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.

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

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.

Autoantibodies against nodal and paranodal proteins, specifically anti-neurofascin antibodies (ANFAs), have been recently described in central and peripheral nervous system demyelinating disorders. We retrospectively reviewed the charts of six individuals evaluated at our Multiple Sclerosis Program who tested positive for serum ANFAs on Western blot. We describe these patients’ clinical and diagnostic findings and attempt to identify features that might guide clinicians in checking for ANFAs. In our series, the women-to-men ratio was 2:1. At presentation, the median age was 60 years (range 30–70). The clinical presentation was pleiotropic and included incomplete transverse myelitis (n = 3), progressive myelopathy (n = 1), recurrent symmetric polyneuropathy (n = 1), and nonspecific neurological symptoms (n = 1). Atypical features prompting further workup included coexisting upper and lower motor neuron features, older age at presentation with active disease, atypical spinal cord MRI features, and unusual cerebrospinal fluid findings. The serum ANFAs panel was positive for the NF-155 isoform in five patients (IgM n = 2; IgG n = 2; both n = 1) and the NF-140 isoform in two (IgG n = 2). Larger studies are needed to assess the relevance of ANFAs in demyelinating nervous system diseases, their impact on long-term clinical outcomes, and associated therapeutic implications.

Objective: Thalamic responsive neurostimulation (RNS) is a surgical option for patients with drug‐refractory epilepsy. However, it is unclear whether thalamic connectivity with the seizure onset zone (SOZ) has a role in clinical outcomes. Here, we aim to investigate the clinical utility of the connectivity between the SOZ and the thalamus for thalamic RNS targeting. Methods: Retrospective analysis was made of 12 patients treated with thalamic RNS. Clinical features and Engel scores were recorded. Patients were divided into responders, partial responders, and nonresponders based on seizure frequency reduction at last follow‐up. Structural connectivity between the SOZ and the whole thalamus was calculated using patient‐specific tractography. RNS electrodes were used to model the volume of tissue activated (VTA) with stimulation parameters at last follow‐up based on individualized electrode locations. The patient's VTAs were then used to identify thalamic areas with high or low probability of connectivity with the SOZ and how they were associated and correlated with clinical outcomes using nonparametric Mann–Whitney U and Spearman correlation tests. Results: Seven patients were responders, three nonresponders, and two partial responders. Thalamic nuclei targeted included anterior nucleus of thalamus and centromedian nucleus. Cortical areas of the SOZs included medial prefrontal, supplementary motor, cingulate, orbitofrontal, insular, mesial temporal, and lateral temporal cortices. Stimulation of thalamic areas with higher connectivity between the SOZ and the thalamus was associated with a clinical response of >50% reduction in seizures ( p = .017). Furthermore, higher degree of tract activation between the SOZ and the thalamus was correlated with better seizure outcomes at last follow‐up ( r = .78, p = .004). Significance: Greater recruitment of white matter connections between the SOZ and thalamus is associated with clinical response and may correlate with improved seizure outcomes during thalamic RNS. Using tractography to map the patient‐specific “thalamic seizure network” and the surgical targeting of these connections may result in improved clinical outcomes in patients treated with thalamic RNS.