Familial aggregation of seizure outcomes in four familial epilepsy cohorts.

OBJECTIVE: To assess the possible effects of genetics on seizure outcome by estimating the familial aggregation of three outcome measures: seizure remission, history of ≥4 tonic-clonic seizures, and seizure control for individuals taking antiseizure medication. METHODS: We analyzed families containing multiple persons with epilepsy in four previously collected retrospective cohorts. Seizure remission was defined as being 5 and 10 years seizure-free at last observation. Total number of tonic-clonic seizures was dichotomized at <4 and ≥4 seizures. Seizure control in patients taking antiseizure medication was defined as no seizures for 1, 2, and 3 years. We used Bayesian generalized linear mixed-effects model (GLMM) to estimate the intraclass correlation coefficient (ICC) of the family-specific random effect, controlling for epilepsy type, age at epilepsy onset, and age at last data collection as fixed effects. We analyzed each cohort separately and performed meta-analysis using GLMMs. RESULTS: The combined cohorts included 3644 individuals with epilepsy from 1463 families. A history of ≥4 tonic-clonic seizures showed strong familial aggregation in three separate cohorts and meta-analysis (ICC .28, 95% confidence interval [CI] .21-.35, Bayes factor 8 × 1016). Meta-analyses did not reveal significant familial aggregation of seizure remission (ICC .08, 95% CI .01-.17, Bayes factor 1.46) or seizure control for individuals taking antiseizure medication (ICC .13, 95% CI 0-.35, Bayes factor 0.94), with heterogeneity among cohorts. SIGNIFICANCE: A history of ≥4 tonic-clonic seizures aggregated strongly in families, suggesting a genetic influence, whereas seizure remission and seizure control for individuals taking antiseizure medications did not aggregate consistently in families. Different seizure outcomes may have different underlying biology and risk factors. These findings should inform the future molecular genetic studies of seizure outcomes.

Disparities in Genetic Testing for Neurologic Disorders.

BACKGROUND AND OBJECTIVES: Genetic testing is now the standard of care for many neurologic conditions. Health care disparities are unfortunately widespread in the US health care system, but disparities in the utilization of genetic testing for neurologic conditions have not been studied. We tested the hypothesis that access to and results of genetic testing vary according to race, ethnicity, sex, socioeconomic status, and insurance status for adults with neurologic conditions. METHODS: We analyzed retrospective data from patients who underwent genetic evaluation and testing through our institution's neurogenetics program. We tested for differences between demographic groups in 3 steps of a genetic evaluation pathway: (1) attending a neurogenetic evaluation, (2) completing genetic testing, and (3) receiving a diagnostic result. We compared patients on this genetic evaluation pathway with the population of all neurology outpatients at our institution, using univariate and multivariable logistic regression analyses. RESULTS: Between 2015 and 2022, a total of 128,440 patients were seen in our outpatient neurology clinics and 2,540 patients underwent genetic evaluation. Black patients were less than half as likely as White patients to be evaluated (odds ratio [OR] 0.49, p < 0.001), and this disparity was similar after controlling for other demographic factors in multivariable analysis. Patients from the least wealthy quartile of zip codes were also less likely to be evaluated (OR 0.67, p < 0.001). Among patients who underwent evaluation, there were no disparities in the likelihood of completing genetic testing, nor in the likelihood of a diagnostic result after adjusting for age. Analyses restricted to specific indications for genetic testing supported these findings. DISCUSSION: We observed unequal utilization of our clinical neurogenetics program for patients from marginalized and minoritized demographic groups, especially Black patients. Among patients who do undergo evaluation, all groups benefit similarly from genetic testing when it is indicated. Understanding and removing barriers to accessing genetic testing will be essential to health care equity and optimal care for all patients with neurologic disorders.

Disparities in seizure outcomes revealed by large language models.

OBJECTIVE: Large-language models (LLMs) can potentially revolutionize health care delivery and research, but risk propagating existing biases or introducing new ones. In epilepsy, social determinants of health are associated with disparities in care access, but their impact on seizure outcomes among those with access remains unclear. Here we (1) evaluated our validated, epilepsy-specific LLM for intrinsic bias, and (2) used LLM-extracted seizure outcomes to determine if different demographic groups have different seizure outcomes. MATERIALS AND METHODS: We tested our LLM for differences and equivalences in prediction accuracy and confidence across demographic groups defined by race, ethnicity, sex, income, and health insurance, using manually annotated notes. Next, we used LLM-classified seizure freedom at each office visit to test for demographic outcome disparities, using univariable and multivariable analyses. RESULTS: We analyzed 84 675 clinic visits from 25 612 unique patients seen at our epilepsy center. We found little evidence of bias in the prediction accuracy or confidence of outcome classifications across demographic groups. Multivariable analysis indicated worse seizure outcomes for female patients (OR 1.33, P ≤ .001), those with public insurance (OR 1.53, P ≤ .001), and those from lower-income zip codes (OR ≥1.22, P ≤ .007). Black patients had worse outcomes than White patients in univariable but not multivariable analysis (OR 1.03, P = .66). CONCLUSION: We found little evidence that our LLM was intrinsically biased against any demographic group. Seizure freedom extracted by LLM revealed disparities in seizure outcomes across several demographic groups. These findings quantify the critical need to reduce disparities in the care of people with epilepsy.

Alcohol for seizure induction in the epilepsy monitoring unit.

RATIONALE: Seizure induction techniques are used in the epilepsy monitoring unit (EMU) to increase diagnostic yield and reduce length of stay. There are insufficient data on the efficacy of alcohol as an induction technique. METHODS: We performed a retrospective cohort study using six years of EMU data at our institution. We compared cases who received alcohol for seizure induction to matched controls who did not. The groups were matched on the following variables: age, reason for admission, length of stay, number of antiseizure medications (ASM) at admission, whether ASMs were tapered during admission, and presence of interictal epileptiform discharges. We used both propensity score and exact matching strategies. We compared the likelihood of epileptic seizures and nonepileptic events in cases versus controls using Kaplan-Meier time-to-event analysis, as well as odds ratios for these outcomes occurring at any time during the admission. RESULTS: We analyzed 256 cases who received alcohol (median dose 2.5 standard drinks) and 256 propensity score-matched controls. Cases who received alcohol were no more likely than controls to have an epileptic seizure (X2(1) = 0.01, p = 0.93) or nonepileptic event (X2(1) = 2.1, p = 0.14) in the first 48 h after alcohol administration. For the admission overall, cases were no more likely to have an epileptic seizure (OR 0.89, 95 % CI 0.61-1.28, p = 0.58), nonepileptic event (OR 0.97, CI 0.62-1.53, p = 1.00), nor require rescue benzodiazepine (OR 0.63, CI 0.35-1.12, p = 0.15). Stratified analyses revealed no increased risk of epileptic seizure in any subgroups. Sensitivity analysis using exact matching showed that results were robust to matching strategy. CONCLUSIONS: Alcohol was not an effective induction technique in the EMU. This finding has implications for counseling patients with epilepsy about the risks of drinking alcohol in moderation in their daily lives.

Genetic testing in adults with neurologic disorders: indications, approach, and clinical impacts.

The role of genetic testing in neurologic clinical practice has increased dramatically in recent years, driven by research on genetic causes of neurologic disease and increased availability of genetic sequencing technology. Genetic testing is now indicated for adults with a wide range of common neurologic conditions. The potential clinical impacts of a genetic diagnosis are also rapidly expanding, with a growing list of gene-specific treatments and clinical trials, in addition to important implications for prognosis, surveillance, family planning, and diagnostic closure. The goals of this review are to provide practical guidance for clinicians about the role of genetics in their practice and to provide the neuroscience research community with a broad survey of current progress in this field. We aim to answer three questions for the neurologist in practice: Which of my patients need genetic testing? What testing should I order? And how will genetic testing help my patient? We focus on common neurologic disorders and presentations to the neurology clinic. For each condition, we review the most current guidelines and evidence regarding indications for genetic testing, expected diagnostic yield, and recommended testing approach. We also focus on clinical impacts of genetic diagnoses, highlighting a number of gene-specific therapies recently approved for clinical use, and a rapidly expanding landscape of gene-specific clinical trials, many using novel nucleotide-based therapeutic modalities like antisense oligonucleotides and gene transfer. We anticipate that more widespread use of genetic testing will help advance therapeutic development and improve the care, and outcomes, of patients with neurologic conditions.

Disparities in seizure outcomes revealed by large language models.

Objective: Large-language models (LLMs) in healthcare have the potential to propagate existing biases or introduce new ones. For people with epilepsy, social determinants of health are associated with disparities in access to care, but their impact on seizure outcomes among those with access to specialty care remains unclear. Here we (1) evaluated our validated, epilepsy-specific LLM for intrinsic bias, and (2) used LLM-extracted seizure outcomes to test the hypothesis that different demographic groups have different seizure outcomes. Methods: First, we tested our LLM for intrinsic bias in the form of differential performance in demographic groups by race, ethnicity, sex, income, and health insurance in manually annotated notes. Next, we used LLM-classified seizure freedom at each office visit to test for outcome disparities in the same demographic groups, using univariable and multivariable analyses. Results: We analyzed 84,675 clinic visits from 25,612 patients seen at our epilepsy center 2005-2022. We found no differences in the accuracy, or positive or negative class balance of outcome classifications across demographic groups. Multivariable analysis indicated worse seizure outcomes for female patients (OR 1.33, p = 3×10-8), those with public insurance (OR 1.53, p = 2×10-13), and those from lower-income zip codes (OR ≥ 1.22, p ≤ 6.6×10-3). Black patients had worse outcomes than White patients in univariable but not multivariable analysis (OR 1.03, p = 0.66). Significance: We found no evidence that our LLM was intrinsically biased against any demographic group. Seizure freedom extracted by LLM revealed disparities in seizure outcomes across several demographic groups. These findings highlight the critical need to reduce disparities in the care of people with epilepsy.

ILAE Genetics Literacy series: Progressive myoclonus epilepsies.

Progressive Myoclonus Epilepsy (PME) is a rare epilepsy syndrome characterized by the development of progressively worsening myoclonus, ataxia, and seizures. A molecular diagnosis can now be established in approximately 80% of individuals with PME. Almost fifty genetic causes of PME have now been established, although some remain extremely rare. Herein, we provide a review of clinical phenotypes and genotypes of the more commonly encountered PMEs. Using an illustrative case example, we describe appropriate clinical investigation and therapeutic strategies to guide the management of this often relentlessly progressive and devastating epilepsy syndrome. This manuscript in the Genetic Literacy series maps to Learning Objective 1.2 of the ILAE Curriculum for Epileptology (Epileptic Disord. 2019;21:129).

Generalization of finetuned transformer language models to new clinical contexts.

Objective: We have previously developed a natural language processing pipeline using clinical notes written by epilepsy specialists to extract seizure freedom, seizure frequency text, and date of last seizure text for patients with epilepsy. It is important to understand how our methods generalize to new care contexts. Materials and methods: We evaluated our pipeline on unseen notes from nonepilepsy-specialist neurologists and non-neurologists without any additional algorithm training. We tested the pipeline out-of-institution using epilepsy specialist notes from an outside medical center with only minor preprocessing adaptations. We examined reasons for discrepancies in performance in new contexts by measuring physical and semantic similarities between documents. Results: Our ability to classify patient seizure freedom decreased by at least 0.12 agreement when moving from epilepsy specialists to nonspecialists or other institutions. On notes from our institution, textual overlap between the extracted outcomes and the gold standard annotations attained from manual chart review decreased by at least 0.11 F1 when an answer existed but did not change when no answer existed; here our models generalized on notes from the outside institution, losing at most 0.02 agreement. We analyzed textual differences and found that syntactic and semantic differences in both clinically relevant sentences and surrounding contexts significantly influenced model performance. Discussion and conclusion: Model generalization performance decreased on notes from nonspecialists; out-of-institution generalization on epilepsy specialist notes required small changes to preprocessing but was especially good for seizure frequency text and date of last seizure text, opening opportunities for multicenter collaborations using these outcomes.

Macrocephaly and developmental delay caused by missense variants in RAB5C.

Rab GTPases are important regulators of intracellular vesicular trafficking. RAB5C is a member of the Rab GTPase family that plays an important role in the endocytic pathway, membrane protein recycling and signaling. Here we report on 12 individuals with nine different heterozygous de novo variants in RAB5C. All but one patient with missense variants (n = 9) exhibited macrocephaly, combined with mild-to-moderate developmental delay. Patients with loss of function variants (n = 2) had an apparently more severe clinical phenotype with refractory epilepsy and intellectual disability but a normal head circumference. Four missense variants were investigated experimentally. In vitro biochemical studies revealed that all four variants were damaging, resulting in increased nucleotide exchange rate, attenuated responsivity to guanine exchange factors and heterogeneous effects on interactions with effector proteins. Studies in C. elegans confirmed that all four variants were damaging in vivo and showed defects in endocytic pathway function. The variant heterozygotes displayed phenotypes that were not observed in null heterozygotes, with two shown to be through a dominant negative mechanism. Expression of the human RAB5C variants in zebrafish embryos resulted in defective development, further underscoring the damaging effects of the RAB5C variants. Our combined bioinformatic, in vitro and in vivo experimental studies and clinical data support the association of RAB5C missense variants with a neurodevelopmental disorder characterized by macrocephaly and mild-to-moderate developmental delay through disruption of the endocytic pathway.

Characterizing the treatment gap in the United States among adult patients with a new diagnosis of epilepsy.

OBJECTIVE: Epilepsy is largely a treatable condition with antiseizure medication (ASM). Recent national administrative claims data suggest one third of newly diagnosed adult epilepsy patients remain untreated 3 years after diagnosis. We aimed to quantify and characterize this treatment gap within a large US academic health system leveraging the electronic health record for enriched clinical detail. METHODS: This retrospective cohort study evaluated the proportion of adult patients in the health system from 2012 to 2020 who remained untreated 3 years after initial epilepsy diagnosis. To identify incident epilepsy, we applied validated administrative health data criteria of two encounters for epilepsy/seizures and/or convulsions, and we required no ASM prescription preceding the first encounter. Engagement with the health system at least 2 years before and at least 3 years after diagnosis was required. Among subjects who met administrative data diagnosis criteria, we manually reviewed medical records for a subset of 240 subjects to verify epilepsy diagnosis, confirm treatment status, and elucidate reason for nontreatment. These results were applied to estimate the proportion of the full cohort with untreated epilepsy. RESULTS: Of 831 patients who were automatically classified as having incident epilepsy by inclusion criteria, 80 (10%) remained untreated 3 years after incident epilepsy diagnosis. Manual chart review of incident epilepsy classification revealed only 33% (78/240) had true incident epilepsy. We found untreated patients were more frequently misclassified (p < .001). Using corrected counts, we extrapolated to the full cohort (831) and estimated <1%-3% had true untreated epilepsy. SIGNIFICANCE: We found a substantially lower proportion of patients with newly diagnosed epilepsy remained untreated compared to previous estimates from administrative data analysis. Manual chart review revealed patients were frequently misclassified as having incident epilepsy, particularly patients who were not treated with an ASM. Administrative data analyses utilizing only diagnosis codes may misclassify patients as having incident epilepsy.

Long-term epilepsy outcome dynamics revealed by natural language processing of clinic notes.

OBJECTIVE: Electronic medical records allow for retrospective clinical research with large patient cohorts. However, epilepsy outcomes are often contained in free text notes that are difficult to mine. We recently developed and validated novel natural language processing (NLP) algorithms to automatically extract key epilepsy outcome measures from clinic notes. In this study, we assessed the feasibility of extracting these measures to study the natural history of epilepsy at our center. METHODS: We applied our previously validated NLP algorithms to extract seizure freedom, seizure frequency, and date of most recent seizure from outpatient visits at our epilepsy center from 2010 to 2022. We examined the dynamics of seizure outcomes over time using Markov model-based probability and Kaplan-Meier analyses. RESULTS: Performance of our algorithms on classifying seizure freedom was comparable to that of human reviewers (algorithm F1 = .88 vs. human annotator κ = .86). We extracted seizure outcome data from 55 630 clinic notes from 9510 unique patients written by 53 unique authors. Of these, 30% were classified as seizure-free since the last visit, 48% of non-seizure-free visits contained a quantifiable seizure frequency, and 47% of all visits contained the date of most recent seizure occurrence. Among patients with at least five visits, the probabilities of seizure freedom at the next visit ranged from 12% to 80% in patients having seizures or seizure-free at the prior three visits, respectively. Only 25% of patients who were seizure-free for 6 months remained seizure-free after 10 years. SIGNIFICANCE: Our findings demonstrate that epilepsy outcome measures can be extracted accurately from unstructured clinical note text using NLP. At our tertiary center, the disease course often followed a remitting and relapsing pattern. This method represents a powerful new tool for clinical research with many potential uses and extensions to other clinical questions.

A pharmacokinetic model of antiseizure medication load to guide care in the epilepsy monitoring unit.

OBJECTIVE: Evaluating patients with drug-resistant epilepsy often requires inducing seizures by tapering antiseizure medications (ASMs) in the epilepsy monitoring unit (EMU). The relationship between ASM taper strategy, seizure timing, and severity remains unclear. In this study, we developed and validated a pharmacokinetic model of total ASM load and tested its association with seizure occurrence and severity in the EMU. METHODS: We studied 80 patients who underwent intracranial electroencephalographic recording for epilepsy surgery planning. We developed a first order pharmacokinetic model of the ASMs administered in the EMU to generate a continuous metric of overall ASM load. We then related modeled ASM load to seizure likelihood and severity. We determined the association between the rate of ASM load reduction, the length of hospital stay, and the probability of having a severe seizure. Finally, we used modeled ASM load to predict oncoming seizures. RESULTS: Seizures occurred in the bottom 50th percentile of sampled ASM loads across the cohort (p < .0001, Wilcoxon signed-rank test), and seizures requiring rescue therapy occurred at lower ASM loads than seizures that did not require rescue therapy (logistic regression mixed effects model, odds ratio = .27, p = .01). Greater ASM decrease early in the EMU was not associated with an increased likelihood of having a severe seizure, nor with a shorter length of stay. SIGNIFICANCE: A pharmacokinetic model can accurately estimate ASM levels for patients in the EMU. Lower modeled ASM levels are associated with increased seizure likelihood and seizure severity. We show that ASM load, rather than ASM taper speed, is associated with severe seizures. ASM modeling has the potential to help optimize taper strategy to minimize severe seizures while maximizing diagnostic yield.

Quantitative artifact reduction and pharmacologic paralysis improve detection of EEG epileptiform activity in critically ill patients.

OBJECTIVE: Epileptiform activity is common in critically ill patients, but movement-related artifacts-including electromyography (EMG) and myoclonus-can obscure EEG, limiting detection of epileptiform activity. We sought to determine the ability of pharmacologic paralysis and quantitative artifact reduction (AR) to improve epileptiform discharge detection. METHODS: Retrospective analysis of patients who underwent continuous EEG monitoring with pharmacologic paralysis. Four reviewers read each patient's EEG pre- and post- both paralysis and AR, and indicated the presence of epileptiform discharges. We compared the interrater reliability (IRR) of identifying discharges at baseline, post-AR, and post-paralysis, and compared the performance of AR and paralysis according to artifact type. RESULTS: IRR of identifying epileptiform discharges at baseline was slight (N = 30; κ = 0.10) with a trend toward increase post-AR (κ = 0.26, p = 0.053) and a significant increase post-paralysis (κ = 0.51, p = 0.001). AR was as effective as paralysis at improving IRR of identifying discharges in those with high EMG artifact (N = 15; post-AR κ = 0.63, p = 0.009; post-paralysis κ = 0.62, p = 0.006) but not with primarily myoclonus artifact (N = 15). CONCLUSIONS: Paralysis improves detection of epileptiform activity in critically ill patients when movement-related artifact obscures EEG features. AR improves detection as much as paralysis when EMG artifact is high, but is ineffective when the primary source of artifact is myoclonus. SIGNIFICANCE: In the appropriate setting, both AR and paralysis facilitate identification of epileptiform activity in critically ill patients.

Inherited bone marrow failure with macrothrombocytopenia due to germline tubulin beta class I (TUBB) variant.

Germline mutations in tubulin beta class I (TUBB), which encodes one of the ß-tubulin isoforms, were previously associated with neurological and cutaneous abnormalities. Here, we describe the first case of inherited bone marrow (BM) failure, including marked thrombocytopenia, morphological abnormalities, and cortical dysplasia, associated with a de novo p.D249V variant in TUBB. Mutant TUBB had abnormal cellular localisation in transfected cells. Following interferon/ribavirin therapy administered for transfusion-acquired hepatitis C, severe pancytopenia and BM aplasia ensued, which was unresponsive to immunosuppression. Acquired chromosome arm 6p loss of heterozygosity was identified, leading to somatic loss of the mutant TUBB allele.

Development of a natural language processing algorithm to extract seizure types and frequencies from the electronic health record.

OBJECTIVE: To develop a natural language processing (NLP) algorithm to abstract seizure types and frequencies from electronic health records (EHR). BACKGROUND: Seizure frequency measurement is an epilepsy quality metric. Yet, abstraction of seizure frequency from the EHR is laborious. We present an NLP algorithm to extract seizure data from unstructured text of clinic notes. Algorithm performance was assessed at two epilepsy centers. METHODS: We developed a rules-based NLP algorithm to recognize terms related to seizures and frequency within the text of an outpatient encounter. Algorithm output (e.g. number of seizures of a particular type within a time interval) was compared to seizure data manually annotated by two expert reviewers ("gold standard"). The algorithm was developed from 150 clinic notes from institution #1 (development set), then tested on a separate set of 219 notes from institution #1 (internal test set) with 248 unique seizure frequency elements. The algorithm was separately applied to 100 notes from institution #2 (external test set) with 124 unique seizure frequency elements. Algorithm performance was measured by recall (sensitivity), precision (positive predictive value), and F1 score (geometric mean of precision and recall). RESULTS: In the internal test set, the algorithm demonstrated 70% recall (173/248), 95% precision (173/182), and 0.82 F1 score compared to manual review. Algorithm performance in the external test set was lower with 22% recall (27/124), 73% precision (27/37), and 0.40 F1 score. CONCLUSIONS: These results suggest NLP extraction of seizure types and frequencies is feasible, though not without challenges in generalizability for large-scale implementation.

Natural History Study of STXBP1-Developmental and Epileptic Encephalopathy Into Adulthood.

BACKGROUND AND OBJECTIVES: Pathogenic STXBP1 variants cause a severe early-onset developmental and epileptic encephalopathy (STXBP1-DEE). We aimed to investigate the natural history of STXBP1-DEE in adults focusing on seizure evolution, the presence of movement disorders, and the level of functional (in)dependence. METHODS: In this observational study, patients with a minimum age of 18 years carrying a (likely) pathogenic STXBP1 variant were recruited through medical genetics departments and epilepsy centers. Treating clinicians completed clinical questionnaires and performed semistructured video examinations while performing tasks from the (modified) Unified Parkinson Disease Rating Scale when possible. RESULTS: Thirty adult patients were included for summary statistics, with video recordings available for 19 patients. The median age at last follow-up was 24 years (range 18-58 years). All patients had epilepsy, with a median onset age of 3.5 months. At last follow-up, 80% of adults had treatment-resistant seizures despite long periods of seizure freedom in 37%. Tonic-clonic, focal, and tonic seizures were most frequent in adults. Epileptic spasms, an unusual feature beyond infancy, were present in 3 adults. All individuals had developmental impairment. Periods of regression were present in 59% and did not always correlate with flare-ups in seizure activity. Eighty-seven percent had severe or profound intellectual disability, 42% had autistic features, and 65% had significant behavioral problems. Video examinations showed gait disorders in all 12 patients able to walk, including postural abnormalities with external rotation of the feet, broad-based gait, and asymmetric posture/dystonia. Tremor, present in 56%, was predominantly of the intention/action type. Stereotypies were seen in 63%. Functional outcome concerning mobility was variable ranging from independent walking (50%) to wheelchair dependence (39%). Seventy-one percent of adults were nonverbal, and all were dependent on caregivers for most activities of daily living. DISCUSSION: STXBP1-DEE warrants continuous monitoring for seizures in adult life. Periods of regression are more frequent than previously established and can occur into adulthood. Movement disorders are often present and involve multiple systems. Although functional mobility is variable in adulthood, STXBP1-DEE frequently leads to severe cognitive impairments and a high level of functional dependence. Understanding the natural history of STXBP1-DEE is important for prognostication and will inform future therapeutic trials.

Common risk variants for epilepsy are enriched in families previously targeted for rare monogenic variant discovery.

BACKGROUND: The epilepsies are highly heritable conditions that commonly follow complex inheritance. While monogenic causes have been identified in rare familial epilepsies, most familial epilepsies remain unsolved. We aimed to determine (1) whether common genetic variation contributes to familial epilepsy risk, and (2) whether that genetic risk is enriched in familial compared with non-familial (sporadic) epilepsies. METHODS: Using common variants derived from the largest epilepsy genome-wide association study, we calculated polygenic risk scores (PRS) for patients with familial epilepsy (n = 1,818 from 1,181 families), their unaffected relatives (n = 771), sporadic patients (n = 1,182), and population controls (n = 15,929). We also calculated separate PRS for genetic generalised epilepsy (GGE) and focal epilepsy. Statistical analyses used mixed-effects regression models to account for familial relatedness, sex, and ancestry. FINDINGS: Patients with familial epilepsies had higher epilepsy PRS compared to population controls (OR 1·20, padj = 5×10-9), sporadic patients (OR 1·11, padj = 0.008), and their own unaffected relatives (OR 1·12, padj = 0.01). The top 1% of the PRS distribution was enriched 3.8-fold for individuals with familial epilepsy when compared to the lowest decile (padj = 5×10-11). Familial PRS enrichment was consistent across epilepsy type; overall, polygenic risk was greatest for the GGE clinical group. There was no significant PRS difference in familial cases with established rare variant genetic etiologies compared to unsolved familial cases. INTERPRETATION: The aggregate effects of common genetic variants, measured as polygenic risk scores, play an important role in explaining why some families develop epilepsy, why specific family members are affected while their relatives are not, and why families manifest specific epilepsy types. Polygenic risk contributes to the complex inheritance of the epilepsies, including in individuals with a known genetic etiology. FUNDING: National Health and Medical Research Council of Australia, National Institutes of Health, American Academy of Neurology, Thomas B and Jeannette E Laws McCabe Fund, Mirowski Family Foundation.

Seizure Detection in Continuous Inpatient EEG: A Comparison of Human vs Automated Review.

BACKGROUND AND OBJECTIVES: The aim of this work was to test the accuracy of Persyst commercially available automated seizure detection in critical care EEG by comparing automated seizure detections to human review in a manually reviewed cohort and on a large scale. METHODS: Automated seizure detections (Persyst versions 12 and 13) were compared to human review in a pilot cohort of 229 seizures from 85 EEG records and then in an expanded cohort of 7,924 EEG records. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for individual seizures (pilot cohort) and for entire records (pilot and expanded cohorts). We assessed EEG features associated with the accuracy of automated seizure detections. RESULTS: In the pilot cohort, accuracy of automated detection for individual seizures was modest (sensitivity 0.50, PPV 0.60). At the record level (did the recording contain seizures or not?), sensitivity was higher (pilot cohort 0.78, expanded cohort 0.91), PPV was low (pilot cohort 0.40, expanded cohort 0.08), and NPV was high (pilot cohort 0.88, expanded cohort 0.97). Different software versions (version 12 vs 13) performed similarly. Sensitivity was higher for records containing focal-onset seizures compared to generalized-onset seizures (0.93 vs 0.85, p = 0.012). DISCUSSION: In critical care continuous EEG recordings, automated detection of individual seizures had rates of both false negatives and false positives that bring into question its utility as a seizure alarm in clinical practice. At the level of entire EEG records, the absence of automated detections accurately predicted EEG records without true seizures. The true value of Persyst automated seizure detection appears to lie in triaging of low-risk EEGs. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that an automated seizure detection program cannot accurately identify EEG records that contain seizures.

Assessing the landscape of STXBP1-related disorders in 534 individuals.

Disease-causing variants in STXBP1 are among the most common genetic causes of neurodevelopmental disorders. However, the phenotypic spectrum in STXBP1-related disorders is wide and clear correlations between variant type and clinical features have not been observed so far. Here, we harmonized clinical data across 534 individuals with STXBP1-related disorders and analysed 19 973 derived phenotypic terms, including phenotypes of 253 individuals previously unreported in the scientific literature. The overall phenotypic landscape in STXBP1-related disorders is characterized by neurodevelopmental abnormalities in 95% and seizures in 89% of individuals, including focal-onset seizures as the most common seizure type (47%). More than 88% of individuals with STXBP1-related disorders have seizure onset in the first year of life, including neonatal seizure onset in 47%. Individuals with protein-truncating variants and deletions in STXBP1 (n = 261) were almost twice as likely to present with West syndrome and were more phenotypically similar than expected by chance. Five genetic hotspots with recurrent variants were identified in more than 10 individuals, including p.Arg406Cys/His (n = 40), p.Arg292Cys/His/Leu/Pro (n = 30), p.Arg551Cys/Gly/His/Leu (n = 24), p.Pro139Leu (n = 12), and p.Arg190Trp (n = 11). None of the recurrent variants were significantly associated with distinct electroclinical syndromes, single phenotypic features, or showed overall clinical similarity, indicating that the baseline variability in STXBP1-related disorders is too high for discrete phenotypic subgroups to emerge. We then reconstructed the seizure history in 62 individuals with STXBP1-related disorders in detail, retrospectively assigning seizure type and seizure frequency monthly across 4433 time intervals, and retrieved 251 anti-seizure medication prescriptions from the electronic medical records. We demonstrate a dynamic pattern of seizure control and complex interplay with response to specific medications particularly in the first year of life when seizures in STXBP1-related disorders are the most prominent. Adrenocorticotropic hormone and phenobarbital were more likely to initially reduce seizure frequency in infantile spasms and focal seizures compared to other treatment options, while the ketogenic diet was most effective in maintaining seizure freedom. In summary, we demonstrate how the multidimensional spectrum of phenotypic features in STXBP1-related disorders can be assessed using a computational phenotype framework to facilitate the development of future precision-medicine approaches.

Extracting seizure frequency from epilepsy clinic notes: a machine reading approach to natural language processing.

OBJECTIVE: Seizure frequency and seizure freedom are among the most important outcome measures for patients with epilepsy. In this study, we aimed to automatically extract this clinical information from unstructured text in clinical notes. If successful, this could improve clinical decision-making in epilepsy patients and allow for rapid, large-scale retrospective research. MATERIALS AND METHODS: We developed a finetuning pipeline for pretrained neural models to classify patients as being seizure-free and to extract text containing their seizure frequency and date of last seizure from clinical notes. We annotated 1000 notes for use as training and testing data and determined how well 3 pretrained neural models, BERT, RoBERTa, and Bio_ClinicalBERT, could identify and extract the desired information after finetuning. RESULTS: The finetuned models (BERTFT, Bio_ClinicalBERTFT, and RoBERTaFT) achieved near-human performance when classifying patients as seizure free, with BERTFT and Bio_ClinicalBERTFT achieving accuracy scores over 80%. All 3 models also achieved human performance when extracting seizure frequency and date of last seizure, with overall F1 scores over 0.80. The best combination of models was Bio_ClinicalBERTFT for classification, and RoBERTaFT for text extraction. Most of the gains in performance due to finetuning required roughly 70 annotated notes. DISCUSSION AND CONCLUSION: Our novel machine reading approach to extracting important clinical outcomes performed at or near human performance on several tasks. This approach opens new possibilities to support clinical practice and conduct large-scale retrospective clinical research. Future studies can use our finetuning pipeline with minimal training annotations to answer new clinical questions.