Background: Generalized triphasic waves (TPWs) occur in both metabolic encephalopathies and non-convulsive status epilepticus (NCSE). Empiric trials of benzodiazepines (BZDs) or non-sedating AED (NSAEDs) are commonly used to differentiate the two, but the utility of such trials is debated. The goal of this study was to assess response rates of such trials and investigate whether metabolic profile differences affect the likelihood of a response. Methods: Three institutions within the Critical Care EEG Monitoring Research Consortium retrospectively identified patients with unexplained encephalopathy and TPWs who had undergone a trial of BZD and/or NSAEDs to differentiate between ictal and non-ictal patterns. We assessed responder rates and compared metabolic profiles of responders and non-responders. Response was defined as resolution of the EEG pattern and either unequivocal improvement in encephalopathy or appearance of previously absent normal EEG patterns, and further categorized as immediate (within <2 h of trial initiation) or delayed (>2 h from trial initiation). Results: We identified 64 patients with TPWs who had an empiric trial of BZD and/or NSAED. Most patients (71.9 %) were admitted with metabolic derangements and/or infection. Positive clinical responses occurred in 10/53 (18.9 %) treated with BZDs. Responses to NSAEDs occurred in 19/45 (42.2 %), being immediate in 6.7 %, delayed but definite in 20.0 %, and delayed but equivocal in 15.6 %. Overall, 22/64 (34.4 %) showed a definite response to either BZDs or NSAEDs, and 7/64 (10.9 %) showed a possible response. Metabolic differences of responders versus non-responders were statistically insignificant, except that the 48-h low value of albumin in the BZD responder group was lower than in the non-responder group. Conclusions: Similar metabolic profiles in patients with encephalopathy and TPWs between responders and non-responders to anticonvulsants suggest that predicting responders a priori is difficult. The high responder rate suggests that empiric trials of anticonvulsants indeed provide useful clinical information. The more than twofold higher response rate to NSAEDs suggests that this strategy may be preferable to BZDs. Further prospective investigation is warranted.

Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia Gill RS, Lee HM, Caldairou B, et al. Neurology. 2021 Oct 19;97(16):e1571-e1582. doi:10.1212/WNL.0000000000012698. Epub 2021 Sep 14. PMID: 34521691; PMCID: PMC8548962. Background and Objective: To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD). Methods: We used clinically acquired 3-dimensional (3D) T1-weighted and 3D fluid-attenuated inversion recovery MRI of 148 patients (median age 23 years [range 2-55 years]; 47% female) with histologically verified FCD at 9 centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed MRI-negative in 51% of patients, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. Sensitivity was tested in an independent cohort of 23 cases with FCD (13 ± 10 years). Applying the algorithm to 42 healthy controls and 89 controls with temporal lobe epilepsy disease tested specificity. Results: Overall sensitivity was 93% (137 of 148 FCD detected) using a leave-one-site-out cross-validation, with an average of 6 false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half, it ranked the highest. Sensitivity in the independent cohort was 83% (19 of 23; average of 5 false positives per patient). Specificity was 89% in healthy and disease controls. Discussion: This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification, this classifier may assist clinicians in adjusting hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for presurgical evaluation of MRI-negative epilepsy. Classification of evidence: This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in patients with epilepsy initially diagnosed as MRI negative.

Objective Previous studies based solely on visual EEG analysis reported equivocal results regarding an association of pharmaco-resistance with EEG asymmetries in genetic generalized epilepsies (GGE). We addressed this issue by applying both visual and quantitative methods to the pretreatment EEG of GGE patients. Methods Socio-demographic/disease characteristics and response to treatment/discontinuation trial for these patients were recorded at 6 months and at last follow up. The first EEG was retrospectively, blindly, and visually assessed for focal slowing, focal discharges and also quantitatively analyzed for amplitude or latency asymmetries of generalized discharges. Association between these variables and development of drug-resistance was evaluated. Results Out of 51 subjects, 40% had some type of EEG asymmetry by visual, 37% by quantitative and 54% by combined analysis. Drug-resistance was identified in 52% of patients after 6 months and in 24% at the end of the follow up period (~4.2 years). 27% of patients underwent a discontinuation trial; 43% unsuccessfully. There was no association between baseline EEG asymmetries of any type and refractoriness to medical therapy, regardless of analytical method used. Conclusions In a carefully selected cohort of medication-naïve GGE patients, visual and quantitative asymmetries in the first EEG were not associated with the development of pharmaco-resistance. Significance These findings do not provide support for utilization of EEG asymmetries as a prognostic tool in GGE.

BACKGROUND: Radiological identification of temporal lobe epilepsy (TLE) is crucial for diagnosis and treatment planning. TLE neuroimaging abnormalities are pervasive at the group level, but they can be subtle and difficult to identify by visual inspection of individual scans, prompting applications of artificial intelligence (AI) assisted technologies. METHOD: We assessed the ability of a convolutional neural network (CNN) algorithm to classify TLE vs. patients with AD vs. healthy controls using T1-weighted magnetic resonance imaging (MRI) scans. We used feature visualization techniques to identify regions the CNN employed to differentiate disease types. RESULTS: We show the following classification results: healthy control accuracy = 81.54% (SD = 1.77%), precision = 0.81 (SD = 0.02), recall = 0.85 (SD = 0.03), and F1-score = 0.83 (SD = 0.02); TLE accuracy = 90.45% (SD = 1.59%), precision = 0.86 (SD = 0.03), recall = 0.86 (SD = 0.04), and F1-score = 0.85 (SD = 0.04); and AD accuracy = 88.52% (SD = 1.27%), precision = 0.64 (SD = 0.05), recall = 0.53 (SD = 0.07), and F1 score = 0.58 (0.05). The high accuracy in identification of TLE was remarkable, considering that only 47% of the cohort had deemed to be lesional based on MRI alone. Model predictions were also considerably better than random permutation classifications (p < 0.01) and were independent of age effects. CONCLUSIONS: AI (CNN deep learning) can classify and distinguish TLE, underscoring its potential utility for future computer-aided radiological assessments of epilepsy, especially for patients who do not exhibit easily identifiable TLE associated MRI features (e.g., hippocampal sclerosis).

Objective: Functional seizures (FS) are often misclassified as epileptic seizures (ES). This study aimed to create an easy to use but comprehensive screening tool to guide further evaluation of patients presenting with this diagnostic dilemma. Materials and methods: Demographic, clinical and diagnostic data were collected on patients admitted for video-EEG monitoring for clarification of their diagnosis. Upon discharge, patients were classified as having ES vs FS. Using the collected characteristics and video-EEG diagnosis, we created a multivariable logistic regression model to identify predictors of ES. Then, we trained an integer-coefficient model with the most frequently selected predictors, creating a pointing system coined DDESVSFS, with scores ranging from -17 to +8 points. Results: 43 patients with FS and 165 patients with ES were recruited. In the final integer-coefficient model, 8 predictors were identified as significant in differentiating ES from FS: normal electroencephalogram (-3 points), predisposing factors for FS (-3 points), increased number of comorbidities (-3 points), semiology suggestive of FS (-4 points), increased seizure frequency (-4 points), longer disease duration (+3 points), antiepileptic polypharmacy (+2 points) and compliance with antiepileptic drugs (+3 points). Cumulative scores of ≤ -9 points carried <5% predictive value for ES, while cumulative scores of ≥ -1 points carried >95% predictive value. The model performed well (AUC: 0.923, sensitivity: 0.945, specificity: 0.698). Conclusions: We propose DDESVSFS as a simple, rapid and comprehensive prediction score for the Differential Diagnosis of Epileptic Seizures VS Functional Seizures. Large prospective studies are needed to evaluate its utility in clinical practice.

Objective: We sought to determine if global cognitive function in patients with epilepsy (PWE) differs when electroencephalographic (EEG) abnormalities are present during concurrent neuropsychological (NP) evaluation. Methods: We explored the association between subclinical epileptiform discharges (sEDs) and interictal epileptiform discharges (IEDs) and global aspects of cognition in 79 consecutive PWE who underwent continuous EEG monitoring during NP evaluation for diagnostic (15%) or presurgical (85%) purposes while on their standard antiseizure medication (ASM) regimens. As some researchers have suggested that the apparent link between IEDs and cognition represent epiphenomena of an underlying damaged neural substrate, we used functional status as a stratifying covariate to allow us to address this position. Results: Despite being on their standard ASM regimen, EEG was abnormal in 68% of patients. Epileptiform abnormalities (IEDs, sEDs, or both) were seen in isolation or coupled with diffuse or focal slowing in 38% of patients. Individuals with IEDs occurring during their NP evaluation demonstrated poorer scores in attention/working memory (forward and backward digit span), processing speed (symbol searching and coding), and speeded components of language (semantic fluency) tests compared with those with normal EEG tracings matched by their real-world, functional status. In two high functioning patients, performance was significantly better when these individuals were tested in the absence of IEDs, with performances appearing invalid when tested during periods of IED activity. No significant association was found between NP performance and nonepileptiform EEG abnormalities. Significance: A substantial proportion of PWE undergoing NP evaluation manifest concurrent EEG abnormalities, with epileptiform abnormalities associated with poorer global cognitive performance. As this pattern was observed regardless of functional status, this association appears to represent more than unrelated features coincidentally shared by the lowest functioning cohort. Coupled with our individual case data, our findings suggest that NP testing may be adversely affected by IEDs and sEDs going unrecognized in the absence of simultaneous EEG recordings, and set the stage for future studies to definitively establish this possible relationship.

Purpose: To investigate whether radiologically apparent brain magnetic resonance imaging (MRI) abnormalities are associated with the functional seizure (FS) semiology. Methods: All patients with a diagnosis of FS at the epilepsy centers at Shiraz University of Medical Sciences, Iran; Aichi Medical University Hospital, Japan; University of Michigan, USA; University of California, Los Angeles, USA; Emory University School of Medicine, USA; and Hospital el Cruce, Argentina, were studied. Results: One hundred patients were included; 77 (77%) had motor functional seizures. Lobar location of brain abnormality did not have an association with the semiology (p =.83). There was no significant difference between ictal behaviors in patients with frontal or parietal lesions compared to those with temporal or occipital lesions. Conclusion: There were no associations between functional seizure ictal behaviors and locations of the radiologically apparent brain MRI abnormalities. Further studies are needed to evaluate the underpinnings of varying behaviors in FS.

This study aims to determine the epidemiology of prolonged psychogenic non-epileptic seizures (pPNES) misdiagnosed as status epilepticus, as well as the risks associated with non-indicated treatment. Methods: We performed an individual patient data analysis from the Rapid Anticonvulsant Medication Prior to Arrival Trial (RAMPART) and the Established Status Epilepticus Treatment Trial (ESETT) to assess incidence, patient characteristics, and clinical course of misdiagnosed pPNES. Results: Among 980 patients aged 8 years or older diagnosed and treated for status epilepticus in RAMPART and ESETT, 79 (8.1%) were discharged with a final diagnosis of pPNES. The relative incidence was highest in adolescents and young adults (20.1%). The typical female preponderance seen in that age bracket was not evident in children and older adults. Adverse effects, including respiratory depression and intubation, were documented in 26% of patients with pPNES receiving benzodiazepines in RAMPART and 33% of patients receiving additional second-line medication in ESETT. In ESETT, patients who were treated with benzodiazepines before hospital admission had higher rates of unresponsiveness and severe adverse effects than those treated after admission, suggesting cumulative effects of accelerated treatment momentum. Across trials, one in five patients with pPNES were admitted to an intensive care unit. Conclusions: Misdiagnosis and treatment of pPNES as status epilepticus are a common and widespread problem with deleterious consequences. Mitigating it will require training of emergency staff in semiological diagnosis. Status epilepticus response protocols should incorporate appropriate diagnostic re-evaluations at each step of treatment escalation, especially in clinical trials.

Structural Brain Network Abnormalities and the Probability of Seizure Recurrence After Epilepsy Surgery Sinha N, Wang Y, Moreira da Silva N, et al. Neurology. 2021;96(5):e758-e771. doi:10.1212/WNL.0000000000011315 Objective: We assessed preoperative structural brain networks and clinical characteristics of patients with drug-resistant temporal lobe epilepsy (TLE) to identify correlates of postsurgical seizure recurrences. Methods: We examined data from 51 patients with TLE who underwent anterior temporal lobe resection (ATLR) and 29 healthy controls. For each patient, using the preoperative structural, diffusion, and postoperative structural magnetic resonance imaging, we generated 2 networks: presurgery network and surgically spared network. Standardizing these networks with respect to controls, we determined the number of abnormal nodes before surgery and expected to be spared by surgery. We incorporated these 2 abnormality measures and 13 commonly acquired clinical data from each patient into a robust machine learning framework to estimate patient-specific chances of seizures persisting after surgery. Results: Patients with more abnormal nodes had a lower chance of complete seizure freedom at 1 year, and, even if seizure-free at 1 year, were more likely to relapse within 5 years. The number of abnormal nodes was greater and their locations more widespread in the surgically spared networks of patients with poor outcome than in patients with good outcome. We achieved an area under the curve of 0.84 ± 0.06 and specificity of 0.89 ± 0.09 in predicting unsuccessful seizure outcomes (International League Against Epilepsy [ILAE] 3-5) as opposed to complete seizure freedom (ILAE 1) at 1 year. Moreover, the model-predicted likelihood of seizure relapse was significantly correlated with the grade of surgical outcome at year 1 and associated with relapses up to 5 years after surgery. Conclusion: Node abnormality offers a personalized, noninvasive marker that can be combined with clinical data to better estimate the chances of seizure freedom at 1 year and subsequent relapse up to 5 years after ATLR. Classification of evidence: This study provides class II evidence that node abnormality predicts postsurgical seizure recurrence.

None