Jonathan J. Halford

Epileptiform discharges, or spikes, within electroencephalogram (EEG) recordings are essential for diagnosing epilepsy and localizing seizure origins. Artificial intelligence (AI) offers a promising approach to automating detection, but current models are often hindered by artifact-related false positives and often target either event- or EEG-level classification, thus limiting clinical utility. We developed SpikeNet2, a deep-learning model based on a residual network architecture, and enhanced it with hard-negative mining to reduce false positives. Our study analyzed 17,812 EEG recordings from 13,523 patients across multiple institutions, including Massachusetts General Brigham (MGB) hospitals. Data from the Human Epilepsy Project (HEP) and SCORE-AI (SAI) were also included. A total of 32,433 event-level samples, labeled by experts, were used for training and evaluation. Performance was assessed using the area under the receiver operating characteristic curve (AUROC), the area under the precision–recall curve (AUPRC), calibration error, and a modified area under the curve (mAUC) metric. The model’s generalizability was evaluated using external datasets. SpikeNet2 demonstrated strong performance in event-level spike detection, achieving an AUROC of 0.973 and an AUPRC of 0.995, with 44% of experts surpassing the model on the MGB dataset. In external validation, the model achieved an AUROC of 0.942 and an AUPRC of 0.948 on the HEP dataset. For EEG-level classification, SpikeNet2 recorded an AUROC of 0.958 and an AUPRC of 0.959 on the MGB dataset, an AUROC of 0.888 and an AUPRC of 0.823 on the HEP dataset, and an AUROC of 0.995 and an AUPRC of 0.991 on the SAI dataset, with 32% of experts outperforming the model. The false-positive rate was reduced to an average of nine spikes per hour. SpikeNet2 offers expert-level accuracy in both event-level spike detection and EEG-level classification, while significantly reducing false positives. Its dual functionality and robust performance across diverse datasets make it a promising tool for clinical and telemedicine applications, particularly in resource-limited settings. (Funded by the National Institutes of Health and others.)

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

Background and Objectives: The validity of brain monitoring using electroencephalography (EEG), particularly to guide care in patients with acute or critical illness, requires that experts can reliably identify seizures and other potentially harmful rhythmic and periodic brain activity, collectively referred to as “ictal-interictal-injury continuum" (IIIC). Prior inter-rater reliability (IRR) studies are limited by small samples and selection bias. This study was conducted to assess the reliability of experts in identifying IIIC. Methods: This prospective analysis included 30 experts with subspecialty clinical neurophysiology training from 18 institutions. Experts independently scored varying numbers of ten-second EEG segments as: “Seizure (SZ)”, “Lateralized Periodic Discharges (LPD)”, “Generalized Periodic Discharges (GPD)”, “Lateralized Rhythmic Delta Activity (LRDA)”, “Generalized Rhythmic Delta Activity (GRDA)”, or “Other”. EEGs were performed for clinical indications at Massachusetts General Hospital between 2006 to 2020. Primary outcome measures were pairwise IRR (average percent agreement (PA) between pairs of experts) and majority IRR (average PA with group consensus) for each class; and beyond chance agreement (κ). Secondary outcomes were calibration of expert scoring to group consensus, and latent trait analysis to investigate contributions of bias and noise to scoring variability. Results: Among 2,711 EEGs, 49% were from females, and median (IQR) age was 55 (41). In total experts scored 50,697 EEG segments; the median [range] number scored by each expert was 6,287.5 [1,002, 45,267]. Overall pairwise IRR was moderate (PA 52%, κ 42%), and majority IRR was substantial (PA 65%, κ 61%). Noise-bias analysis demonstrated that a single underlying receiver operating curve can account for most variation in experts9 false positive vs true positive characteristics (median [range] of variance explained (R²): 95 [93, 98]%), and for most variation in experts’ precision vs sensitivity characteristics (R²: 75 [59, 89]%). Thus, variation between experts is mostly attributable not to differences in expertise, but rather to variation in decision thresholds. Discussion: Our results provide precise estimates of expert reliability from a large and diverse sample, and a parsimonious theory to explain the origin of disagreements between experts. The results also establish a standard for how well an automated IIIC classifier must perform to match experts. Classification of Evidence: This study provides Class II evidence that independent expert review reliably identifies ictal-interictal injury continuum patterns on EEG compared to expert consensus.

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.

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.