Search

Objective: Recently, a deep learning artificial intelligence (AI) model forecasted seizure risk using retrospective seizure diaries with higher accuracy than random forecasts. The present study sought to prospectively evaluate the same algorithm., Methods: We recruited a prospective cohort of 46 people with epilepsy; 25 completed sufficient data entry for analysis (median = 5 months). We used the same AI method as in our prior study. Group-level and individual-level Brier Skill Scores (BSSs) compared random forecasts and simple moving average forecasts to the AI., Results: The AI had an area under the receiver operating characteristic curve of .82. At the group level, the AI outperformed random forecasting (BSS = .53). At the individual level, AI outperformed random in 28% of cases. At the group and individual level, the moving average outperformed the AI. If pre-enrollment (nonverified) diaries (with presumed underreporting) were included, the AI significantly outperformed both comparators. Surveys showed most did not mind poor-quality LOW-RISK or HIGH-RISK forecasts, yet 91% wanted access to these forecasts., Significance: The previously developed AI forecasting tool did not outperform a very simple moving average forecasting in this prospective cohort, suggesting that the AI model should be replaced., (© 2024 International League Against Epilepsy.)

Objective: A realistic seizure diary simulator is currently unavailable for many research needs, including clinical trial analysis and evaluation of seizure detection and seizure-forecasting tools. In recent years, important statistical features of seizure diaries have been characterized. These include (1) heterogeneity of individual seizure frequencies, (2) the relation between average seizure rate and standard deviation, (3) multiple risk cycles, (4) seizure clusters, and (5) limitations on inter-seizure intervals. The present study unifies these features into a single model., Methods: Our approach, Cyclic Heterogeneous Overdispersed Clustered Open-source L-relationship Adjustable Temporally limited E-diary Simulator (CHOCOLATES) is based on a hierarchical model centered on a gamma Poisson generator with several modifiers. This model accounts for the aforementioned statistical properties. The model was validated by simulating 10 000 randomized clinical trials (RCTs) of medication to compare with 23 historical RCTs. Metrics of 50% responder rate (RR50) and median percent change (MPC) were evaluated. We also used CHOCOLATES as input to a seizure-forecasting tool to test the flexibility of the model. We examined the area under the receiver-operating characteristic (ROC) curve (AUC) for test data with and without cycles and clusters., Results: The model recapitulated typical findings in 23 historical RCTs without the necessity of introducing an additional "placebo effect." The model produced the following RR50 values: placebo: 17 ± 4%; drug 38 ± 5%; and the following MPC values: placebo: 13 ± 6%; drug 40 ± 4%. These values are similar to historical data: for RR50: placebo, 21 ± 10%, drug: 43 ± 13%; and for MPC: placebo: 17 ± 10%, drug: 41 ± 11%. The seizure forecasts achieved an AUC of 0.68 with cycles and clusters, whereas without them the AUC was 0.51., Significance: CHOCOLATES represents the most realistic seizure occurrence simulator to date, based on observations from thousands of patients in different contexts. This tool is open source and flexible, and can be used for many applications, including clinical trial simulation and testing of seizure-forecasting tools., (© 2022 International League Against Epilepsy.)

People with epilepsy can experience tremendous stress from the uncertainty of when a seizure will occur. Three factors deemed important because of their potential influence on seizure risk are exercise, medication adherence, and the menstrual cycle. A narrative review was conducted through PubMed searching for relevant articles on how seizure risk is modified by 1) exercise, 2) medication adherence, and 3) the menstrual cycle. There was no consensus about the impact of exercise on seizure risk. Studies about medication nonadherence suggested an increase in seizure risk, but there was not a sufficient amount of data for a definitive conclusion. Most studies about the menstrual cycle reported an increase in seizures connected to a specific aspect of the menstrual cycle. No definitive studies were available to quantify this impact precisely. All three triggers reviewed had gaps in the research available, making it not yet possible to definitively quantify a relationship to seizure risk. More quantitative prospective studies are needed to ascertain the extent to which these triggers modify seizure risk., Competing Interests: Declarations of interest None., (Copyright © 2022 Elsevier B.V. All rights reserved.)

Purpose: Recently a realistic simulator of patient seizure diaries was developed that can reproduce effects seen in randomized clinical trials (RCTs). RCTs suffer from high costs and statistical inefficiencies. Using realistic simulation and machine learning this study aimed to identify a more statistically efficient outcome metric., Methods: Five candidate deep learning architectures with 54 permutations of hyperparameters were compared to the traditional standard, median percent change (MPC). Each were also tested for type 1 error. All models had similar outcomes, with appropriate low levels of type 1 error., Results: The simplest model was equivalent to a logistic regression of a histogram of individual percentage changes in seizure rate, requiring 21-22% less patients to discriminate drug from placebo at 90% power. This model was referred to as LPC., Conclusion: Future studies to validate LPC may enable faster, cheaper and more efficient clinical trials., (Copyright © 2021 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.)

Objective: The aim was to determine the prevalence and risk factors for electrographic seizures and other electroencephalographic (EEG) patterns in patients with Coronavirus disease 2019 (COVID-19) undergoing clinically indicated continuous electroencephalogram (cEEG) monitoring and to assess whether EEG findings are associated with outcomes., Methods: We identified 197 patients with COVID-19 referred for cEEG at 9 participating centers. Medical records and EEG reports were reviewed retrospectively to determine the incidence of and clinical risk factors for seizures and other epileptiform patterns. Multivariate Cox proportional hazards analysis assessed the relationship between EEG patterns and clinical outcomes., Results: Electrographic seizures were detected in 19 (9.6%) patients, including nonconvulsive status epilepticus (NCSE) in 11 (5.6%). Epileptiform abnormalities (either ictal or interictal) were present in 96 (48.7%). Preceding clinical seizures during hospitalization were associated with both electrographic seizures (36.4% in those with vs 8.1% in those without prior clinical seizures, odds ratio [OR] 6.51, p = 0.01) and NCSE (27.3% vs 4.3%, OR 8.34, p = 0.01). A pre-existing intracranial lesion on neuroimaging was associated with NCSE (14.3% vs 3.7%; OR 4.33, p = 0.02). In multivariate analysis of outcomes, electrographic seizures were an independent predictor of in-hospital mortality (hazard ratio [HR] 4.07 [1.44-11.51], p < 0.01). In competing risks analysis, hospital length of stay increased in the presence of NCSE (30 day proportion discharged with vs without NCSE: HR 0.21 [0.03-0.33] vs 0.43 [0.36-0.49])., Interpretation: This multicenter retrospective cohort study demonstrates that seizures and other epileptiform abnormalities are common in patients with COVID-19 undergoing clinically indicated cEEG and are associated with adverse clinical outcomes. ANN NEUROL 2021;89:872-883., (© 2021 American Neurological Association.)

Objective: There is a harmful myth that persists in modern culture that one should place objects into a seizing person's mouth to prevent "swallowing the tongue." Despite expert guidelines against this, the idea remains alive in popular media and public belief. We aimed to investigate the myth's origins and discredit it., Methods: A medical and popular literature review was conducted for the allusions to "swallowing one's tongue" and practice recommendations for and against placing objects into a seizing person's mouth. Current prevalence of these beliefs and relevant anatomy and physiology were summarised., Results: The first English language allusions to placing objects in a patient's mouth occurred in the mid-19th century, and the first allusions to swallowing one's tongue during a seizure occurred in the late 19th century. By the mid-20th century, it was clear that some were recommending against the practice of placing objects in a patient's mouth to prevent harm. Relatively recent popular literature and film continue to portray incorrect seizure first aid through at least 2013. There is ample modern literature confirming the anatomical impossibility of swallowing one's tongue and confirming the potential harm of putting objects in a patient's mouth., Conclusion: One cannot swallow their tongue during a seizure. Foreign objects should not be placed into a seizing person's mouth. We must continue to disseminate these ideas to our patients and colleagues. As neurologists, we have an obligation to champion safe practices for our patients, especially when popular media and culture continue to propagate dangerous ones., (Copyright © 2020 British Epilepsy Association. Published by Elsevier Ltd. All rights reserved.)

Objective: There are no validated methods for predicting the timing of seizures. Using machine learning, we sought to forecast 24-hour risk of self-reported seizure from e-diaries., Methods: Data from 5,419 patients on SeizureTracker.com (including seizure count, type, and duration) were split into training (3,806 patients/1,665,215 patient-days) and testing (1,613 patients/549,588 patient-days) sets with no overlapping patients. An artificial intelligence (AI) program, consisting of recurrent networks followed by a multilayer perceptron ("deep learning" model), was trained to produce risk forecasts. Forecasts were made from a sliding window of 3-month diary history for each day of each patient's diary. After training, the model parameters were held constant and the testing set was scored. A rate-matched random (RMR) forecast was compared to the AI. Comparisons were made using the area under the receiver operating characteristic curve (AUC), a measure of binary discrimination performance, and the Brier score, a measure of forecast calibration. The Brier skill score (BSS) measured the improvement of the AI Brier score compared to the benchmark RMR Brier score. Confidence intervals (CIs) on performance statistics were obtained via bootstrapping., Results: The AUC was 0.86 (95% CI = 0.85-0.88) for AI and 0.83 (95% CI = 0.81-0.85) for RMR, favoring AI (p < 0.001). Overall (all patients combined), BSS was 0.27 (95% CI = 0.23-0.31), also favoring AI (p < 0.001)., Interpretation: The AI produced a valid forecast superior to a chance forecaster, and provided meaningful forecasts in the majority of patients. Future studies will be needed to quantify the clinical value of these forecasts for patients. ANN NEUROL 2020;88:588-595., (© 2020 American Neurological Association.)

Objective: Seizure clusters are often encountered in people with poorly controlled epilepsy. Detection of seizure clusters is currently based on simple clinical rules, such as two seizures separated by four or fewer hours or multiple seizures in 24 h. Current definitions fail to distinguish between statistically significant clusters and those that may result from natural variation in the person's seizures. Ability to systematically define when a seizure cluster is significant for the individual carries major implications for treatment. However, there is no uniform consensus on how to define seizure clusters. This study proposes a principled statistical approach to defining seizure clusters that addresses these issues., Methods: A total of 533,968 clinical seizures from 1,748 people with epilepsy in the Seizure Tracker™ seizure diary database were used for algorithm development. We propose an algorithm for automated individualized seizure cluster identification combining cumulative sum change-point analysis with bootstrapping and aberration detection, which provides a new approach to personalized seizure cluster identification at user-specified levels of clinical significance. We develop a standalone user interface to make the proposed algorithm accessible for real-time seizure cluster identification (ClusterCalc™). Clinical impact of systematizing cluster identification is demonstrated by comparing empirically-defined clusters to those identified by routine seizure cluster definitions. We also demonstrate use of the Hurst exponent as a standardized measure of seizure clustering for comparison of seizure clustering burden within or across patients., Results: Seizure clustering was present in 26.7 % (95 % CI, 24.5-28.7 %) of people with epilepsy. Empirical tables were provided for standardizing inter- and intra-patient comparisons of seizure cluster tendency. Using the proposed algorithm, we found that 37.7-59.4 % of seizures identified as clusters based on routine definitions had high probability of occurring by chance. Several clusters identified by the algorithm were missed by conventional definitions. The utility of the ClusterCalc algorithm for individualized seizure cluster detection is demonstrated., Significance: This study proposes a principled statistical approach to individualized seizure cluster identification and demonstrates potential for real-time clinical usage through ClusterCalc. Using this approach accounts for individual variations in baseline seizure frequency and evaluates statistical significance. This new definition has the potential to improve individualized epilepsy treatment by systematizing identification of unrecognized seizure clusters and preventing unnecessary intervention for random events previously considered clusters., Competing Interests: Declaration of Competing Interest SC is the founder of EpilepsyAI, LLC. RM is the cofounder and owner of Seizure Tracker, LLC, cofounder of EpilepsyAI, LLC, and has received personal fees from Cyberonics, Courtagen, Engage Therapeutics, Brain Sentinel, Neurelis, UCB, and grants from the Tuberous Sclerosis Alliance. DG is on the medical advisory board of Magic Leap, and has received grant support from BIDMC and NIH T32NS048005. SH is on the Editorial Board of Epilepsy and Behavior. A patent application has been filed based on these results. The remaining authors have no conflicts of interest., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Background: Changes in patient-reported seizure frequencies are the gold standard used to test efficacy of new treatments in randomized controlled trials (RCTs). Recent analyses of patient seizure diary data suggest that the placebo response may be attributable to natural fluctuations in seizure frequency, though the evidence is incomplete. Here we develop a data-driven statistical model and assess the impact of the model on interpretation of placebo response., Methods: A synthetic seizure diary generator matching statistical properties seen across multiple epilepsy diary datasets was constructed. The model was used to simulate the placebo arm of 5000 RCTs. A meta-analysis of 23 historical RCTs was compared to the simulations., Results: The placebo 50 %-responder rate (RR50) was 27.3 ± 3.6 % (simulated) and 21.1 ± 10.0 % (historical). The placebo median percent change (MPC) was 22.0 ± 6.0 % (simulated) and 16.7 ± 10.3 % (historical)., Conclusions: A statistical model of daily seizure count generation which incorporates quantities related to the natural fluctuations of seizure count data produces a placebo response comparable to those seen in historical RCTs. This model may be useful in better understanding the seizure count fluctuations seen in patients in other clinical settings., Competing Interests: Declaration of Competing Interest The authors declare that there are no conflicts of interest., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Objective: We conducted clinical testing of an automated Bayesian machine learning algorithm (Epilepsy Seizure Assessment Tool [EpiSAT]) for outpatient seizure risk assessment using seizure counting data, and validated performance against specialized epilepsy clinician experts., Methods: We conducted a prospective longitudinal study of EpiSAT performance against 24 specialized clinician experts at three tertiary referral epilepsy centers in the United States. Accuracy, interrater reliability, and intra-rater reliability of EpiSAT for correctly identifying changes in seizure risk (improvements, worsening, or no change) were evaluated using 120 seizures from four synthetic seizure diaries (seizure risk known) and 120 seizures from four real seizure diaries (seizure risk unknown). The proportion of observed agreement between EpiSAT and clinicians was evaluated to assess compatibility of EpiSAT with clinical decision patterns by epilepsy experts., Results: EpiSAT exhibited substantial observed agreement (75.4%) with clinicians for assessing seizure risk. The mean accuracy of epilepsy providers for correctly assessing seizure risk was 74.7%. EpiSAT accurately identified seizure risk in 87.5% of seizure diary entries, corresponding to a significant improvement of 17.4% (P = .002). Clinicians exhibited low-to-moderate interrater reliability for seizure risk assessment (Krippendorff's α = 0.46) with good intrarater reliability across a 4- to 12-week evaluation period (Scott's π = 0.89)., Significance: These results validate the ability of EpiSAT to yield objective clinical recommendations on seizure risk which follow decision patterns similar to those from specialized epilepsy providers, but with improved accuracy and reproducibility. This algorithm may serve as a useful clinical decision support system for quantitative analysis of clinical seizure frequency in clinical epilepsy practice., (Wiley Periodicals, Inc. © 2019 International League Against Epilepsy.)

Machine learning leverages statistical and computer science principles to develop algorithms capable of improving performance through interpretation of data rather than through explicit instructions. Alongside widespread use in image recognition, language processing, and data mining, machine learning techniques have received increasing attention in medical applications, ranging from automated imaging analysis to disease forecasting. This review examines the parallel progress made in epilepsy, highlighting applications in automated seizure detection from electroencephalography (EEG), video, and kinetic data, automated imaging analysis and pre-surgical planning, prediction of medication response, and prediction of medical and surgical outcomes using a wide variety of data sources. A brief overview of commonly used machine learning approaches, as well as challenges in further application of machine learning techniques in epilepsy, is also presented. With increasing computational capabilities, availability of effective machine learning algorithms, and accumulation of larger datasets, clinicians and researchers will increasingly benefit from familiarity with these techniques and the significant progress already made in their application in epilepsy., (Wiley Periodicals, Inc. © 2019 International League Against Epilepsy.)

Individual seizure rates are highly volatile, with large fluctuations from month-to-month. Nevertheless, changes in individual mean seizure rates are used to measure whether or not trial participants successfully respond to treatment. This study aims to quantify the challenges in identifying individual treatment responders in epilepsy. A power calculation was performed to determine the trial duration required to detect a significant 50% decrease in seizure rates (P < .05) for individuals. Seizure rate simulations were also performed to determine the number of people who would appear to be 50% responders by chance. Seizure rate statistics were derived from long-term seizure counts recorded during a previous clinical trial for an implantable seizure monitoring device. We showed that individual variance in monthly seizure rates can lead to an unacceptably high false-positive rate in the detection of individual treatment responders. This error rate cannot be reduced by increasing the trial population; however, it can be reduced by increasing the duration of clinical trials. This finding suggests that some drugs may be incorrectly evaluated as effective; or, conversely, that helpful drugs could be rejected based on 50% response rates. It is important to pursue more nuanced approaches to measuring individual treatment response, which consider the patient-specific distributions of seizure rates., (Wiley Periodicals, Inc. © 2019 International League Against Epilepsy.)

Objective: Given the known association of daylight saving time (DST) transitions with increased risk of accidents, heart attack, and stroke, we aimed to determine whether seizures, which are reportedly influenced by sleep and circadian disruption, also increased in frequency following the transition into DST., Methods: Using Seizure Tracker's self-reported data from 12 401 individuals from 2008-2016, 932 717 seizures were assessed for changes in incidence in relation to DST transitions. Two methods of standardization-z scores and unit-scaled rate ratios (RRs)-were used to compare seizure propensities following DST transitions to other time periods., Results: As a percentile relative to all other weeks in a given year, absolute seizure counts in the week of DST fell below the median (DST seizure percentiles mean ± SD: 19.68 ± 16.25, P = 0.01), which was concordant with weekday-specific comparisons. Comparatively, RRs for whole-week (1.06, 95% confidence interval [CI] 1.02-1.10, P = 0.0054) and weekday-to-weekday (RR range 1.04-1.16, all P < 0.001) comparisons suggested a slightly higher incidence of seizures in the DST week compared to all other weeks of the year. However, examining the similar risk of the week preceding and following the DST-transition week revealed no significant weekday-to-weekday differences in seizure incidence, although there was an unexpected, modestly decreased seizure propensity in the DST week relative to the whole week prior (RR 0.94, 95% CI 0.91-0.96, P < 0.001)., Significance: Despite expectations that circadian and sleep disruption related to DST transitions would increase the incidence of seizures, we found little substantive evidence for such an association in this large, longitudinal cohort. Although large-scale observational/epidemiologic cohorts can be effective at answering such questions, additional covariates (eg, sleep duration, seizure type, and so on) that may underpin the association were not able available, so the association has not definitively been ruled out., (Wiley Periodicals, Inc. © 2019 International League Against Epilepsy.)

Using approximations based on presumed U.S. time zones, we characterized day and nighttime seizure patterns in a patient-reported database, Seizure Tracker. A total of 632 995 seizures (9698 patients) were classified into 4 categories: isolated seizure event (ISE), cluster without status epilepticus (CWOS), cluster including status epilepticus (CIS), and status epilepticus (SE). We used a multinomial mixed-effects logistic regression model to calculate odds ratios (ORs) to determine night/day ratios for the difference between seizure patterns: ISE versus SE, ISE versus CWOS, ISE versus CIS, and CWOS versus CIS. Ranges of OR values were reported across cluster definitions. In adults, ISE was more likely at night compared to CWOS (OR = 1.49, 95% adjusted confidence interval [CI] = 1.36-1.63) and to CIS (OR = 1.61, 95% adjusted CI = 1.34-1.88). The ORs for ISE versus SE and CWOS versus SE were not significantly different regardless of cluster definition. In children, ISE was less likely at night compared to SE (OR = 0.85, 95% adjusted CI = 0.79-0.91). ISE was more likely at night compared to CWOS (OR = 1.35, 95% adjusted CI = 1.26-1.44) and CIS (OR = 1.65, 95% adjusted CI = 1.44-1.86). CWOS was more likely during the night compared to CIS (OR = 1.22, 95% adjusted CI = 1.05-1.39). With the exception of SE in children, our data suggest that more severe patterns favor daytime. This suggests distinct day/night preferences for different seizure patterns in children and adults., (Wiley Periodicals, Inc. © 2018 International League Against Epilepsy.)

Purpose of Review: The estimation of seizure frequency is a cornerstone of clinical management of epilepsy and the evaluation of new therapies. Current estimation approaches are significantly limited by several factors. Comparing patient diaries and objective estimates (through both inpatient video-EEG monitoring of and long-term ambulatory EEG studies) reveal that patients document seizures inaccurately. So far, few practical alternative methods of estimation have been available., Recent Findings: We review the systems of counting currently utilized and their limitations, as well as the limitations imposed by problems defining clinical events. Alternative methodologies that permit the volatility of seizure rates to be accommodated, and possible alternative measures of brain excitability will be outlined. Recent developments in technologies around data capture, such as wearable and implantable devices, as well as significant advances in the ability to analyse the large data-sets supplied by these systems have provided a wealth of information., Summary: There are now unprecedented opportunities to utilize and apply these insights in routine clinical management and assessment of therapies. The rapid adoption of long-term, wearable monitoring systems will permit major advances in our understanding of the natural history of epilepsy, and lead to more effective therapies and improved patient safety.

Objective: Seizure frequency variability is associated with placebo responses in randomized controlled trials (RCT). Increased variability can result in drug misclassification and, hence, decreased statistical power. We investigated a new method that directly incorporated variability into RCT analysis, Z V ., Methods: Two models were assessed: the traditional 50%-responder rate (RR50), and the variability-corrected score, Z V . Each predicted seizure frequency upper and lower limits using prior seizures. Accuracy was defined as percentage of time-intervals when the observed seizure frequencies were within the predicted limits. First, we tested the Z V method on three datasets (SeizureTracker: n=3016, Human Epilepsy Project: n=107, and NeuroVista: n=15). An additional independent SeizureTracker validation dataset was used to generate a set of 200 simulated trials each for 5 different sample sizes (total N=100 to 500 by 100), assuming 20% dropout and 30% drug efficacy. "Power" was determined as the percentage of trials successfully distinguishing placebo from drug (p<0.05)., Results: Prediction accuracy across datasets was, Z V : 91-100%, RR50: 42-80%. Simulated RCT Z V analysis achieved >90% power at N=100 per arm while RR50 required N=200 per arm., Significance: Z V may increase the statistical power of an RCT relative to the traditional RR50., (Published by Elsevier B.V.)