epilepsy etiology, cerebral lobe of seizure onset identified by EEG and MRI findings. Thirty two patients who later underwent epilepsy surgery had postoperative seizure freedom data at <1, 6 and 12 months. Results Sixty patients (63.2%) had positive SPECT localizations − 51 with a hyperperfused region that was concordant with the cerebral lobe of seizure origin identified by EEG and 9 with discordant localizations. Of these, 35 patients (58.3%) had temporal and 25 (41.7%) had extratemporal seizures. The ictal SPECT result was significantly correlated with the injection delay (p < 0.01) and cerebral lobe of seizure onset (specifically frontal versus temporal; p = 0.02) but not MRI findings (p = 0.33), epilepsy etiology (p ≥ 0.27) or seizure duration (p = 0.20). Concordance of SPECT, scalp EEG and resected area was significantly correlated with seizure freedom at 6 months after surgery (p = 0.04). Significance Ictal SPECT holds promise as a powerful source imaging tool for presurgical planning in pediatric epilepsies. To optimize the SPECT result the radiotracer injection delay should be minimized to ≤25 s, although the origin of seizure onset (specifically temporal versus frontal) also significantly impacts the localization. [ABSTRACT FROM AUTHOR]

Objective The three important questions in video-EEG monitoring are (1) whether it is productive to monitor patients with low outpatient seizure frequency, (2) whether rapid down-titration of antiepileptic drugs (AEDs) during EMU admission helps generate more recorded seizures, and (3) how long a patient who has not yet had a seizure should be monitored in the EMU. This study aimed to answer these three questions. Methods Preadmission seizure frequency, times of AED administration, and times of seizure occurrence were collected on all adult patients admitted to the EMU at the Medical University of South Carolina (MUSC) between 2012 and 2014 — a total of 439 patients. The correlations between EMU seizure frequency and both (1) preadmission seizure frequency and (2) rate of antiepileptic drug (AED) down-titration were evaluated. The time of occurrence of seizures was evaluated. Results There was no correlation between patient-reported outpatient seizure frequency and EMU seizure frequency. In patients who were tapered off AEDs during monitoring, the rate of AED taper correlated with the EMU seizure frequency. Patients whose AEDs were more quickly tapered had higher EMU seizure frequencies. In order to record a first event in patients of unknown seizure type, approximately 3.5 days of EMU monitoring was required. Significance Clinicians should not hesitate to admit patients with low preadmission seizure frequency to the EMU since many of these patients will have a seizure during monitoring. Faster AED down-titration in the EMU increases EMU seizure frequency. In patients who have not yet had a seizure in the EMU, monitoring should continue for at least four days. [ABSTRACT FROM AUTHOR]

The article presents the guideline of the American Clinical Neurophysiology Society (ACNS) on the minimum technical requirements for performing clinical electroencephalography (EEG). Topics include the use of digital EEG equipment for recording, utilization of subdermal needle electrodes (SNE) or wire electrodes (SWE) for prolonged EEG recordings, and the importance of calibration in every EEG recording.

Objectives Generalized periodic discharges (GPDs) are associated with nonconvulsive seizures. Triphasic waves (TWs), a subtype of GPDs, have been described in relation to metabolic encephalopathy and not felt to be associated with seizures. We sought to establish the consistency of use of this descriptive term and its association with seizures. Methods 11 experts in continuous EEG monitoring scored 20 cEEG samples containing GPDs using Standardized Critical Care EEG Terminology. In the absence of patient information, the inter-rater agreement (IRA) for EEG descriptors including TWs was assessed along with raters’ clinical EEG interpretation and compared with actual patient information. Results The IRA for ‘generalized’ and ‘periodic’ was near-perfect (kappa = 0.81), but fair for ‘triphasic’ (kappa = 0.33). Patients with TWs were as likely to develop seizures as those without (25% vs 26%, N.S.) and surprisingly, patients with TWs were less likely to have toxic-metabolic encephalopathy than those without TWs (55% vs 79%, p < 0.01). Conclusions While IRA for the terms “generalized” and “periodic” is high, it is only fair for TWs. EEG interpreted as TWs presents similar risk for seizures as GPDs without triphasic appearance. GPDs are commonly associated with metabolic encephalopathy, but ‘triphasic’ appearance is not predictive. Significance Conventional association of ‘triphasic waves’ with specific clinical conditions may lead to inaccurate EEG interpretation. [ABSTRACT FROM AUTHOR]

Purpose: Medial temporal epilepsy (MTLE) is associated with extrahippocampal brain atrophy. The mechanisms underlying brain damage in MTLE are unknown. Seizures may lead to neuronal damage, but another possible explanation is deafferentation from loss of hippocampal connections. This study aimed to investigate the relationship between hippocampal deafferentation and brain atrophy in MTLE. Methods: Three different MRI studies were performed involving 23 patients with unilateral MTLE (8 left and 15 right) and 34 healthy controls: (1) voxel-based morphometry (VBM), (2) diffusion tensor imaging (DTI) and (3) probabilistic tractography (PT). VBM was employed to define differences in regional gray matter volume (GMV) between controls and patients. Voxel-wise analyses of DTI evaluated differences in fractional anisotropy (FA), mean diffusivity (MD) and hippocampal PT. Z-scores were computed for regions-of-interest (ROI) GMV and peri-hippocampal FA and MD (to quantify hippocampal fiber integrity). The relationship between hippocampal deafferentation and regional GMV was investigated through the association between ROI Z scores and hippocampal fiber integrity. Results: Patients with MTLE exhibited a significant reduction in GMV and FA in perihippocampal and limbic areas. There was a decrease in hippocampal PT in patients with MTLE in limbic areas. A significant relationship between loss of hippocampal connections and regional GMV atrophy was found involving the putamen, pallidum, middle and inferior temporal areas, amygdala and ceberellar hemisphere. Discussion: There is a relationship between hippocampal disconnection and regional brain atrophy in MTLE. These results indicate that hippocampal deafferentation plays a contributory role in extrahippocampal brain damage in MTLE. [ABSTRACT FROM AUTHOR]

To assess the efficacy, safety, and tolerability of the investigational drug carisbamate as adjunctive treatment for partial-onset seizures (POS). Two identical, randomized, placebo-controlled, double-blind studies were conducted in adults with POS uncontrolled for ≥1 year. Therapy-refractory epilepsy patients (≥16 years) remained on stable doses of prescribed antiepileptic drugs (≤2) for an 8-week prospective baseline phase and were then randomized (1:1:1) to carisbamate 200 mg/day, carisbamate 400 mg/day, or placebo, for a 12-week double-blind phase. Primary efficacy end points were percent reduction in seizure frequency and responder rate (patients with ≥50% reduction in POS frequency) during the double-blind phase compared with the prospective baseline phase. Of the 565 patients randomized in study 1, 93% completed the study; of the 562 randomized in study 2, 94% completed the study. Patient characteristics were similar across both studies and treatment arms: mean age, 35 years (study 1, range 16–75 years) and 36 years (study 2, range 16–74 years); approximately 50% were men. Treatment with carisbamate 400 mg/day resulted in significant improvement (p < 0.01) in both efficacy measures compared with placebo in study 1 but not in study 2. Carisbamate 200 mg/day did not differ statistically from placebo in either study. Among the most common treatment-emergent adverse events (≥5% in any group), those with an incidence exceeding placebo (≥3%) were dizziness (400 mg/day group) and somnolence. Carisbamate 400 mg/day was effective in patients with refractory partial-onset seizures in one of these global studies. More than 200 mg/day of carisbamate is required for efficacy. Carisbamate was well-tolerated in both studies. [ABSTRACT FROM AUTHOR]

• Collected 88,341 labels regarding seizures and Ictal Interictal Injury Continuum (IIIC) patterns for 9,808 EEG segments from 25 clinical experts. • Compared a wide variety of Active Learning (AL) schemes for accelerating the collection of expert labels for seizure and IIIC patterns. • Developed a method based on embedding maps to create high quality pseudo labels to enhance the training of machine learning models. • Utilizing the labels and pseudo-labels obtained, we trained a model approaching expert-level performance across all pattern categories. 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. 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). 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. Our results provide guidance regarding the use of AL to efficiently label large EEG datasets in critically ill patients. [ABSTRACT FROM AUTHOR]