Recent advances in clinical electroencephalography.

PURPOSE OF REVIEW: Clinical electroencephalography (EEG) is a conservative medical field. This explains likely the significant gap between clinical practice and new research developments. This narrative review discusses possible causes of this discrepancy and how to circumvent them. More specifically, we summarize recent advances in three applications of clinical EEG: source imaging (ESI), high-frequency oscillations (HFOs) and EEG in critically ill patients. RECENT FINDINGS: Recently published studies on ESI provide further evidence for the accuracy and clinical utility of this method in the multimodal presurgical evaluation of patients with drug-resistant focal epilepsy, and opened new possibilities for further improvement of the accuracy. HFOs have received much attention as a novel biomarker in epilepsy. However, recent studies questioned their clinical utility at the level of individual patients. We discuss the impediments, show up possible solutions and highlight the perspectives of future research in this field. EEG in the ICU has been one of the major driving forces in the development of clinical EEG. We review the achievements and the limitations in this field. SUMMARY: This review will promote clinical implementation of recent advances in EEG, in the fields of ESI, HFOs and EEG in the intensive care.

Automated detection of tonic seizures using wearable movement sensor and artificial neural network.

Although several validated wearable devices are available for detection of generalized tonic-clonic seizures, automated detection of tonic seizures is still a challenge. In this phase 1 study, we report development and validation of an artificial neural network (ANN) model for automated detection of tonic seizures with visible clinical manifestation using a wearable wristband movement sensor (accelerometer and gyroscope). The dataset prospectively recorded for this study included 70 tonic seizures from 15 patients (seven males, age 3-46 years, median = 19 years). We trained an ANN model to detect tonic seizures. The independent test dataset comprised nocturnal recordings, including 10 tonic seizures from three patients and additional (distractor) data from three subjects without seizures. The ANN model detected nocturnal tonic seizures with visible clinical manifestation with a sensitivity of 100% (95% confidence interval = 69%-100%) and with an average false alarm rate of .16/night. The mean detection latency was 14.1 s (median = 10 s), with a maximum of 47 s. These data suggest that nocturnal tonic seizures can be reliably detected with movement sensors using ANN. Large-scale, multicenter prospective (phase 3) trials are needed to provide compelling evidence for the clinical utility of this device and detection algorithm.

Focal electroclinical features in generalized tonic-clonic seizures: Decision flowchart for a diagnostic challenge.

OBJECTIVE: Bilateral tonic-clonic seizures with focal semiology or focal interictal electroencephalography (EEG) can occur in both focal and generalized epilepsy types, leading to diagnostic errors and inappropriate therapy. We investigated the prevalence and prognostic values of focal features in patients with idiopathic generalized epilepsy (IGE), and we propose a decision flowchart to distinguish between focal and generalized epilepsy in patients with bilateral tonic-clonic seizures and focal EEG or semiology. METHODS: We retrospectively analyzed video-EEG recordings of 101 bilateral tonic-clonic seizures from 60 patients (18 with IGE, 42 with focal epilepsy). Diagnosis and therapeutic response were extracted after ≥1-year follow-up. The decision flowchart was based on previous observations and assessed concordance between interictal and ictal EEG. RESULTS: Focal semiology in IGE was observed in 75% of seizures and 77.8% of patients, most often corresponding to forced head version (66.7%). In patients with multiple seizures, direction of head version was consistent across seizures. Focal interictal epileptiform discharges (IEDs) were observed in 61.1% of patients with IGE, whereas focal ictal EEG onset only occurred in 13% of seizures and 16.7% of patients. However, later during the seizures, a reproducible pattern of 7-Hz lateralized ictal rhythm was observed in 56% of seizures, associated with contralateral head version. We did not find correlation between presence of focal features and therapeutic response in IGE patients. Our decision flowchart distinguished between focal and generalized epilepsy in patients with bilateral tonic-clonic seizures and focal features with an accuracy of 96.6%. SIGNIFICANCE: Focal semiology associated with bilateral tonic-clonic seizures and focal IEDs are common features in patients with IGE, but focal ictal EEG onset is rare. None of these focal findings appears to influence therapeutic response. By assessing the concordance between interictal and ictal EEG findings, one can accurately distinguish between focal and generalized epilepsies.

Investigating current clinical opinions in stereoelectroencephalography-informed epilepsy surgery.

OBJECTIVE: Stereoelectroencephalography (SEEG) is increasingly utilized worldwide in epilepsy surgery planning. International guidelines for SEEG terminology and interpretation are yet to be proposed. There are worldwide differences in SEEG definitions, application of features in epilepsy surgery planning, and interpretation of surgical outcomes. This hinders the clinical interpretation of SEEG findings and collaborative research. We aimed to assess the global perspectives on SEEG terminology, differences in the application of presurgical features, and variability in the interpretation of surgery outcome scores, and analyze how clinical expert demographics influenced these opinions. METHODS: We assessed the practices and opinions of epileptologists with specialized training in SEEG using a survey. Data were qualitatively analyzed, and subgroups were examined based on geographical regions and years of experience. Primary outcomes included opinions on SEEG terminology, features used for epilepsy surgery, and interpretation of outcome scores. Additionally, we conducted a multilevel regression and poststratification analysis to characterize the nonresponders. RESULTS: A total of 321 expert responses from 39 countries were analyzed. We observed substantial differences in terminology, practices, and use of presurgical features across geographical regions and SEEG expertise levels. The majority of experts (220, 68.5%) favored the Lüders epileptogenic zone definition. Experts were divided regarding the seizure onset zone definition, with 179 (55.8%) favoring onset alone and 135 (42.1%) supporting onset and early propagation. In terms of presurgical SEEG features, a clear preference was found for ictal features over interictal features. Seizure onset patterns were identified as the most important features by 265 experts (82.5%). We found similar trends after correcting for nonresponders using regression analysis. SIGNIFICANCE: This study underscores the need for standardized terminology, interpretation, and outcome assessment in SEEG-informed epilepsy surgery. By highlighting the diverse perspectives and practices in SEEG, this research lays a solid foundation for developing globally accepted terminology and guidelines, advancing the field toward improved communication and standardization in epilepsy surgery.

Prediction tools and risk stratification in epilepsy surgery.

OBJECTIVE: This study was undertaken to conduct external validation of previously published epilepsy surgery prediction tools using a large independent multicenter dataset and to assess whether these tools can stratify patients for being operated on and for becoming free of disabling seizures (International League Against Epilepsy stage 1 and 2). METHODS: We analyzed a dataset of 1562 patients, not used for tool development. We applied two scales: Epilepsy Surgery Grading Scale (ESGS) and Seizure Freedom Score (SFS); and two versions of Epilepsy Surgery Nomogram (ESN): the original version and the modified version, which included electroencephalographic data. For the ESNs, we used calibration curves and concordance indexes. We stratified the patients into three tiers for assessing the chances of attaining freedom from disabling seizures after surgery: high (ESGS = 1, SFS = 3-4, ESNs > 70%), moderate (ESGS = 2, SFS = 2, ESNs = 40%-70%), and low (ESGS = 2, SFS = 0-1, ESNs < 40%). We compared the three tiers as stratified by these tools, concerning the proportion of patients who were operated on, and for the proportion of patients who became free of disabling seizures. RESULTS: The concordance indexes for the various versions of the nomograms were between .56 and .69. Both scales (ESGS, SFS) and nomograms accurately stratified the patients for becoming free of disabling seizures, with significant differences among the three tiers (p < .05). In addition, ESGS and the modified ESN accurately stratified the patients for having been offered surgery, with significant difference among the three tiers (p < .05). SIGNIFICANCE: ESGS and the modified ESN (at thresholds of 40% and 70%) stratify patients undergoing presurgical evaluation into three tiers, with high, moderate, and low chance for favorable outcome, with significant differences between the groups concerning having surgery and becoming free of disabling seizures. Stratifying patients for epilepsy surgery has the potential to help select the optimal candidates in underprivileged areas and better allocate resources in developed countries.

Generalizability of electroencephalographic interpretation using artificial intelligence: An external validation study.

OBJECTIVE: The automated interpretation of clinical electroencephalograms (EEGs) using artificial intelligence (AI) holds the potential to bridge the treatment gap in resource-limited settings and reduce the workload at specialized centers. However, to facilitate broad clinical implementation, it is essential to establish generalizability across diverse patient populations and equipment. We assessed whether SCORE-AI demonstrates diagnostic accuracy comparable to that of experts when applied to a geographically different patient population, recorded with distinct EEG equipment and technical settings. METHODS: We assessed the diagnostic accuracy of a "fixed-and-frozen" AI model, using an independent dataset and external gold standard, and benchmarked it against three experts blinded to all other data. The dataset comprised 50% normal and 50% abnormal routine EEGs, equally distributed among the four major classes of EEG abnormalities (focal epileptiform, generalized epileptiform, focal nonepileptiform, and diffuse nonepileptiform). To assess diagnostic accuracy, we computed sensitivity, specificity, and accuracy of the AI model and the experts against the external gold standard. RESULTS: We analyzed EEGs from 104 patients (64 females, median age = 38.6 [range = 16-91] years). SCORE-AI performed equally well compared to the experts, with an overall accuracy of 92% (95% confidence interval [CI] = 90%-94%) versus 94% (95% CI = 92%-96%). There was no significant difference between SCORE-AI and the experts for any metric or category. SCORE-AI performed well independently of the vigilance state (false classification during awake: 5/41 [12.2%], false classification during sleep: 2/11 [18.2%]; p = .63) and normal variants (false classification in presence of normal variants: 4/14 [28.6%], false classification in absence of normal variants: 3/38 [7.9%]; p = .07). SIGNIFICANCE: SCORE-AI achieved diagnostic performance equal to human experts in an EEG dataset independent of the development dataset, in a geographically distinct patient population, recorded with different equipment and technical settings than the development dataset.

Grading system for assessing the confidence in the epileptogenic zone reported in published studies: A Delphi consensus study.

OBJECTIVE: This study was undertaken to develop a standardized grading system based on expert consensus for evaluating the level of confidence in the localization of the epileptogenic zone (EZ) as reported in published studies, to harmonize and facilitate systematic reviews in the field of epilepsy surgery. METHODS: We conducted a Delphi study involving 22 experts from 18 countries, who were asked to rate their level of confidence in the localization of the EZ for various theoretical clinical scenarios, using different scales. Information provided in these scenarios included one or several of the following data: magnetic resonance imaging (MRI) findings, invasive electroencephalography summary, and postoperative seizure outcome. RESULTS: The first explorative phase showed an overall interrater agreement of .347, pointing to large heterogeneity among experts' assessments, with only 17% of the 42 proposed scenarios associated with a substantial level of agreement. A majority showed preferences for the simpler scale and single-item scenarios. The successive Delphi voting phases resulted in a majority consensus across experts, with more than two thirds of respondents agreeing on the rating of each of the tested single-item scenarios. High or very high levels of confidence were ascribed to patients with either an Engel class I or class IA postoperative seizure outcome, a well-delineated EZ according to all available invasive EEG (iEEG) data, or a well-delineated focal epileptogenic lesion on MRI. MRI signs of hippocampal sclerosis or atrophy were associated with a moderate level of confidence, whereas a low level was ascribed to other MRI findings, a poorly delineated EZ according to iEEG data, or an Engel class II-IV postoperative seizure outcome. SIGNIFICANCE: The proposed grading system, based on an expert consensus, provides a simple framework to rate the level of confidence in the EZ reported in published studies in a structured and harmonized way, offering an opportunity to facilitate and increase the quality of systematic reviews and guidelines in the field of epilepsy surgery.

Automated detection of focal seizures using subcutaneously implanted electrocardiographic device: A proof-of-concept study.

Phase 2 studies showed that focal seizures could be detected by algorithms using heart rate variability (HRV) in patients with marked autonomic ictal changes. However, wearable surface electrocardiographic (ECG) devices use electrode patches that need to be changed often and may cause skin irritation. We report the first study of automated seizure detection using a subcutaneously implantable cardiac monitor (ICM; Confirm Rx, Abbott). For this proof-of-concept (phase 1) study, we recruited six patients admitted to long-term video-electroencephalographic monitoring. Fifteen-minute epochs of ECG signals were saved for each seizure and for control (nonseizure) epochs in the epilepsy monitoring unit (EMU) and in the patients' home environment (1-8 months). We analyzed the ICM signals offline, using a previously developed HRV algorithm. Thirteen seizures were recorded in the EMU, and 41 seizures were recorded in the home-monitoring period. The algorithm accurately identified 50 of 54 focal seizures (sensitivity = 92.6%, 95% confidence interval [CI] = 85.6%-99.6%). Twelve of the 13 seizures in the EMU were detected (sensitivity = 92.3%, 95% CI = 77.2%-100%), and 38 of the 41 seizures in the out-of-hospital setting were detected (sensitivity = 92.7%, 95% CI = 84.7%-100%). Four false detections were found in the 141 control (nonseizure) epochs (false alarm rate = 2.7/24 h). Our results suggest that automated seizure detection using a long-term, subcutaneous ICM device is feasible and accurate in patients with focal seizures and autonomic ictal changes.

Duration of epileptic seizure types: A data-driven approach.

OBJECTIVE: To determine the duration of epileptic seizure types in patients who did not undergo withdrawal of antiseizure medication. METHODS: From a large, structured database of 11 919 consecutive, routine video-electroencephalograpy (EEG) recordings, labeled using the SCORE (Standardized Computer-Based Organized Reporting of EEG) system, we extracted and analyzed 2742 seizures. For each seizure type we determined median duration and range after removal of outliers (2.5-97.5 percentile). We used surface electromyography (EMG) for accurate measurement of short motor seizures. RESULTS: Myoclonic seizures last <150 ms, epileptic spasms 0.4-2 s, tonic seizures 1.5-36 s, atonic seizures 0.1-12,5 s, when measured using surface EMG. Generalized clonic seizures last 1-24 s. Typical absence seizures are rarely longer than 30 s (2.75-26.5 s) and atypical absences last 2-100 s. In our patients, the duration of focal aware (median: 27 s; 1.25-166 s) and impaired awareness seizures (median: 42.5 s; 9.5-271 s) was shorter than reported previously in patients undergoing withdrawal of antiseizure medication. All focal seizures terminated within 10 min. Median duration of generalized tonic-clonic seizures was 79.5 s (57-102 s) and of focal-to-bilateral tonic-clonic seizures was 103.5 (77.5-237 s). All tonic-clonic seizures terminated within 5 min. SIGNIFICANCE: This comprehensive list of seizure durations provides important information for characterizing seizures and diagnosing patients with epilepsy. The upper limits of seizure durations are helpful in early recognition of imminent status epilepticus.

Diagnosing nonconvulsive status epilepticus: Defining electroencephalographic and clinical response to diagnostic intravenous antiseizure medication trials.

OBJECTIVE: The Salzburg criteria for nonconvulsive status epilepticus (NCSE) and the American Clinical Neurophysiology Society (ACNS) Standardized Critical Care EEG Terminology 2021 include a diagnostic trial with intravenous (IV) antiseizure medications (ASMs) to assess electroencephalographic (EEG) and clinical response as a diagnostic criterion for definite NCSE and possible NCSE. However, how to perform this diagnostic test and assessing the EEG and clinical responses have not been operationally defined. METHODS: We performed a Delphi process involving six experts to standardize the diagnostic administration of IV ASM and propose operational criteria for EEG and clinical response. RESULTS: Either benzodiazepines (BZDs) or non-BZD ASMs can be used as first choice for a diagnostic IV ASM trial. However, non-BZDs should be considered in patients who already have impaired alertness or are at risk of respiratory depression. Levetiracetam, valproate, lacosamide, brivaracetam, or (if the only feasible drug) fosphenytoin or phenobarbital were deemed appropriate for a diagnostic IV trial. The starting dose should be approximately two thirds to three quarters of the full loading dose recommended for treatment of status epilepticus, with an additional smaller dose if needed. ASMs should be administered during EEG recording under supervision. A monitoring time of at least 15 min is recommended. If there is no response, a second trial with another non-BDZ or BDZs may be considered. A positive EEG response is defined as the resolution of the ictal-interictal continuum pattern for at least three times the longest previously observed spontaneous interval of resolution (if any), but minimum of one continuous minute. For a clinical response, physicians should use a standardized examination before and after IV ASM administration. We suggest a definite time-locked improvement in a focal deficit or at least one-step improvement on a new dedicated one-domain 10-level NCSE response scale. SIGNIFICANCE: The proposed standardized approach of a diagnostic IV ASM trial further refines the ACNS and Salzburg diagnostic criteria for NCSE.

Artificial intelligence in epilepsy phenotyping.

Artificial intelligence (AI) allows data analysis and integration at an unprecedented granularity and scale. Here we review the technological advances, challenges, and future perspectives of using AI for electro-clinical phenotyping of animal models and patients with epilepsy. In translational research, AI models accurately identify behavioral states in animal models of epilepsy, allowing identification of correlations between neural activity and interictal and ictal behavior. Clinical applications of AI-based automated and semi-automated analysis of audio and video recordings of people with epilepsy, allow significant data reduction and reliable detection and classification of major motor seizures. AI models can accurately identify electrographic biomarkers of epilepsy, such as spikes, high-frequency oscillations, and seizure patterns. Integrating AI analysis of electroencephalographic, clinical, and behavioral data will contribute to optimizing therapy for patients with epilepsy.

Added value of advanced workup after the first seizure: A 7-year cohort study.

OBJECTIVE: This study was undertaken to establish whether advanced workup including long-term electroencephalography (LT-EEG) and brain magnetic resonance imaging (MRI) provides an additional yield for the diagnosis of new onset epilepsy (NOE) in patients presenting with a first seizure event (FSE). METHODS: In this population-based study, all adult (≥16 years) patients presenting with FSE in the emergency department (ED) between March 1, 2010 and March 1, 2017 were assessed. Patients with obvious nonepileptic or acute symptomatic seizures were excluded. Routine EEG, LT-EEG, brain computed tomography (CT), and brain MRI were performed as part of the initial workup. These examinations' sensitivity and specificity were calculated on the basis of the final diagnosis after 2 years, along with the added value of advanced workup (MRI and LT-EEG) over routine workup (routine EEG and CT). RESULTS: Of the 1010 patients presenting with FSE in the ED, a definite diagnosis of NOE was obtained for 501 patients (49.6%). Sensitivity of LT-EEG was higher than that of routine EEG (54.39% vs. 25.5%, p < .001). Similarly, sensitivity of MRI was higher than that of CT (67.98% vs. 54.72%, p = .009). Brain MRI showed epileptogenic lesions in an additional 32% compared to brain CT. If only MRI and LT-EEG were considered, five would have been incorrectly diagnosed as nonepileptic (5/100, 5%) compared to patients with routine EEG and MRI (25/100, 25%, p = .0001). In patients with all four examinations, advanced workup provided an overall additional yield of 50% compared to routine workup. SIGNIFICANCE: Our results demonstrate the remarkable added value of the advanced workup launched already in the ED for the diagnosis of NOE versus nonepileptic causes of seizure mimickers. Our findings suggest the benefit of first-seizure tracks or even units with overnight EEG, similar to stroke units, activated upon admission in the ED.

Routine and sleep EEG: Minimum recording standards of the International Federation of Clinical Neurophysiology and the International League Against Epilepsy.

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.

Non-electroencephalogram-based seizure detection devices: State of the art and future perspectives.

INTRODUCTION AND PURPOSE: The continuously expanding research and development of wearable devices for automated seizure detection in epilepsy uses mostly non-invasive technology. Real-time alarms, triggered by seizure detection devices, are needed for safety and prevention to decrease seizure-related morbidity and mortality, as well as objective quantification of seizure frequency and severity. Our review strives to provide a state-of-the-art on automated seizure detection using non-invasive wearable devices in an ambulatory (home) environment and to highlight the prospects for future research. METHODS: A joint working group of the International League Against Epilepsy (ILAE) and the International Federation of Clinical Neurophysiology (IFCN) recently published a clinical practice guideline on automated seizure detection using wearable devices. We updated the systematic literature search for the period since the last search by the joint working group. We selected studies qualifying minimally as phase-2 clinical validation trials, in accordance with standards for testing and validation of seizure detection devices. RESULTS: High-level evidence (phases 3 and 4) is available only for the detection of tonic-clonic seizures and major motor seizures when using wearable devices based on accelerometry, surface electromyography (EMG), or a multimodal device combining accelerometry and heart rate. The reported sensitivity of these devices is 79.4-96%, with a false alarm rate of 0.20-1.92 per 24 hours (0-0.03 per night). A single phase-3 study validated the detection of absence seizures using a single-channel wearable EEG device. Two phase-4 studies showed overall user satisfaction with wearable seizure detection devices, which helped decrease injuries related to tonic-clonic seizures. Overall satisfaction, perceived sensitivity, and improvement in quality-of-life were significantly higher for validated devices. CONCLUSIONS: Among the vast number of studies published on seizure detection devices, most are strongly affected by potential bias, providing a too-optimistic perspective. By applying the standards for clinical validation studies, potential bias can be reduced, and the quality of a continuously growing number of studies in this field can be assessed and compared. The ILAE-IFCN clinical practice guideline on automated seizure detection using wearable devices recommends using clinically validated wearable devices for automated detection of tonic-clonic seizures when significant safety concerns exist. The studies published after the guideline was issued only provide incremental knowledge and would not change the current recommendations.

Pitfalls in scalp EEG: Current obstacles and future directions.

Although electroencephalography (EEG) serves a critical role in the evaluation and management of seizure disorders, it is commonly misinterpreted, resulting in avoidable medical, social, and financial burdens to patients and health care systems. Overinterpretation of sharply contoured transient waveforms as being representative of interictal epileptiform abnormalities lies at the core of this problem. However, the magnitude of these errors is amplified by the high prevalence of paroxysmal events exhibited in clinical practice that compel investigation with EEG. Neurology training programs, which vary considerably both in the degree of exposure to EEG and the composition of EEG didactics, have not effectively addressed this widespread issue. Implementation of competency-based curricula in lieu of traditional educational approaches may enhance proficiency in EEG interpretation amongst general neurologists in the absence of formal subspecialty training. Efforts in this regard have led to the development of a systematic, high-fidelity approach to the interpretation of epileptiform discharges that is readily employable across medical centers. Additionally, machine learning techniques hold promise for accelerating accurate and reliable EEG interpretation, particularly in settings where subspecialty interpretive EEG services are not readily available. This review highlights common diagnostic errors in EEG interpretation, limitations in current educational paradigms, and initiatives aimed at resolving these challenges.

Real-world user experience with seizure detection wearable devices in the home environment.

OBJECTIVE: To evaluate direct user experience with wearable seizure detection devices in the home environment. METHODS: A structured online questionnaire was completed by 242 users (175 caregivers and 67 persons with epilepsy), most of the patients (87.19%) having tonic-clonic seizures. RESULTS: The vast majority of the users were overall satisfied with the wearable device, considered that using the device was easy, and agreed that the use of the device improved their quality of life (median = 6 on 7-point Likert scale). A high retention rate (84.58%) and a long median usage time (14 months) were reported. In the home environment, most users (75.85%) experienced seizure detection sensitivity similar (≥95%) to what was previously reported in validation studies in epilepsy monitoring units. The experienced false alarm rate was relatively low (0-0.43 per day). Due to the alarms, almost one third of persons with epilepsy (PWEs; 30.00%) experienced decrease in the number of seizure-related injuries, and almost two thirds of PWEs (65.41%) experienced improvement in the accuracy of seizure diaries. Nonvalidated devices had significantly lower retention rate, overall satisfaction, perceived sensitivity, and improvement in quality of life, as compared with validated devices. SIGNIFICANCE: Our results demonstrate the feasibility and usefulness of automated seizure detection in the home environment.

Semiautomated classification of nocturnal seizures using video recordings.

OBJECTIVE: The objective of this study was to evaluate the accuracy of a semiautomated classification of nocturnal seizures using a hybrid system consisting of an artificial intelligence-based algorithm, which selects epochs with potential clinical relevance to be reviewed by human experts. METHODS: Consecutive patients with nocturnal motor seizures admitted for video-electroencephalographic long-term monitoring (LTM) were prospectively recruited. We determined the extent of data reduction by using the algorithm, and we evaluated the accuracy of seizure classification from the hybrid system compared with the gold standard of LTM. RESULTS: Forty consecutive patients (24 male; median age = 15 years) were analyzed. The algorithm reduced the duration of epochs to be reviewed to 14% of the total recording time (1874 h). There was a fair agreement beyond chance in seizure classification between the hybrid system and the gold standard (agreement coefficient = .33, 95% confidence interval = .20-.47). The hybrid system correctly identified all tonic-clonic and clonic seizures and 82% of focal motor seizures. However, there was low accuracy in identifying seizure types with more discrete or subtle motor phenomena. SIGNIFICANCE: Using a hybrid (algorithm-human) system for reviewing nocturnal video recordings significantly decreased the workload and provided accurate classification of major motor seizures (tonic-clonic, clonic, and focal motor seizures).

Minimum standards for inpatient long-term video-electroencephalographic monitoring: A clinical practice guideline of the International League Against Epilepsy and International Federation of Clinical Neurophysiology.

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.

Progressive slowing of clonic phase predicts postictal generalized EEG suppression.

OBJECTIVE: Postictal generalized electroencephalography (EEG) suppression (PGES) is a surrogate marker of sudden unexpected death in epilepsy (SUDEP). It is still unclear which ictal phenomena lead to prolonged PGES and increased risk of SUDEP. Semiology features of generalized convulsive seizure (GCS type 1) have been reported as a predictor of prolonged PGES. Progressive slowing of clonic phase (PSCP) has been observed in GCSs, with gradually increasing inhibitory periods interrupting the tonic contractions. We hypothesized that PSCP is associated with prolonged PGES. METHODS: We analyzed 90 bilateral convulsive seizures in 50 consecutive patients (21 female; age: 11-62 years, median: 31 years) recruited to video-EEG monitoring. Five raters, blinded to all other data, independently assessed the presence of PSCP. PGES and seizure semiology were evaluated independently. We determined inter-rater agreement (IRA) for the presence of PSCP, and we evaluated its association, as well as that of other ictal features, with the occurrence of PGES, prolonged PGES (≥20 s) and very prolonged PGES (≥50 s) using multivariate logistic regression analysis. RESULTS: We found substantial IRA for the presence of PSCP (percent agreement: 80%; beyond-chance agreement coefficient: .655). PSCP was an independent predictor of the occurrence of PGES and prolonged PGES (p < .001). All seizures with very prolonged PGES had PSCP. GCS type 1 was an independent predictor of occurrence of PGES (p = .02) and prolonged PGES (p = .03) but not of very prolonged PGES. Only half of the seizures with very prolonged PGES were GCS type 1. SIGNIFICANCE: PSCP predicts prolonged PGES, emphasizing the importance of gradually increasing inhibitory phenomena at the end of the seizures. Our findings shed more light on the ictal phenomena leading to increased risk of SUDEP. These phenomena may provide basis for algorithms implemented into wearable devices for identifying GCS with increased risk of SUDEP.

Accurate identification of EEG recordings with interictal epileptiform discharges using a hybrid approach: Artificial intelligence supervised by human experts.

OBJECTIVE: To evaluate the diagnostic performance of artificial intelligence (AI)-based algorithms for identifying the presence of interictal epileptiform discharges (IEDs) in routine (20-min) electroencephalography (EEG) recordings. METHODS: We evaluated two approaches: a fully automated one and a hybrid approach, where three human raters applied an operational IED definition to assess the automated detections grouped into clusters by the algorithms. We used three previously developed AI algorithms: Encevis, SpikeNet, and Persyst. The diagnostic gold standard (epilepsy or not) was derived from video-EEG recordings of patients' habitual clinical episodes. We compared the algorithms with the gold standard at the recording level (epileptic or not). The independent validation data set (not used for training) consisted of 20-min EEG recordings containing sharp transients (epileptiform or not) from 60 patients: 30 with epilepsy (with a total of 340 IEDs) and 30 with nonepileptic paroxysmal events. We compared sensitivity, specificity, overall accuracy, and the review time-burden of the fully automated and hybrid approaches, with the conventional visual assessment of the whole recordings, based solely on unrestricted expert opinion. RESULTS: For all three AI algorithms, the specificity of the fully automated approach was too low for clinical implementation (16.67%; 63.33%; 3.33%), despite the high sensitivity (96.67%; 66.67%; 100.00%). Using the hybrid approach significantly increased the specificity (93.33%; 96.67%; 96.67%) with good sensitivity (93.33%; 56.67%; 76.67%). The overall accuracy of the hybrid methods (93.33%; 76.67%; 86.67%) was similar to the conventional visual assessment of the whole recordings (83.33%; 95% confidence interval [CI]: 71.48-91.70%; p > .5), yet the time-burden of review was significantly lower (p < .001). SIGNIFICANCE: The hybrid approach, where human raters apply the operational IED criteria to automated detections of AI-based algorithms, has high specificity, good sensitivity, and overall accuracy similar to conventional EEG reading, with a significantly lower time-burden. The hybrid approach is accurate and suitable for clinical implementation.