Diagnostic challenges in epilepsy: seizure under-reporting and seizure detection

Are the seizures under control or unnoticed? Electroclinical evaluation of epilepsy with eyelid myoclonia

PURPOSE

In this study, patients with epilepsy with eyelid myoclonia (E-EM) were evaluated according to their EEG findings, seizure outcomes, and their consistency with the final ictal EEG findings. We also investigated the possible prognostic factors.

METHODS

Patients with E-EM and at least two years of follow-up in our clinic were included in the study. We analyzed the presence of eyelid myoclonia, absence and myoclonic seizures, and generalized tonic-clonic seizures for the prior two years and then verified with the latest ictal EEG features. Video-EEGs were analyzed according to the background activity, the existence of generalized spike-wave discharge or polyspike-wave complexes, focal spike-wave discharge, photoparoxysmal responses, and fast activity.

RESULTS

21 patients were involved in this study. In six patients, the seizures were undetected on the first EEGs, whereas they were detected on subsequent ones. The seizures were captured on the first EEGs of six patients; however, they disappeared on subsequent ones. Only one patient had seizures detected on every EEG. The consistency of the seizures was variable in eight patients. At the final follow-up, seizures were reported as being under control for more than two years in 12 patients, according to patients and their parents' reports. However, ictal EEG findings were detected in six of these patients. No electroclinical feature was associated with seizure freedom.

CONCLUSION

This study provides further evidence that seizure freedom in E-EM patients is overestimated. The patients and their parents may not be aware of the seizures. Therefore, video-EEG monitorization is essential during follow-up.

CM-Pf deep brain stimulation in polyneuromodulation for epilepsy

OBJECTIVE

Neuromodulation is a viable option for patients with drug-resistant epilepsies. We reviewed the management of patients with two deep brain neurostimulators. In addition, patients implanted with a device targeting the centromedian-parafascicular (CM-Pf) nuclear complex supplements this report to provide an illustrative case to implantation and programming a patient with three active devices.

METHODS

A narrative review using PubMed and Embase identified patients with drug-resistant epilepsy implanted with more than one neurostimulator was performed. Combinations of vagus nerve stimulation (VNS), deep brain stimulation (DBS), and responsive neurostimulation (RNS) were identified. We provide a background of a newly reported case of an adult with a triple implant eventually responding to CM-Pf DBS as the third implant following suboptimal benefit from VNS and RNS.

RESULTS

In review of the literature, dual-device therapy is increasing in reports of use with combinations of VNS, RNS, and DBS to treat patients with drug-resistant epilepsy. We review dual-device implants with thalamic DBS device combinations, functional neural networks, and programming patients with dual devices. CM-Pf is a new target for DBS and has shown a variable response in focal epilepsy. We report the unique case of 28-year-old male with drug-resistant focal epilepsy who experienced a 75% seizure reduction with CM-Pf DBS as his third device after suboptimal responses to VNS and RNS. After 9 months, he also experienced seizure freedom from recurrent focal to bilateral tonic-clonic seizures. No medical or surgical complications or safety issues were encountered.

CONCLUSION

We demonstrate safety and feasibility in an adult combining active VNS, RNS, and CM-Pf DBS. Patients with dual-device therapy who experience a suboptimal response to initial device use at optimized settings should not be considered a neuromodulation "failure." Strategies to combine devices require a working knowledge of brain networks.

A scheme combining feature fusion and hybrid deep learning models for epileptic seizure detection and prediction

Epilepsy is one of the most well-known neurological disorders globally, leading to individuals experiencing sudden seizures and significantly impacting their quality of life. Hence, there is an urgent necessity for an efficient method to detect and predict seizures in order to mitigate the risks faced by epilepsy patients. In this paper, a new method for seizure detection and prediction is proposed, which is based on multi-class feature fusion and the convolutional neural network-gated recurrent unit-attention mechanism (CNN-GRU-AM) model. Initially, the Electroencephalography (EEG) signal undergoes wavelet decomposition through the Discrete Wavelet Transform (DWT), resulting in six subbands. Subsequently, time-frequency domain and nonlinear features are extracted from each subband. Finally, the CNN-GRU-AM further extracts features and performs classification. The CHB-MIT dataset is used to validate the proposed approach. The results of tenfold cross validation show that our method achieved a sensitivity of 99.24% and 95.47%, specificity of 99.51% and 94.93%, accuracy of 99.35% and 95.16%, and an AUC of 99.34% and 95.15% in seizure detection and prediction tasks, respectively. The results show that the method proposed in this paper can effectively achieve high-precision detection and prediction of seizures, so as to remind patients and doctors to take timely protective measures.

High precision in epileptic seizure self-reporting with an app diary

People with epilepsy frequently under- or inaccurately report their seizures, which poses a challenge for evaluating their treatment. The introduction of epilepsy health apps provides a novel approach that could improve seizure documentation. This study assessed the documentation performance of an app-based seizure diary and a conventional paper seizure diary. At two tertiary epilepsy centers patients were asked to use one of two offered methods to report their seizures (paper or app diary) during their stay in the epilepsy monitoring unit. The performances of both methods were assessed based on the gold standard of video-EEG annotations. In total 89 adults (54 paper and 35 app users) with focal epilepsy were included in the analysis, of which 58 (33 paper and 25 app users) experienced at least one seizure and made at least one seizure diary entry. We observed a high precision of 85.7% for the app group, whereas the paper group's precision was lower due to overreporting (66.9%). Sensitivity was similar for both methods. Our findings imply that performance of seizure self-reporting is patient-dependent but is more precise for patients who are willing to use digital apps. This may be relevant for treatment decisions and future clinical trial design.

How accurate do self-reported seizures need to be for effective medication management in epilepsy?

Studies suggest that self-reported seizure diaries suffer from 50% under-reporting on average. It is unknown to what extent this impacts medication management. This study used simulation to predict the seizure outcomes of a large heterogeneous clinic population treated with a standardized algorithm based on self-reported seizures. Using CHOCOLATES, a state-of-the-art realistic seizure diary simulator, 100 000 patients were simulated over 10 years. A standard algorithm for medication management was employed at 3 month intervals for all patients. The impact on true seizure rates, expected seizure rates, and time-to-steady-dose were computed for self-reporting sensitivities 0%-100%. Time-to-steady-dose and medication use mostly did not depend on sensitivity. True seizure rate decreased minimally with increasing self-reporting in a non-linear fashion, with the largest decreases at low sensitivity rates (0%-10%). This study suggests that an extremely wide range of sensitivity will have similar seizure outcomes when patients are clinically treated using an algorithm similar to the one presented. Conversely, patients with sensitivity ≤10% would be expected to benefit (via lower seizure rates) from objective devices that provide even small improvements in seizure sensitivity.

Long-term seizure diary tracking habits in clinical studies: Evidence from the Human Epilepsy Project

OBJECTIVE

To characterize seizure tracking patterns of people with focal epilepsy using electronic seizure diary entries, and to assess for risk factors associated with poor tracking.

METHODS

We analyzed electronic seizure diary data from 410 participants with newly diagnosed focal epilepsy in the Human Epilepsy Project 1 (HEP1). Each participant was expected to record data each day during the study, regardless of seizure occurrence. The primary outcome of this post-hoc analysis was whether each participant properly tracked a seizure diary entry each day during their study participation. Using finite mixture modeling, we grouped patient tracking trajectories into data-driven clusters. Once defined, we used multinomial modeling to test for independent risk factors of tracking group membership.

RESULTS

Using over up to three years of daily seizure diary data per subject, we found four distinct seizure tracking groups: consistent, frequent at study onset, occasional, and rare. Participants in the consistent tracking group tracked a median of 92% (interquartile range, IQR: 82%, 99%) of expected days, compared to 47% (IQR:34%, 60%) in the frequent at study onset group, 37% (IQR: 26%, 49%) in the occasional group, and 9% (IQR: 3%, 15%) in the rare group. In multivariable analysis, consistent trackers had lower rates of seizure days per tracked year during their study participation, compared to other groups.

SIGNIFICANCE

Future efforts need to focus on improving seizure diary tracking adherence to improve quality of outcome data, particularly in those with higher seizure burden. In addition, accounting for missing data when using seizure diary data as a primary outcome is important in research trials. If not properly accounted for, total seizure burden may be underestimated and biased, skewing results of clinical trials.

Feasibility, Safety, and Performance of Full-Head Subscalp EEG Using Minimally Invasive Electrode Implantation

BACKGROUND AND OBJECTIVES

Current practice in clinical neurophysiology is limited to short recordings with conventional EEG (days) that fail to capture a range of brain (dys)functions at longer timescales (months). The future ability to optimally manage chronic brain disorders, such as epilepsy, hinges upon finding methods to monitor electrical brain activity in daily life. We developed a device for full-head subscalp EEG (Epios) and tested here the feasibility to safely insert the electrode leads beneath the scalp by a minimally invasive technique (primary outcome). As secondary outcome, we verified the noninferiority of subscalp EEG in measuring physiologic brain oscillations and pathologic discharges compared with scalp EEG, the established standard of care.

METHODS

Eight participants with pharmacoresistant epilepsy undergoing intracranial EEG received in the same surgery subscalp electrodes tunneled between the scalp and the skull with custom-made tools. Postoperative safety was monitored on an inpatient ward for up to 9 days. Sleep-wake, ictal, and interictal EEG signals from subscalp, scalp, and intracranial electrodes were compared quantitatively using windowed multitaper transforms and spectral coherence. Noninferiority was tested for pairs of neighboring subscalp and scalp electrodes with a Bland-Altman analysis for measurement bias and calculation of the interclass correlation coefficient (ICC).

RESULTS

As primary outcome, up to 28 subscalp electrodes could be safely placed over the entire head through 1-cm scalp incisions in a ∼1-hour procedure. Five of 10 observed perioperative adverse events were linked to the investigational procedure, but none were serious, and all resolved. As a secondary outcome, subscalp electrodes advantageously recorded EEG percutaneously without requiring any maintenance and were noninferior to scalp electrodes for measuring (1) variably strong, stage-specific brain oscillations (alpha in wake, delta, sigma, and beta in sleep) and (2) interictal spikes peak-potentials and ictal signals coherent with seizure propagation in different brain regions (ICC >0.8 and absence of bias).

DISCUSSION

Recording full-head subscalp EEG for localization and monitoring purposes is feasible up to 9 days in humans using minimally invasive techniques and noninferior to the current standard of care. A longer prospective ambulatory study of the full system will be necessary to establish the safety and utility of this innovative approach.

TRIAL REGISTRATION INFORMATION

clinicaltrials.gov/study/NCT04796597.

Cosine convolutional neural network and its application for seizure detection

Traditional convolutional neural networks (CNNs) often suffer from high memory consumption and redundancy in their kernel representations, leading to overfitting problems and limiting their application in real-time, low-power scenarios such as seizure detection systems. In this work, a novel cosine convolutional neural network (CosCNN), which replaces traditional kernels with the robust cosine kernel modulated by only two learnable factors, is presented, and its effectiveness is validated on the tasks of seizure detection. Meanwhile, based on the cosine lookup table and KL-divergence, an effective post-training quantization algorithm is proposed for CosCNN hardware implementation. With quantization, CosCNN can achieve a nearly 75% reduction in the memory cost with almost no accuracy loss. Moreover, we design a configurable cosine convolution accelerator on Field Programmable Gate Array (FPGA) and deploy the quantized CosCNN on Zedboard, proving the proposed seizure detection system can operate in real-time and low-power scenarios. Extensive experiments and comparisons were conducted using two publicly available epileptic EEG databases, the Bonn database and the CHB-MIT database. The results highlight the performance superiority of the CosCNN over traditional CNNs as well as other seizure detection methods.

Prospective validation of a seizure diary forecasting falls short

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.

Autoimmune-associated epilepsy - a challenging concept

The current International League Against Epilepsy (ILAE) definition and classification guidelines for the first time introduced the category of immune-mediated focal epilepsy in addition to structural, genetic, infectious, and metabolic aetiologies. Moreover, the ILAE Autoimmunity and Inflammation Taskforce recently provided a conceptual framework for the distinction between acute "provoked" seizures in the acute phase of autoimmune encephalitis from chronic "unprovoked" seizures due to autoimmune-associated epilepsy. The first category predominately applies to those autoimmune encephalitis patients with autoantibodies against cell surface neural antigens, in whom autoantibodies are assumed to exert a direct ictogenic effect without overt structural damage. These patients do not exhibit enduring predisposition to seizures after the "acute phase" encephalitis, and thus do not fulfil the definition of epilepsy. The second category applies to those autoimmune encephalitis patients with autoantibodies against intracellular neural antigens and Rasmussen's encephalitis, in whom T cells are assumed to cause epileptogenic effects through immune-inflammation and overt structural damage. These patients do exhibit enduring predisposition to seizures after the "acute phase" of encephalitis and thus fulfil the definition of epilepsy. AAE may result from both, ongoing brain autoimmunity and associated structural brain damage according to the current ILAE definition and classification guideline. We here discuss the difficulties of this concept and suggest an unbiased translationally validated and data-driven approach to predict in an individual encephalitis patient the propensity to develop (or not) AAE and the cognitive and behavioural outcome.

Over- and underreporting of seizures: How big is the problem?

OBJECTIVE

Clinical decisions on managing epilepsy patients rely on patient accuracy regarding seizure reporting. Studies have noted disparities between patient-reported seizures and electroencephalographic (EEG) findings during video-EEG monitoring periods, chiefly highlighting underreporting of seizures, a well-recognized phenomenon. However, seizure overreporting is a significant problem discussed within the literature, although not in such a large cohort. Our aim is to quantify the over- and underreporting of seizures in a large cohort of ambulatory EEG patients.

METHODS

We performed a retrospective data analysis on 3407 patients referred to a diagnostic service for ambulatory video-EEG between 2020 and 2022. Both patient-reported events and events discovered on review of the video-EEG were analyzed and classified as epileptic, psychogenic (typically clinical motor events, without accompanying EEG change), or noncorrelated events (NCEs; without perceivable clinical or EEG change). Events were analyzed by state of arousal and indication for referral. Subgroup analysis was performed in patients with focal and generalized epilepsies.

RESULTS

A total of 21 024 events were recorded by 3407 patients. Fifty-eight percent of reported events were NCEs, whereas 27% of all events were epileptic. Sixty-four percent of epileptic seizures were not reported by the patient but discovered by the clinical service on review of the recording. NCEs were in the highest proportion in the awake and drowsy arousal states and were the most common event type for the majority of referral indications. Subgroup analysis found a significantly higher proportion of NCEs in the patients with focal epilepsy (23%) compared to generalized epilepsy (10%; p < .001, chi-squared proportion test).

SIGNIFICANCE

Our results reaffirm the phenomenon of underreporting and highlight the prevalence of overreporting. Overreporting likely represents irrelevant symptoms or electrographic discharges not represented on scalp electrodes, identification of which has important clinical relevance. Future studies should analyze events by risk factors to elucidate relationships clinicians can use and investigate the etiology of NCEs.

Calibrating Deep Learning Classifiers for Patient-Independent Electroencephalogram Seizure Forecasting

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice.

A platform for brain network sensing and stimulation with quantitative behavioral tracking: Application to limbic circuit epilepsy

Temporal lobe epilepsy is a common neurological disease characterized by recurrent seizures. These seizures often originate from limbic networks and people also experience chronic comorbidities related to memory, mood, and sleep (MMS). Deep brain stimulation targeting the anterior nucleus of the thalamus (ANT-DBS) is a proven therapy, but the optimal stimulation parameters remain unclear. We developed a neurotechnology platform for tracking seizures and MMS to enable data streaming between an investigational brain sensing-stimulation implant, mobile devices, and a cloud environment. Artificial Intelligence algorithms provided accurate catalogs of seizures, interictal epileptiform spikes, and wake-sleep brain states. Remotely administered memory and mood assessments were used to densely sample cognitive and behavioral response during ANT-DBS. We evaluated the efficacy of low-frequency versus high-frequency ANT-DBS. They both reduced seizures, but low-frequency ANT-DBS showed greater reductions and better sleep and memory. These results highlight the potential of synchronized brain sensing and behavioral tracking for optimizing neuromodulation therapy.

Seizure Cycles under Pharmacotherapy

OBJECTIVE

This study was undertaken to determine the effects of antiseizure medications (ASMs) on multidien (multiday) cycles of interictal epileptiform activity (IEA) and seizures and evaluate their potential clinical significance.

METHODS

We retrospectively analyzed up to 10 years of data from 88 of the 256 total adults with pharmacoresistant focal epilepsy who participated in the clinical trials of the RNS System, an intracranial device that keeps records of IEA counts. Following adjunctive ASM trials, we evaluated changes over months in (1) rates of self-reported disabling seizures and (2) multidien IEA cycle strength (spectral power for periodicity between 4 and 40 days). We used a survival analysis and the receiver operating characteristics to assess changes in IEA as a predictor of seizure control.

RESULTS

Among 56 (33.3%) of the 168 adjunctive ASM trials suitable for analysis, ASM introduction was followed by an average 50 to 70% decrease in multidien IEA cycle strength and a concomitant 50 to 70% decrease in relative seizure rate for up to 12 months. Individuals with a ≥50% decrease in IEA cycle strength in the first 3 months of an ASM trial had a higher probability of remaining seizure responders (≥50% seizure rate reduction, p < 10-7) or super-responders (≥90%, p < 10-8) over the next 12 months.

INTERPRETATION

In this large cohort, a decrease in multidien IEA cycle strength following initiation of an adjunctive ASM correlated with seizure control for up to 12 months, suggesting that fluctuations in IEA mirror "disease activity" in pharmacoresistant focal epilepsy and may have clinical utility as a biomarker to predict treatment response. ANN NEUROL 2024;95:743-753.

Detection of seizures with ictal tachycardia, using heart rate variability and patient adaptive logistic regression machine learning methods: A hospital-based validation study

OBJECTIVE

Automated seizure detection of focal epileptic seizures is needed for objective seizure quantification to optimize the treatment of patients with epilepsy. Heart rate variability (HRV)-based seizure detection using patient-adaptive threshold with logistic regression machine learning (LRML) methods has presented promising performance in a study with a Danish patient cohort. The objective of this study was to assess the generalizability of the novel LRML seizure detection algorithm by validating it in a dataset recorded from long-term video-EEG monitoring (LTM) in a Brazilian patient cohort.

METHODS

Ictal and inter-ictal ECG-data epochs recorded during LTM were analyzed retrospectively. Thirty-four patients had 107 seizures (79 focal, 28 generalized tonic-clonic [GTC] including focal-to-bilateral-tonic-clonic seizures) eligible for analysis, with a total of 185.5 h recording. Because HRV-based seizure detection is only suitable in patients with marked ictal autonomic change, patients with >50 beats/min change in heart rate during seizures were selected as responders. The patient-adaptive LRML seizure detection algorithm was applied to all elected ECG data, and results were computed separately for responders and non-responders.

RESULTS

The patient-adaptive LRML seizure detection algorithm yielded a sensitivity of 84.8% (95% CI: 75.6-93.9) with a false alarm rate of .25/24 h in the responder group (22 patients, 59 seizures). Twenty-five of the 26 GTC seizures were detected (96.2%), and 25 of the 33 focal seizures without bilateral convulsions were detected (75.8%).

SIGNIFICANCE

The study confirms in a new, independent external dataset the good performance of seizure detection from a previous study and suggests that the method is generalizable. This method seems useful for detecting both generalized and focal epileptic seizures. The algorithm can be embedded in a wearable seizure detection system to alert patients and caregivers of seizures and generate objective seizure counts helping to optimize the treatment of the patients.

Diagnostic utility of prolonged ambulatory video-electroencephalography monitoring

OBJECTIVES

Ambulatory video-electroencephalography (video-EEG) represents a low-cost, convenient and accessible alternative to inpatient video-EEG monitoring, however few studies have examined their diagnostic yield. In this large-scale retrospective study conducted in Australia, we evaluated the efficacy of prolonged ambulatory video-EEG recordings in capturing diagnostic events and resolving the referring question.

METHODS

Sequential adult and paediatric ambulatory video-EEG reports from April 2020 to June 2021 were reviewed retrospectively. Data collection included patient demographics, clinical information, and details of events and EEG abnormalities. Clinical utility was assessed by examining i) time to first diagnostic event, and ii) ability to resolve the referring questions - seizure localisation, quantification, classification, and differentiation (differentiating seizures from non-epileptic events).

RESULTS

Of the 600 reports analysed, 49 % captured at least one event, and 45 % captured interictal abnormalities (epileptiform or non-epileptiform). Seizures, probable psychogenic events (mostly non-convulsive), and other non-epileptic events occurred in 13 %, 23 % and 21 % of recordings respectively, with overlap. Unreported events were captured in 53 (9 %) recordings, and unreported seizures represented more than half of all seizures captured (51 %, 392/773). Nine percent of events were missing clinical, video or electrographic data. A diagnostic event occurred in 244 (41 %) recordings, of which 14 % were captured between the fifth and eighth day of recording. Reported event frequency ≥ 1/week was the only significant predictor of diagnostic event capture. In recordings with both seizures and psychogenic events, unrecognized seizures were frequent, and seizures may be missed if recording is terminated early. The referring question was resolved in 85 % of reports with at least one event, and 53 % of all reports. Specifically, this represented 46 % of reports (235/512) for differentiation of events, and 75 % of reports (27/36) for classification of seizures.

CONCLUSION

Ambulatory video-EEG recordings are of high diagnostic value in capturing clinically relevant events and resolving the referring clinical questions.

Minimum clinical utility standards for wearable seizure detectors: A simulation study

OBJECTIVE

Epilepsy management employs self-reported seizure diaries, despite evidence of seizure underreporting. Wearable and implantable seizure detection devices are now becoming more widely available. There are no clear guidelines about what levels of accuracy are sufficient. This study aimed to simulate clinical use cases and identify the necessary level of accuracy for each.

METHODS

Using a realistic seizure simulator (CHOCOLATES), a ground truth was produced, which was then sampled to generate signals from simulated seizure detectors of various capabilities. Five use cases were evaluated: (1) randomized clinical trials (RCTs), (2) medication adjustment in clinic, (3) injury prevention, (4) sudden unexpected death in epilepsy (SUDEP) prevention, and (5) treatment of seizure clusters. We considered sensitivity (0%-100%), false alarm rate (FAR; 0-2/day), and device type (external wearable vs. implant) in each scenario.

RESULTS

The RCT case was efficient for a wide range of wearable parameters, though implantable devices were preferred. Lower accuracy wearables resulted in subtle changes in the distribution of patients enrolled in RCTs, and therefore higher sensitivity and lower FAR values were preferred. In the clinic case, a wide range of sensitivity, FAR, and device type yielded similar results. For injury prevention, SUDEP prevention, and seizure cluster treatment, each scenario required high sensitivity and yet was minimally influenced by FAR.

SIGNIFICANCE

The choice of use case is paramount in determining acceptable accuracy levels for a wearable seizure detection device. We offer simulation results for determining and verifying utility for specific use case and specific wearable parameters.

Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence

Introduction

Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.

Methods

In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects).

Results

At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h.

Discussion

These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

Real-Time Seizure Detection Using Behind-the-Ear Wearable System

INTRODUCTION

This study examines the usability and comfort of a behind-the-ear seizure detection device called brain seizure detection (BrainSD) that captures ictal electroencephalogram (EEG) data using four scalp electrodes.

METHODS

This is a feasibility study. Thirty-two patients admitted to a level 4 Epilepsy Monitoring Unit were enrolled. The subjects wore BrainSD and the standard 21-channel video-EEG simultaneously. Epileptologists analyzed the EEG signals collected by BrainSD and validated it using video-EEG data to confirm its accuracy. A poststudy survey was completed by each participant to evaluate the comfort and usability of the device. In addition, a focus group of UT Southwestern epileptologists was held to discuss the features they would like to see in a home EEG-based seizure detection device such as BrainSD.

RESULTS

In total, BrainSD captured 11 of the 14 seizures that occurred while the device was being worn. All 11 seizures captured on BrainSD had focal onset, with three becoming bilateral tonic-clonic and one seizure being of subclinical status. The device was worn for an average of 41 hours. The poststudy survey showed that most users found the device comfortable, easy-to-use, and stated they would be interested in using BrainSD. Epileptologists in the focus group expressed a similar interest in BrainSD.

CONCLUSIONS

Brain seizure detection is able to detect EEG signals using four behind-the-ear electrodes. Its comfort, ease-of-use, and ability to detect numerous types of seizures make BrainSD an acceptable at-home EEG detection device from both the patient and provider perspective.

Antidepressant use and the risk of seizure: a meta-analysis of observational studies

PURPOSE

The association between antidepressant use and the risk of seizures remains controversial. Therefore, this meta-analysis examined whether antidepressant use affects the risk of seizures.

METHODS

To identify relevant observational studies, we conducted systematic searches in PubMed and Embase of studies published through May 2023. Random-effects models were used to estimate overall relative risk.

RESULTS

Our meta-analysis included eight studies involving 1,709,878 individuals. Our results showed that selective serotonin reuptake inhibitors (SSRI) (odds ratio [OR] 1.48, 95% confidence interval [CI] 1.32-1.66; P < 0.001) and selective noradrenalin reuptake inhibitors (SNRI) (OR 1.65, 95% CI 1.24-2.19; P = 0.001), but not tricyclic antidepressants (TCA) (OR 1.27, 95% CI 0.84-1.92; P = 0.249), were associated with an increased risk of seizures. Subgroup analyses revealed an OR of 2.35 (95% CI 1.7, 3.24; P < 0.001) among short-term (< 30 days) antidepressant users.

CONCLUSIONS

The findings of this meta-analysis support an increased risk of seizures in new-generation antidepressant users, expanding previous knowledge by demonstrating a more pronounced risk in short-term users.

EEG brain network variability is correlated with other pathophysiological indicators of critical patients in neurology intensive care unit

Continuous electroencephalogram (cEEG) plays a crucial role in monitoring and postoperative evaluation of critical patients with extensive EEG abnormalities. Recently, the temporal variability of dynamic resting-state functional connectivity has emerged as a novel approach to understanding the pathophysiological mechanisms underlying diseases. However, little is known about the underlying temporal variability of functional connections in critical patients admitted to neurology intensive care unit (NICU). Furthermore, considering the emerging field of network physiology that emphasizes the integrated nature of human organisms, we hypothesize that this temporal variability in brain activity may be potentially linked to other physiological functions. Therefore, this study aimed to investigate network variability using fuzzy entropy in 24-hour dynamic resting-state networks of critical patients in NICU, with an emphasis on exploring spatial topology changes over time. Our findings revealed both atypical flexible and robust architectures in critical patients. Specifically, the former exhibited denser functional connectivity across the left frontal and left parietal lobes, while the latter showed predominantly short-range connections within anterior regions. These patterns of network variability deviating from normality may underlie the altered network integrity leading to loss of consciousness and cognitive impairment observed in these patients. Additionally, we explored changes in 24-hour network properties and found simultaneous decreases in brain efficiency, heart rate, and blood pressure between approximately 1 pm and 5 pm. Moreover, we observed a close relationship between temporal variability of resting-state network properties and other physiological indicators including heart rate as well as liver and kidney function. These findings suggest that the application of a temporal variability-based cEEG analysis method offers valuable insights into underlying pathophysiological mechanisms of critical patients in NICU, and may present novel avenues for their condition monitoring, intervention, and treatment.

Association between retinal thickness and disease characteristics in adult epilepsy: A cross-sectional OCT evaluation

OBJECTIVE

Thinning of the peripapillary retinal nerve fiber layer (p-RNFL), as measured by optical coherence tomography (OCT), was recently introduced as a promising marker for cerebral neuronal loss in people with epilepsy (PwE). However, its clinical implication remains to be elucidated. We thus aimed to (1) systematically characterize the extent of the retinal neuroaxonal loss in a broad spectrum of unselected PwE and (2) to evaluate the main clinical determinants.

METHODS

In this prospective study, a spectral-domain OCT evaluation was performed on 98 well-characterized PwE and 85 healthy controls (HCs) (18-55 years of age). All inner retinal layers and the total macula volume were assessed. Group comparisons and linear regression analyses with stepwise backward selection were performed to identify relevant clinical and demographic modulators of the retinal neuroaxonal integrity.

RESULTS

PwE (age: 33.7 ± 10.6 years; 58.2% female) revealed a significant neuroaxonal loss across all assessed retinal layers (global pRNFL, P = 0.001, Δ = 4.24 μm; macular RNFL, P < 0.001, Δ = 0.05 mm3 ; ganglion cell inner plexiform layer, P < 0.001, Δ = 0.11 mm3 ; inner nuclear layer, INL, P = 0.03, Δ = 0.02 mm3 ) as well as significantly reduced total macula volumes (TMV, P < 0.001, Δ = 0.18 mm3 ) compared to HCs (age: 31.2 ± 9.0 years; 57.6% female). The extent of retinal neuroaxonal loss was associated with the occurrence and frequency of tonic-clonic seizures and the number of antiseizure medications, and was most pronounced in male patients.

SIGNIFICANCE

PwE presented an extensive retinal neuroaxonal loss, affecting not only the peripapillary but also macular structures. The noninvasive and economic measurement via OCT bears the potential to establish as a practical tool to inform patient management, as the extent of the retinal neuroaxonal loss reflects aspects of disease severity and sex-specific vulnerability.

PLAIN LANGUAGE SUMMARY

The retina is an extension of the brain and closely connected to it. Thus, cerebral alterations like atrophy reflect also on the retinal level. This is advantageous, as the retina is easily accessible and measureable with help of the optical coherence tomography. Here we report that adults with epilepsy have a significantly thinner retina than healthy persons. Especially people with many big seizures and a lot of medications have a thinner retina. We propose that measurement of the retina can be useful as a marker of disease severity and to inform patient management.

Heart Rate Variability as a Tool for Seizure Prediction: A Scoping Review

The most critical burden for People with Epilepsy (PwE) is represented by seizures, the unpredictability of which severely impacts quality of life. The design of real-time warning systems that can detect or even predict ictal events would enhance seizure management, leading to high benefits for PwE and their caregivers. In the past, various research works highlighted that seizure onset is anticipated by significant changes in autonomic cardiac control, which can be assessed through heart rate variability (HRV). This manuscript conducted a scoping review of the literature analyzing HRV-based methods for detecting or predicting ictal events. An initial search on the PubMed database returned 402 papers, 72 of which met the inclusion criteria and were included in the review. These results suggest that seizure detection is more accurate in neonatal and pediatric patients due to more significant autonomic modifications during the ictal transitions. In addition, conventional metrics are often incapable of capturing cardiac autonomic variations and should be replaced with more advanced methodologies, considering non-linear HRV features and machine learning tools for processing them. Finally, studies investigating wearable systems for heart monitoring denoted how HRV constitutes an efficient biomarker for seizure detection in patients presenting significant alterations in autonomic cardiac control during ictal events.

The time-evolving epileptic brain network: concepts, definitions, accomplishments, perspectives

Epilepsy is now considered a network disease that affects the brain across multiple levels of spatial and temporal scales. The paradigm shift from an epileptic focus-a discrete cortical area from which seizures originate-to a widespread epileptic network-spanning lobes and hemispheres-considerably advanced our understanding of epilepsy and continues to influence both research and clinical treatment of this multi-faceted high-impact neurological disorder. The epileptic network, however, is not static but evolves in time which requires novel approaches for an in-depth characterization. In this review, we discuss conceptual basics of network theory and critically examine state-of-the-art recording techniques and analysis tools used to assess and characterize a time-evolving human epileptic brain network. We give an account on current shortcomings and highlight potential developments towards an improved clinical management of epilepsy.

A ResNet-LSTM hybrid model for predicting epileptic seizures using a pretrained model with supervised contrastive learning

In this paper, we propose a method for predicting epileptic seizures using a pre-trained model utilizing supervised contrastive learning and a hybrid model combining residual networks (ResNet) and long short-term memory (LSTM). The proposed training approach encompasses three key phases: pre-processing, pre-training as a pretext task, and training as a downstream task. In the pre-processing phase, the data is transformed into a spectrogram image using short time Fourier transform (STFT), which extracts both time and frequency information. This step compensates for the inherent complexity and irregularity of electroencephalography (EEG) data, which often hampers effective data analysis. During the pre-training phase, augmented data is generated from the original dataset using techniques such as band-stop filtering and temporal cutout. Subsequently, a ResNet model is pre-trained alongside a supervised contrastive loss model, learning the representation of the spectrogram image. In the training phase, a hybrid model is constructed by combining ResNet, initialized with weight values from the pre-trained model, and LSTM. This hybrid model extracts image features and time information to enhance prediction accuracy. The proposed method's effectiveness is validated using datasets from CHB-MIT and Seoul National University Hospital (SNUH). The method's generalization ability is confirmed through Leave-one-out cross-validation. From the experimental results measuring accuracy, sensitivity, and false positive rate (FPR), CHB-MIT was 91.90%, 89.64%, 0.058 and SNUH was 83.37%, 79.89%, and 0.131. The experimental results demonstrate that the proposed method outperforms the conventional methods.

Prospective validation of a seizure diary forecasting falls short

OBJECTIVE

Recently, a deep learning 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 (BSS) compared random forecasts and simple moving average forecasts to the AI.

RESULTS

The AI had an AUC of 0.82. At the group level, the AI outperformed random forecasting (BSS=0.53). 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 (non-verified) diaries (with presumed under-reporting) 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 this prospective cohort, suggesting that the AI model should be replaced.

The role of trained and untrained dogs in the detection and warning of seizures

Seizure unpredictability plays a major role in disability and decreased quality of life in people with epilepsy. Dogs have been used to assist people with disabilities and have shown promise in detecting seizures. There have been reports of trained seizure-alerting dogs (SADs) successfully detecting when a seizure is occurring or indicating imminent seizures, allowing patients to take preventative measures. Untrained pet dogs have also shown the ability to detect seizures and provide comfort and protection during and after seizures. Dogs' exceptional olfactory abilities and sensitivity to human cues could contribute to their seizure-detection capabilities. This has been supported by studies in which dogs have distinguished between epileptic seizure and non-seizure sweat samples, probably though the detection of volatile organic compounds (VOCs). However, the existing literature has limitations, with a lack of well-controlled, prospective studies and inconsistencies in reported timings of alerting behaviours. More research is needed to standardize reporting and validate the results. Advances in VOC profiling could aid in distinguishing seizure types and developing rapid and unbiased seizure detection methods. In conclusion, using dogs in epilepsy management shows considerable promise, but further research is needed to fully validate their effectiveness and potential as valuable companions for people with epilepsy.

Measuring Real-Time Medication Effects From Electroencephalography

PURPOSE

Evaluating the effects of antiseizure medication (ASM) on patients with epilepsy remains a slow and challenging process. Quantifiable noninvasive markers that are measurable in real-time and provide objective and useful information could guide clinical decision-making. We examined whether the effect of ASM on patients with epilepsy can be quantitatively measured in real-time from EEGs.

METHODS

This retrospective analysis was conducted on 67 patients in the long-term monitoring unit at Boston Children's Hospital. Two 30-second EEG segments were selected from each patient premedication and postmedication weaning for analysis. Nonlinear measures including entropy and recurrence quantitative analysis values were computed for each segment and compared before and after medication weaning.

RESULTS

Our study found that ASM effects on the brain were measurable by nonlinear recurrence quantitative analysis on EEGs. Highly significant differences ( P < 1e-11) were found in several nonlinear measures within the seizure zone in response to antiseizure medication. Moreover, the size of the medication effect correlated with a patient's seizure frequency, seizure localization, number of medications, and reported seizure frequency reduction on medication.

CONCLUSIONS

Our findings show the promise of digital biomarkers to measure medication effects and epileptogenicity.

Effectiveness of Yoga Intervention in Reducing Felt Stigma in Adults With Epilepsy: A Randomized Controlled Trial

BACKGROUND AND OBJECTIVES

Persons with epilepsy are afflicted with comorbidities such as stigma, anxiety, and depression which have a significant impact on their quality of life. These comorbidities remain largely unaddressed in resource-limited countries. This randomized controlled trial (RCT) aimed to investigate whether yoga and psychoeducation were effective in reducing felt stigma (primary outcome), neuropsychiatric outcomes, and seizure frequency, as compared with sham yoga and psychoeducation in persons with epilepsy.

METHODS

This was an assessor-blinded, sham yoga-controlled RCT. Patients clinically diagnosed with epilepsy, aged 18-60 years, and scoring higher than the cutoff score for felt stigma as measured by the Kilifi Stigma Scale (KSS) in our population were randomly assigned to receive either yoga therapy plus psychoeducation (intervention) or sham yoga therapy plus psychoeducation (comparator) for a duration of 3 months. The primary outcome was a significant decrease in felt stigma as compared with the comparator arm as measured by the KSS. Primary and secondary outcomes (seizure frequency, quality of life, anxiety, depression, mindfulness, trait rumination, cognitive impairment, emotion regulation) were assessed at baseline, 3 months, and 6 months. Parametric/nonparametric analysis of covariance and the χ2 test were used to compare the 2 arms.

RESULTS

A total of 160 patients were enrolled in the trial. At the end of the follow-up period (6 months), the intervention arm reported significant reduction in felt stigma as compared with the control arm (Cohen's d = 0.23, 95% CI -0.08 to 0.55, p = 0.006). Significantly higher odds of >50% seizure reduction (odds ratio [OR] 4.11, 95% CI 1.34-14.69, p = 0.01) and complete seizure remission (OR 7.4, 95% CI 1.75-55.89, p = 0.005) were also observed in the intervention group. The intervention group showed significant improvement in symptoms of anxiety, cognitive impairment, mindfulness, and quality of life relative to the control group at the end of follow-up period (p < 0.05).

DISCUSSION

Yoga can alleviate the burden of epilepsy and improve the overall quality of life in epilepsy by reducing perceived stigma.

TRIAL REGISTRATION INFORMATION

Clinical Trials Registry of India (CTRI/2017/04/008385).

CLASSIFICATION OF EVIDENCE

This study provides Class I evidence that yoga reduces felt stigma in adult patients with epilepsy.

Differentiation of subclinical and clinical electrographic events in long-term electroencephalographic recordings

OBJECTIVE

With the advent of ultra-long-term recordings for monitoring of epilepsies, the interpretation of results of isolated electroencephalographic (EEG) recordings covering only selected brain regions attracts considerable interest. In this context, the question arises of whether detected ictal EEG patterns correspond to clinically manifest seizures or rather to purely electrographic events, that is, subclinical events.

METHODS

EEG patterns from 268 clinical seizures and 252 subclinical electrographic events from 50 patients undergoing video-EEG monitoring were analyzed. Features extracted included predominant frequency band, duration, association with rhythmic muscle artifacts, spatial extent, and propagation patterns. Classification using logistic regression was performed based on data from the whole dataset of 10-20 system EEG recordings and from a subset of two temporal electrode contacts.

RESULTS

Correct separation of clinically manifest and purely electrographic events based on 10-20 system EEG recordings was possible in up to 83.8% of events, depending on the combination of features included. Correct classification based on two-channel recordings was only slightly inferior, achieving 78.6% accuracy; 74.4% and 74.8%, respectively, of events could be correctly classified when using duration alone with either electrode set, although classification accuracies were lower for some subgroups of seizures, particularly focal aware seizures and epileptic arousals.

SIGNIFICANCE

A correct classification of subclinical versus clinical EEG events was possible in 74%-83% of events based on full EEG recordings, and in 74%-78% when considering only a subset of two electrodes, matching the channel number available from new implantable diagnostic devices. This is a promising outcome, suggesting that ultra-long-term low-channel EEG recordings may provide sufficient information for objective seizure diaries. Intraindividual optimization using high numbers of ictal events may further improve separation, provided that supervised learning with external validation is feasible.

Seizure forecasting using minimally invasive, ultra-long-term subcutaneous electroencephalography: Individualized intrapatient models

OBJECTIVE

One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG.

METHODS

We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation.

RESULTS

Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence.

SIGNIFICANCE

This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.

Diagnostic yield and limitations of in-hospital documentation in patients with epilepsy

OBJECTIVE

To determine the diagnostic yield of in-hospital video-electroencephalography (EEG) monitoring to document seizures in patients with epilepsy.

METHODS

Retrospective analysis of electronic seizure documentation at the University Hospital Freiburg (UKF) and at King's College London (KCL). Statistical assessment of the role of the duration of monitoring, and subanalyses on presurgical patient groups and patients undergoing reduction of antiseizure medication.

RESULTS

Of more than 4800 patients with epilepsy undergoing in-hospital recordings at the two institutions since 2005, seizures with documented for 43% (KCL) and 73% (UKF).. Duration of monitoring was highly significantly associated with seizure recordings (p < .0001), and presurgical patients as well as patients with drug reduction had a significantly higher diagnostic yield (p < .0001). Recordings with a duration of >5 days lead to additional new seizure documentation in only less than 10% of patients.

SIGNIFICANCE

There is a need for the development of new ambulatory monitoring strategies to document seizures for diagnostic and monitoring purposes for a relevant subgroup of patients with epilepsy in whom in-hospital monitoring fails to document seizures.

Artificial intelligence-enhanced epileptic seizure detection by wearables

OBJECTIVE

Wrist- or ankle-worn devices are less intrusive than the widely used electroencephalographic (EEG) systems for monitoring epileptic seizures. Using custom-developed deep-learning seizure detection models, we demonstrate the detection of a broad range of seizure types by wearable signals.

METHODS

Patients admitted to the epilepsy monitoring unit were enrolled and asked to wear wearable sensors on either wrists or ankles. We collected patients' electrodermal activity, accelerometry (ACC), and photoplethysmography, from which blood volume pulse (BVP) is derived. Board-certified epileptologists determined seizure onset, offset, and types using video and EEG recordings per the International League Against Epilepsy 2017 classification. We applied three neural network models-a convolutional neural network (CNN) and a CNN-long short-term memory (LSTM)-based generalized detection model and an autoencoder-based personalized detection model-to the raw time-series sensor data to detect seizures and utilized performance measures, including sensitivity, false positive rate (the number of false alarms divided by the total number of nonseizure segments), number of false alarms per day, and detection delay. We applied a 10-fold patientwise cross-validation scheme to the multisignal biosensor data and evaluated model performance on 28 seizure types.

RESULTS

We analyzed 166 patients (47.6% female, median age = 10.0 years) and 900 seizures (13 254 h of sensor data) for 28 seizure types. With a CNN-LSTM-based seizure detection model, ACC, BVP, and their fusion performed better than chance; ACC and BVP data fusion reached the best detection performance of 83.9% sensitivity and 35.3% false positive rate. Nineteen of 28 seizure types could be detected by at least one data modality with area under receiver operating characteristic curve > .8 performance.

SIGNIFICANCE

Results from this in-hospital study contribute to a paradigm shift in epilepsy care that entails noninvasive seizure detection, provides time-sensitive and accurate data on additional clinical seizure types, and proposes a novel combination of an out-of-the-box monitoring algorithm with an individualized person-oriented seizure detection approach.

Lightweight Seizure Detection Based on Multi-Scale Channel Attention

Epilepsy is one kind of neurological disease characterized by recurring seizures. Recurrent seizures can cause ongoing negative mental and cognitive damage to the patient. Therefore, timely diagnosis and treatment of epilepsy are crucial for patients. Manual electroencephalography (EEG) signals analysis is time and energy consuming, making automatic detection using EEG signals particularly important. Many deep learning algorithms have thus been proposed to detect seizures. These methods rely on expensive and bulky hardware, which makes them unsuitable for deployment on devices with limited resources due to their high demands on computer resources. In this paper, we propose a novel lightweight neural network for seizure detection using pure convolutions, which is composed of inverted residual structure and multi-scale channel attention mechanism. Compared with other methods, our approach significantly reduces the computational complexity, making it possible to deploy on low-cost portable devices for seizures detection. We conduct experiments on the CHB-MIT dataset and achieves 98.7% accuracy, 98.3% sensitivity and 99.1% specificity with 2.68[Formula: see text]M multiply-accumulate operations (MACs) and only 88[Formula: see text]K parameters.

Automated detection of absence seizures using a wearable electroencephalographic device: a phase 3 validation study and feasibility of automated behavioral testing

OBJECTIVE

Our primary goal was to measure the accuracy of fully automated absence seizure detection, using a wearable electroencephalographic (EEG) device. As a secondary goal, we also tested the feasibility of automated behavioral testing triggered by the automated detection.

METHODS

We conducted a phase 3 clinical trial (NCT04615442), with a prospective, multicenter, blinded study design. The input was the one-channel EEG recorded with dry electrodes embedded into a wearable headband device connected to a smartphone. The seizure detection algorithm was developed using artificial intelligence (convolutional neural networks). During the study, the predefined algorithm, with predefined cutoff value, analyzed the EEG in real time. The gold standard was derived from expert evaluation of simultaneously recorded full-array video-EEGs. In addition, we evaluated the patients' responsiveness to the automated alarms on the smartphone, and we compared it with the behavioral changes observed in the clinical video-EEGs.

RESULTS

We recorded 102 consecutive patients (57 female, median age = 10 years) on suspicion of absence seizures. We recorded 364 absence seizures in 39 patients. Device deficiency was 4.67%, with a total recording time of 309 h. Average sensitivity per patient was 78.83% (95% confidence interval [CI] = 69.56%-88.11%), and median sensitivity was 92.90% (interquartile range [IQR] = 66.7%-100%). The average false detection rate was .53/h (95% CI = .32-.74). Most patients (n = 66, 64.71%) did not have any false alarms. The median F1 score per patient was .823 (IQR = .57-1). For the total recording duration, F1 score was .74. We assessed the feasibility of automated behavioral testing in 36 seizures; it correctly documented nonresponsiveness in 30 absence seizures, and responsiveness in six electrographic seizures.

SIGNIFICANCE

Automated detection of absence seizures with a wearable device will improve seizure quantification and will promote assessment of patients in their home environment. Linking automated seizure detection to automated behavioral testing will provide valuable information from wearable devices.

Learning to generalize seizure forecasts

OBJECTIVE

Epilepsy is characterized by spontaneous seizures that recur at unexpected times. Nonetheless, using years-long electroencephalographic (EEG) recordings, we previously found that patient-reported seizures consistently occur when interictal epileptiform activity (IEA) cyclically builds up over days. This multidien (multiday) interictal-ictal relationship, which is shared across patients, may bear phasic information for forecasting seizures, even if individual patterns of seizure timing are unknown. To test this rigorously in a large retrospective dataset, we pretrained algorithms on data recorded from a group of patients, and forecasted seizures in other, previously unseen patients.

METHODS

We used retrospective long-term data from participants (N = 159) in the RNS System clinical trials, including intracranial EEG recordings (icEEG), and from two participants in the UNEEG Medical clinical trial of a subscalp EEG system (sqEEG). Based on IEA detections, we extracted instantaneous multidien phases and trained generalized linear models (GLMs) and recurrent neural networks (RNNs) to forecast the probability of seizure occurrence at a 24-h horizon.

RESULTS

With GLMs and RNNs, seizures could be forecasted above chance in 79% and 81% of previously unseen subjects with a median discrimination of area under the curve (AUC) = .70 and .69 and median Brier skill score (BSS) = .07 and .08. In direct comparison, individualized models had similar median performance (AUC = .67, BSS = .08), but for fewer subjects (60%). Moreover, calibration of pretrained models could be maintained to accommodate different seizure rates across subjects.

SIGNIFICANCE

Our findings suggest that seizure forecasting based on multidien cycles of IEA can generalize across patients, and may drastically reduce the amount of data needed to issue forecasts for individuals who recently started collecting chronic EEG data. In addition, we show that this generalization is independent of the method used to record seizures (patient-reported vs. electrographic) or IEA (icEEG vs. sqEEG).

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals

Introduction

This study evaluated the accuracy of motion signals extracted from video monitoring data to differentiate epileptic motor seizures in patients with drug-resistant epilepsy. 3D near-infrared video was recorded by the Nelli® seizure monitoring system (Tampere, Finland).

Methods

10 patients with 130 seizures were included in the training dataset, and 17 different patients with 98 seizures formed the testing dataset. Only seizures with unequivocal hyperkinetic, tonic, and tonic-clonic semiology were included. Motion features from the catch22 feature collection extracted from video were explored to transform the patients' videos into numerical time series for clustering and visualization.

Results

Changes in feature generation provided incremental discrimination power to differentiate between hyperkinetic, tonic, and tonic-clonic seizures. Temporal motion features showed the best results in the unsupervised clustering analysis. Using these features, the system differentiated hyperkinetic, tonic and tonic-clonic seizures with 91, 88, and 45% accuracy after 100 cross-validation runs, respectively. F1-scores were 93, 90, and 37%, respectively. Overall accuracy and f1-score were 74%.

Conclusion

The selected features of motion distinguished semiological differences within epileptic seizure types, enabling seizure classification to distinct motor seizure types. Further studies are needed with a larger dataset and additional seizure types. These results indicate the potential of video-based hybrid seizure monitoring systems to facilitate seizure classification improving the algorithmic processing and thus streamlining the clinical workflow for human annotators in hybrid (algorithmic-human) seizure monitoring systems.

Getting Under the Skin of Seizure Monitoring: A Subcutaneous EEG Tool to Keep a Tally Over the Long Haul

Detecting Temporal Lobe Seizures in Ultra Long-Term Subcutaneous EEG Using Algorithm-Based Data Reduction Remvig LS, Duun-Henriksen J, Fürbass F, Hartmann M, Viana PF, Kappel Overby AM, Weisdorf S, Richardson MP, Beniczky S, Kjaer TW. Clin Neurophysiol . 2022;142:86-93. doi:10.1016/j.clinph.2022.07.504 . PMID: 35987094 Objective: Ultra long-term monitoring with subcutaneous EEG (sqEEG) offers objective outpatient recording of electrographic seizures as an alternative to self-reported epileptic seizure diaries. This methodology requires an algorithm-based automatic seizure detection to indicate periods of potential seizure activity to reduce the time spent on visual review. The objective of this study was to evaluate the performance of a sqEEG-based automatic seizure detection algorithm. Methods: A multicenter cohort of subjects using sqEEG were analyzed, including nine people with epilepsy (PWE) and 12 healthy subjects, recording a total of 965 days. The automatic seizure detections of a deep-neural-network algorithm were compared to annotations from three human experts. Results: Data reduction ratios were 99.6% in PWE and 99.9% in the control group. The cross-PWE sensitivity was 86% (median 80%, range 69-100% when PWE were evaluated individually), and the corresponding median false detection rate was 2.4 detections per 24 hours (range: 2.0-13.0). Conclusions: Our findings demonstrated that step one in a sqEEG-based semi-automatic seizure detection/review process can be performed with high sensitivity and clinically applicable specificity. Significance: Ultra long-term sqEEG bears the potential of improving objective seizure quantification.

The role of molecular chaperones in the mechanisms of epileptogenesis

Epilepsy is a group of neurological diseases which requires significant economic costs for the treatment and care of patients. The central point of epileptogenesis stems from the failure of synaptic signal transmission mechanisms, leading to excessive synchronous excitation of neurons and characteristic epileptic electroencephalogram activity, in typical cases being manifested as seizures and loss of consciousness. The causes of epilepsy are extremely diverse, which is one of the reasons for the complexity of selecting a treatment regimen for each individual case and the high frequency of pharmacoresistant cases. Therefore, the search for new drugs and methods of epilepsy treatment requires an advanced study of the molecular mechanisms of epileptogenesis. In this regard, the investigation of molecular chaperones as potential mediators of epileptogenesis seems promising because the chaperones are involved in the processing and regulation of the activity of many key proteins directly responsible for the generation of abnormal neuronal excitation in epilepsy. In this review, we try to systematize current data on the role of molecular chaperones in epileptogenesis and discuss the prospects for the use of chemical modulators of various chaperone groups' activity as promising antiepileptic drugs.

Wearable detection of tonic seizures in childhood epilepsy: An exploratory cohort study

OBJECTIVE

To investigate the performance of a multimodal wearable device for the offline detection of tonic seizures (TS) in a pediatric childhood epilepsy cohort, with a focus on patients with Lennox-Gastaut syndrome.

METHODS

Parallel with prolonged video-electroencephalography (EEG), the Plug 'n Patch system, a multimodal wearable device using the Sensor Dot and replaceable electrode adhesives, was used to detect TS. Multiple biosignals were recorded: behind-the-ear EEG, surface electromyography, electrocardiography, and accelerometer/gyroscope. Biosignals were annotated blindly by a neurologist. Seizure characteristics were described, and performance was assessed by sensitivity, positive predictive value (PPV), F1 score, and false alarm rate (FAR) per hour. Performance was compared to seizure diaries kept by the caretaker.

RESULTS

Ninety-nine TS were detected in 13 patients. Seven patients (54%) had Lennox-Gastaut syndrome and six patients (46%) had other forms of (developmental) epileptic encephalopathies or drug-resistant epilepsy. All but one patient had intellectual disability. Overall sensitivity was 41%, with a PPV of 9%, an F1 score of 14%, and a median FAR per hour of 0.75. Performance increased to an F1 score of 66% for nightly seizures lasting at least 10 s (sensitivity 66%, PPV 66%) and 71% for nightly seizures lasting at least 20 s (sensitivity 62%, PPV 82%). For these seizures there were no false alarms in 10 of 13 patients. Sensitivity of seizure diaries reached a maximum of 52% for prolonged (≥20 s) nightly seizures, even though caretakers slept in the same room.

SIGNIFICANCE

We showed that it is feasible to use a multimodal wearable device with multiple adhesive sites in children with epilepsy and intellectual disability. For prolonged nightly seizures, offline manual detection of TS outperformed seizure diaries. The recognition of seizure-specific signatures using multiple modalities can help in the development of automated TS detection algorithms.

Non-electroencephalogram-based seizure detection devices: State of the art and future perspectives

INTRODUCTION AND PURPOSE

The continuously expanding research and development of wearable devices for automated seizure detection in epilepsy uses mostly non-invasive technology. Real-time alarms, triggered by seizure detection devices, are needed for safety and prevention to decrease seizure-related morbidity and mortality, as well as objective quantification of seizure frequency and severity. Our review strives to provide a state-of-the-art on automated seizure detection using non-invasive wearable devices in an ambulatory (home) environment and to highlight the prospects for future research.

METHODS

A joint working group of the International League Against Epilepsy (ILAE) and the International Federation of Clinical Neurophysiology (IFCN) recently published a clinical practice guideline on automated seizure detection using wearable devices. We updated the systematic literature search for the period since the last search by the joint working group. We selected studies qualifying minimally as phase-2 clinical validation trials, in accordance with standards for testing and validation of seizure detection devices.

RESULTS

High-level evidence (phases 3 and 4) is available only for the detection of tonic-clonic seizures and major motor seizures when using wearable devices based on accelerometry, surface electromyography (EMG), or a multimodal device combining accelerometry and heart rate. The reported sensitivity of these devices is 79.4-96%, with a false alarm rate of 0.20-1.92 per 24 hours (0-0.03 per night). A single phase-3 study validated the detection of absence seizures using a single-channel wearable EEG device. Two phase-4 studies showed overall user satisfaction with wearable seizure detection devices, which helped decrease injuries related to tonic-clonic seizures. Overall satisfaction, perceived sensitivity, and improvement in quality-of-life were significantly higher for validated devices.

CONCLUSIONS

Among the vast number of studies published on seizure detection devices, most are strongly affected by potential bias, providing a too-optimistic perspective. By applying the standards for clinical validation studies, potential bias can be reduced, and the quality of a continuously growing number of studies in this field can be assessed and compared. The ILAE-IFCN clinical practice guideline on automated seizure detection using wearable devices recommends using clinically validated wearable devices for automated detection of tonic-clonic seizures when significant safety concerns exist. The studies published after the guideline was issued only provide incremental knowledge and would not change the current recommendations.

In-ear integrated sensor array for the continuous monitoring of brain activity and of lactate in sweat

Owing to the proximity of the ear canal to the central nervous system, in-ear electrophysiological systems can be used to unobtrusively monitor brain states. Here, by taking advantage of the ear's exocrine sweat glands, we describe an in-ear integrated array of electrochemical and electrophysiological sensors placed on a flexible substrate surrounding a user-generic earphone for the simultaneous monitoring of lactate concentration and brain states via electroencephalography, electrooculography and electrodermal activity. In volunteers performing an acute bout of exercise, the device detected elevated lactate levels in sweat concurrently with the modulation of brain activity across all electroencephalography frequency bands. Simultaneous and continuous unobtrusive in-ear monitoring of metabolic biomarkers and brain electrophysiology may allow for the discovery of dynamic and synergetic interactions between brain and body biomarkers in real-world settings for long-term health monitoring or for the detection or monitoring of neurodegenerative diseases.

Deep learning for automated detection of generalized paroxysmal fast activity in Lennox-Gastaut syndrome

OBJECTIVES

Generalized paroxysmal fast activity (GPFA) is a key electroencephalographic (EEG) feature of Lennox-Gastaut Syndrome (LGS). Automated analysis of scalp EEG has been successful in detecting more typical abnormalities. Automatic detection of GPFA has been more challenging, due to its variability from patient to patient and similarity to normal brain rhythms. In this work, a deep learning model is investigated for detection of GPFA events and estimating their overall burden from scalp EEG.

METHODS

Data from 10 patients recorded during four ambulatory EEG monitoring sessions are used to generate and validate the model. All patients had confirmed LGS and were recruited into a trial for thalamic deep-brain stimulation therapy (ESTEL Trial).

RESULTS

The correlation coefficient between manual and model estimates of event counts was r2 = 0.87, and for total burden was r2 = 0.91. The average GPFA detection sensitivity was 0.876, with an average false-positive rate of 3.35 per minute. There was no significant difference found between patients with early or delayed deep brain stimulation (DBS) treatment, or those with active vagal nerve stimulation (VNS).

CONCLUSIONS

Overall, the deep learning model was able to accurately detect GPFA and provide accurate estimates of the overall GPFA burden and electrographic event counts, albeit with a high false-positive rate.

SIGNIFICANCE

Automated GPFA detection may enable automated calculation of EEG biomarkers of burden of disease in LGS.

Wrist-worn smartwatch and predictive models for seizures

OBJECTIVE

This study was undertaken to describe extracerebral biosignal characteristics of overall and various seizure types as compared with baseline physical activities using multimodal devices (Empatica E4); develop predictive models for overall and each seizure type; and assess diagnostic performance of each model.

METHODS

We prospectively recruited patients with focal epilepsy who were admitted to the epilepsy monitoring unit for presurgical evaluation during January to December 2020. All study participants were simultaneously applied gold standard long-term video-electroencephalographic (EEG) monitoring and an index test, E4. Two certified epileptologists independently determined whether captured events were seizures and then indicated ictal semiology and EEG information. Both were blind to multimodal biosignal findings detected by E4. Biosignals during 5-min epochs of both seizure events and baseline were collected and compared. Predictive models for occurrence overall and of each seizure type were developed using a generalized estimating equation. Diagnostic performance of each model was then assessed.

RESULTS

Thirty patients had events recorded and were recruited for analysis. One hundred eight seizure events and 120 baseline epochs were collected. Heart rate (HR), acceleration (ACC), and electrodermal activity (EDA) but not temperature were significantly elevated during seizures. Cluster analysis showed trends of greatest elevation of HR and ACC in bilateral tonic-clonic seizures (BTCs), as compared with non-BTCs and isolated auras. HR and ACC were independent predictors for overall seizure types, BTCs, and non-BTCs, whereas only HR was a predictor for isolated aura. Diagnostic performance including sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve of the predictive model for overall seizures were 77.78%, 60%, and .696 (95% confidence interval = .628-.764), respectively.

SIGNIFICANCE

Multimodal extracerebral biosignals (HR, ACC, EDA) detected by a wrist-worn smartwatch can help differentiate between epileptic seizures and normal physical activities. It would be worthwhile to implement our predictive algorithms in commercial seizure detection devices. However, larger studies to externally validate our predictive models are required.

Text mining of electronic health records can validate a register-based diagnosis of epilepsy and subgroup into focal and generalized epilepsy

OBJECTIVE

Combining population-based health registries and electronic health records offers the opportunity to create large, phenotypically detailed patient cohorts of high quality. In this study, we used text mining of clinical notes to confirm International Classification of Diseases, 10th Revision (ICD-10)-registered epilepsy diagnoses and classify patients according to focal and generalized epilepsy types.

METHODS

Using the Danish National Patient Registry, we identified patients who between 2006 and 2016 received an ICD-10 diagnosis of epilepsy. To validate the epilepsy diagnosis and stratify patients into focal and generalized epilepsy types, we constructed dictionaries for text mining-based extraction of clinical notes. Two physicians manually reviewed the clinical notes for a total of 527 patients and assigned epilepsy diagnoses, which were compared with the text-mined diagnoses.

RESULTS

We identified 23 632 patients with an ICD-10 diagnosis of epilepsy, of whom 50% were registered with an unspecified epilepsy diagnosis. In total, 11 211 patients were considered likely to have epilepsy by text mining, with an F1 measure ranging from 82% to 90%. Manual review of the electronic health records for 310 patients revealed a false discovery rate of 29%. This rate was decreased to 4% by the text mining algorithm. The weighted average F1 measure for text mining-assigned epilepsy types was 79% (82% for focal and 76% for generalized epilepsy). Text mining successfully assigned a focal or generalized epilepsy type to 92% of the text mining-eligible patients registered with unspecified epilepsy.

SIGNIFICANCE

Text mining of electronic health records can be used to establish a patient cohort with much higher likelihood of having a diagnosis of epilepsy and a focal or generalized epilepsy type compared to the cohort created from ICD-10 epilepsy codes alone. We believe the concept will be essential for future genome-wide and phenome-wide association studies and subsequently the development of precision medicine for epilepsy patients.

A novel approach to automatic seizure detection using computer vision and independent component analysis

OBJECTIVE

Epilepsy is a neurological disease that affects ~50 million people worldwide, 30% of which have refractory epilepsy and recurring seizures, which may contribute to higher anxiety levels and poorer quality of life. Seizure detection may contribute to addressing some of the challenges associated with this condition, by providing information to health professionals regarding seizure frequency, type, and/or location in the brain, thereby improving diagnostic accuracy and medication adjustment, and alerting caregivers or emergency services of dangerous seizure episodes. The main focus of this work was the development of an accurate video-based seizure-detection method that ensured unobtrusiveness and privacy preservation, and provided novel approaches to reduce confounds and increase reliability.

METHODS

The proposed approach is a video-based seizure-detection method based on optical flow, principal component analysis, independent component analysis, and machine learning classification. This method was tested on a set of 21 tonic-clonic seizure videos (5-30 min each, total of 4 h and 36 min of recordings) from 12 patients using leave-one-subject-out cross-validation.

RESULTS

High accuracy levels were observed, namely a sensitivity and specificity of 99.06% ± 1.65% at the equal error rate and an average latency of 37.45 ± 1.31 s. When compared to annotations by health care professionals, the beginning and ending of seizures was detected with an average offset of 9.69 ± 0.97 s.

SIGNIFICANCE

The video-based seizure-detection method described herein is highly accurate. Moreover, it is intrinsically privacy preserving, due to the use of optical flow motion quantification. In addition, given our novel independence-based approach, this method is robust to different lighting conditions, partial occlusions of the patient, and other movements in the video frame, thereby setting the base for accurate and unobtrusive seizure detection.

Perceived seizure risk in epilepsy: Chronic electronic surveys with and without concurrent electroencephalography

OBJECTIVE

Previous studies suggested that patients with epilepsy might be able to forecast their own seizures. This study aimed to assess the relationships between premonitory symptoms, perceived seizure risk, and future and recent self-reported and electroencephalographically (EEG)-confirmed seizures in ambulatory patients with epilepsy in their natural home environments.

METHODS

Long-term e-surveys were collected from patients with and without concurrent EEG recordings. Information obtained from the e-surveys included medication adherence, sleep quality, mood, stress, perceived seizure risk, and seizure occurrences preceding the survey. EEG seizures were identified. Univariate and multivariate generalized linear mixed-effect regression models were used to estimate odds ratios (ORs) for the assessment of the relationships. Results were compared with the seizure forecasting classifiers and device forecasting literature using a mathematical formula converting OR to equivalent area under the curve (AUC).

RESULTS

Fifty-four subjects returned 10 269 e-survey entries, with four subjects acquiring concurrent EEG recordings. Univariate analysis revealed that increased stress (OR = 2.01, 95% confidence interval [CI] = 1.12-3.61, AUC = .61, p = .02) was associated with increased relative odds of future self-reported seizures. Multivariate analysis showed that previous self-reported seizures (OR = 5.37, 95% CI = 3.53-8.16, AUC = .76, p < .001) were most strongly associated with future self-reported seizures, and high perceived seizure risk (OR = 3.34, 95% CI = 1.87-5.95, AUC = .69, p < .001) remained significant when prior self-reported seizures were added to the model. No correlation with medication adherence was found. No significant association was found between e-survey responses and subsequent EEG seizures.

SIGNIFICANCE

Our results suggest that patients may tend to self-forecast seizures that occur in sequential groupings and that low mood and increased stress may be the result of previous seizures rather than independent premonitory symptoms. Patients in the small cohort with concurrent EEG showed no ability to self-predict EEG seizures. The conversion from OR to AUC values facilitates direct comparison of performance between survey and device studies involving survey premonition and forecasting.

Multimodal nocturnal seizure detection in children with epilepsy: A prospective, multicenter, long-term, in-home trial

OBJECTIVE

There is a pressing need for reliable automated seizure detection in epilepsy care. Performance evidence on ambulatory non-electroencephalography-based seizure detection devices is low, and evidence on their effect on caregiver's stress, sleep, and quality of life (QoL) is still lacking. We aimed to determine the performance of NightWatch, a wearable nocturnal seizure detection device, in children with epilepsy in the family home setting and to assess its impact on caregiver burden.

METHODS

We conducted a phase 4, multicenter, prospective, video-controlled, in-home NightWatch implementation study (NCT03909984). We included children aged 4-16 years, with ≥1 weekly nocturnal major motor seizure, living at home. We compared a 2-month baseline period with a 2-month NightWatch intervention. The primary outcome was the detection performance of NightWatch for major motor seizures (focal to bilateral or generalized tonic-clonic [TC] seizures, focal to bilateral or generalized tonic seizures lasting >30 s, hyperkinetic seizures, and a remainder category of focal to bilateral or generalized clonic seizures and "TC-like" seizures). Secondary outcomes included caregivers' stress (Caregiver Strain Index [CSI]), sleep (Pittsburgh Quality of Sleep Index), and QoL (EuroQol five-dimension five-level scale).

RESULTS

We included 53 children (55% male, mean age = 9.7 ± 3.6 years, 68% learning disability) and analyzed 2310 nights (28 173 h), including 552 major motor seizures. Nineteen participants did not experience any episode of interest during the trial. The median detection sensitivity per participant was 100% (range = 46%-100%), and the median individual false alarm rate was .04 per hour (range = 0-.53). Caregiver's stress decreased significantly (mean total CSI score = 8.0 vs. 7.1, p = .032), whereas caregiver's sleep and QoL did not change significantly during the trial.

SIGNIFICANCE

The NightWatch system demonstrated high sensitivity for detecting nocturnal major motor seizures in children in a family home setting and reduced caregiver stress.