Seizure prediction - ready for a new era

Parameter estimation in a whole-brain network model of epilepsy: Comparison of parallel global optimization solvers

The Virtual Epileptic Patient (VEP) refers to a computer-based representation of a patient with epilepsy that combines personalized anatomical data with dynamical models of abnormal brain activities. It is capable of generating spatio-temporal seizure patterns that resemble those recorded with invasive methods such as stereoelectro EEG data, allowing for the evaluation of clinical hypotheses before planning surgery. This study highlights the effectiveness of calibrating VEP models using a global optimization approach. The approach utilizes SaCeSS, a cooperative metaheuristic capable of parallel computation, to yield high-quality solutions without requiring excessive computational time. Through extensive benchmarking on synthetic data, our proposal successfully solved a set of different configurations of VEP models, demonstrating better scalability and superior performance against other parallel solvers. These results were further enhanced using a Bayesian optimization framework for hyperparameter tuning, with significant gains in terms of both accuracy and computational cost. Additionally, we added a scalable uncertainty quantification phase after model calibration, and used it to assess the variability in estimated parameters across different problems. Overall, this study has the potential to improve the estimation of pathological brain areas in drug-resistant epilepsy, thereby to inform the clinical decision-making process.

Time-series-analysis-based detection of critical transitions in real-world non-autonomous systems

Real-world non-autonomous systems are open, out-of-equilibrium systems that evolve in and are driven by temporally varying environments. Such systems can show multiple timescale and transient dynamics together with transitions to very different and, at times, even disastrous dynamical regimes. Since such critical transitions disrupt the systems' intended or desired functionality, it is crucial to understand the underlying mechanisms, to identify precursors of such transitions, and to reliably detect them in time series of suitable system observables to enable forecasts. This review critically assesses the various steps of investigation involved in time-series-analysis-based detection of critical transitions in real-world non-autonomous systems: from the data recording to evaluating the reliability of offline and online detections. It will highlight pros and cons to stimulate further developments, which would be necessary to advance understanding and forecasting nonlinear behavior such as critical transitions in complex systems.

Addressing data limitations in seizure prediction through transfer learning

According to the literature, seizure prediction models should be developed following a patient-specific approach. However, seizures are usually very rare events, meaning the number of events that may be used to optimise seizure prediction approaches is limited. To overcome such constraint, we analysed the possibility of using data from patients from an external database to improve patient-specific seizure prediction models. We present seizure prediction models trained using a transfer learning procedure. We trained a deep convolutional autoencoder using electroencephalogram data from 41 patients collected from the EPILEPSIAE database. Then, a bidirectional long short-term memory and a classifier layers were added on the top of the encoder part and were optimised for 24 patients from the Universitätsklinikum Freiburg individually. The encoder was used as a feature extraction module. Therefore, its weights were not changed during the patient-specific training. Experimental results showed that seizure prediction models optimised using pretrained weights present about four times fewer false alarms while maintaining the same ability to predict seizures and achieved more 13% validated patients. Therefore, results evidenced that the optimisation using transfer learning was more stable and faster, saving computational resources. In summary, adopting transfer learning for seizure prediction models represents a significant advancement. It addresses the data limitation seen in the seizure prediction field and offers more efficient and stable training, conserving computational resources. Additionally, despite the compact size, transfer learning allows to easily share data knowledge due to fewer ethical restrictions and lower storage requirements. The convolutional autoencoder developed in this study will be shared with the scientific community, promoting further research.

User experience of a seizure risk forecasting app: A mixed methods investigation

OBJECTIVE

Over recent years, there has been a growing interest in exploring the utility of seizure risk forecasting, particularly how it could improve quality of life for people living with epilepsy. This study reports on user experiences and perspectives of a seizure risk forecaster app, as well as the potential impact on mood and adjustment to epilepsy.

METHODS

Active app users were asked to complete a survey (baseline and 3-month follow-up) to assess perspectives on the forecast feature as well as mood and adjustment. Post-hoc, nine neutral forecast users (neither agreed nor disagreed it was useful) completed semi-structured interviews, to gain further insight into their perspectives of epilepsy management and seizure forecasting. Non-parametric statistical tests and inductive thematic analyses were used to analyse the quantitative and qualitative data, respectively.

RESULTS

Surveys were completed by 111 users. Responders consisted of "app users" (n = 58), and "app and forecast users" (n = 53). Of the "app and forecast users", 40 % believed the forecast was accurate enough to be useful in monitoring for seizure risk, and 60 % adopted it for purposes like scheduling activities and helping mental state. Feeling more in control was the most common response to both high and low risk forecasted states. In-depth interviews revealed five broad themes, of which 'frustrations with lack of direction' (regarding their current epilepsy management approach), 'benefits of increased self-knowledge' and 'current and anticipated usefulness of forecasting' were the most common.

SIGNIFICANCE

Preliminary results suggest that seizure risk forecasting can be a useful tool for people with epilepsy to make lifestyle changes, such as scheduling daily events, and experience greater feelings of control. These improvements may be attributed, at least partly, to the improvements in self-knowledge experienced through forecast use.

Autonomic biosignals, seizure detection, and forecasting

Wearable devices have attracted significant attention in epilepsy research in recent years for their potential to enhance patient care through improved seizure monitoring and forecasting. This narrative review presents a detailed overview of the current clinical state of the art while addressing how devices that assess autonomic nervous system (ANS) function reflect seizures and central nervous system (CNS) state changes. This includes a description of the interactions between the CNS and the ANS, including physiological and epilepsy-related changes affecting their dynamics. We first discuss technical aspects of measuring autonomic biosignals and considerations for using ANS sensors in clinical practice. We then review recent seizure detection and seizure forecasting studies, highlighting their performance and capability for seizure detection and forecasting using devices measuring ANS biomarkers. Finally, we address the field's challenges and provide an outlook for future developments.

Supervised and Unsupervised Deep Learning Approaches for EEG Seizure Prediction

Epilepsy affects more than 50 million people worldwide, making it one of the world's most prevalent neurological diseases. The main symptom of epilepsy is seizures, which occur abruptly and can cause serious injury or death. The ability to predict the occurrence of an epileptic seizure could alleviate many risks and stresses people with epilepsy face. We formulate the problem of detecting preictal (or pre-seizure) with reference to normal EEG as a precursor to incoming seizure. To this end, we developed several supervised deep learning approaches model to identify preictal EEG from normal EEG. We further develop novel unsupervised deep learning approaches to train the models on only normal EEG, and detecting pre-seizure EEG as an anomalous event. These deep learning models were trained and evaluated on two large EEG seizure datasets in a person-specific manner. We found that both supervised and unsupervised approaches are feasible; however, their performance varies depending on the patient, approach and architecture. This new line of research has the potential to develop therapeutic interventions and save human lives.

EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction

BACKGROUND

The seizure prediction algorithms have demonstrated their potential in mitigating epilepsy risks by detecting the pre-ictal state using ongoing electroencephalogram (EEG) signals. However, most of them require high-density EEG, which is burdensome to the patients for daily monitoring. Moreover, prevailing seizure models require extensive training with significant labeled data which is very time-consuming and demanding for the epileptologists.

METHOD

To address these challenges, here we propose an adaptive channel selection strategy and a semi-supervised deep learning model respectively to reduce the number of EEG channels and to limit the amount of labeled data required for accurate seizure prediction. Our channel selection module is centered on features from EEG power spectra parameterization that precisely characterize the epileptic activities to identify the seizure-associated channels for each patient. The semi-supervised model integrates generative adversarial networks and bidirectional long short-term memory networks to enhance seizure prediction.

RESULTS

Our approach is evaluated on the CHB-MIT and Siena epilepsy datasets. With utilizing only 4 channels, the method demonstrates outstanding performance with an AUC of 93.15% on the CHB-MIT dataset and an AUC of 88.98% on the Siena dataset. Experimental results also demonstrate that our selection approach reduces the model parameters and training time.

CONCLUSIONS

Adaptive channel selection coupled with semi-supervised learning can offer the possible bases for a light weight and computationally efficient seizure prediction system, making the daily monitoring practical to improve patients' quality of life.

Reducing False Alarms in Wearable Seizure Detection With EEGformer: A Compact Transformer Model for MCUs

The long-term, continuous analysis of electroencephalography (EEG) signals on wearable devices to automatically detect seizures in epileptic patients is a high-potential application field for deep neural networks, and specifically for transformers, which are highly suited for end-to-end time series processing without handcrafted feature extraction. In this work, we propose a small-scale transformer detector, the EEGformer, compatible with unobtrusive acquisition setups that use only the temporal channels. EEGformer is the result of a hardware-oriented design exploration, aiming for efficient execution on tiny low-power micro-controller units (MCUs) and low latency and false alarm rate to increase patient and caregiver acceptance.Tests conducted on the CHB-MIT dataset show a 20% reduction of the onset detection latency with respect to the state-of-the-art model for temporal acquisition, with a competitive 73% seizure detection probability and 0.15 false-positive-per-hour (FP/h). Further investigations on a novel and challenging scalp EEG dataset result in the successful detection of 88% of the annotated seizure events, with 0.45 FP/h.We evaluate the deployment of the EEGformer on three commercial low-power computing platforms: the single-core Apollo4 MCU and the GAP8 and GAP9 parallel MCUs. The most efficient implementation (on GAP9) results in as low as 13.7 ms and 0.31 mJ per inference, demonstrating the feasibility of deploying the EEGformer on wearable seizure detection systems with reduced channel count and multi-day battery duration.

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.

Differentiating Epileptic and Psychogenic Non-Epileptic Seizures Using Machine Learning Analysis of EEG Plot Images

The treatment of epilepsy, the second most common chronic neurological disorder, is often complicated by the failure of patients to respond to medication. Treatment failure with anti-seizure medications is often due to the presence of non-epileptic seizures. Distinguishing non-epileptic from epileptic seizures requires an expensive and time-consuming analysis of electroencephalograms (EEGs) recorded in an epilepsy monitoring unit. Machine learning algorithms have been used to detect seizures from EEG, typically using EEG waveform analysis. We employed an alternative approach, using a convolutional neural network (CNN) with transfer learning using MobileNetV2 to emulate the real-world visual analysis of EEG images by epileptologists. A total of 5359 EEG waveform plot images from 107 adult subjects across two epilepsy monitoring units in separate medical facilities were divided into epileptic and non-epileptic groups for training and cross-validation of the CNN. The model achieved an accuracy of 86.9% (Area Under the Curve, AUC 0.92) at the site where training data were extracted and an accuracy of 87.3% (AUC 0.94) at the other site whose data were only used for validation. This investigation demonstrates the high accuracy achievable with CNN analysis of EEG plot images and the robustness of this approach across EEG visualization software, laying the groundwork for further subclassification of seizures using similar approaches in a clinical setting.

Concept-drifts adaptation for machine learning EEG epilepsy seizure prediction

Seizure prediction remains a challenge, with approximately 30% of patients unresponsive to conventional treatments. Addressing this issue is crucial for improving patients' quality of life, as timely intervention can mitigate the impact of seizures. In this research field, it is critical to identify the preictal interval, the transition from regular brain activity to a seizure. While previous studies have explored various Electroencephalogram (EEG) based methodologies for prediction, few have been clinically applicable. Recent studies have underlined the dynamic nature of EEG data, characterised by data changes with time, known as concept drifts, highlighting the need for automated methods to detect and adapt to these changes. In this study, we investigate the effectiveness of automatic concept drift adaptation methods in seizure prediction. Three patient-specific seizure prediction approaches with a 10-minute prediction horizon are compared: a seizure prediction algorithm incorporating a window adjustment method by optimising performance with Support Vector Machines (Backwards-Landmark Window), a seizure prediction algorithm incorporating a data-batch (seizures) selection method using a logistic regression (Seizure-batch Regression), and a seizure prediction algorithm with a dynamic integration of classifiers (Dynamic Weighted Ensemble). These methods incorporate a retraining process after each seizure and use a combination of univariate linear features and SVM classifiers. The Firing Power was used as a post-processing technique to generate alarms before seizures. These methodologies were compared with a control approach based on the typical machine learning pipeline, considering a group of 37 patients with Temporal Lobe Epilepsy from the EPILEPSIAE database. The best-performing approach (Backwards-Landmark Window) achieved results of 0.75 ± 0.33 for sensitivity and 1.03 ± 1.00 for false positive rate per hour. This new strategy performed above chance for 89% of patients with the surrogate predictor, whereas the control approach only validated 46%.

Ambulatory seizure detection

PURPOSE OF REVIEW

To review recent advances in the field of seizure detection in ambulatory patients with epilepsy.

RECENT FINDINGS

Recent studies have shown that wrist or arm wearable sensors, using 3D-accelerometry, electrodermal activity or photoplethysmography, in isolation or in combination, can reliably detect focal-to-bilateral and generalized tonic-clonic seizures (GTCS), with a sensitivity over 90%, and false alarm rates varying from 0.1 to 1.2 per day. A headband EEG has also demonstrated a high sensitivity for detecting and help monitoring generalized absence seizures. In contrast, no appropriate solution is yet available to detect focal seizures, though some promising findings were reported using ECG-based heart rate variability biomarkers and subcutaneous EEG.

SUMMARY

Several FDA and/or EU-certified solutions are available to detect GTCS and trigger an alarm with acceptable rates of false alarms. However, data are still missing regarding the impact of such intervention on patients' safety. Noninvasive solutions to reliably detect focal seizures in ambulatory patients, based on either EEG or non-EEG biosignals, remain to be developed. To this end, a number of challenges need to be addressed, including the performance, but also the transparency and interpretability of machine learning algorithms.

Fostering patient engagement through the co-design of seizure detection and monitoring technologies: A roadmap for collaboration between research and development

The large number of technological developments suggests that patients with epilepsy can be better supported in the management of their seizures, especially when their condition is drug resistant. Patients and their caregivers, who are generally supportive of seizure detection and monitoring technologies, can provide relevant information to improve their effectiveness. We propose a comprehensive co-design approach to support more efficient development of seizure detection and monitoring technologies. Such an approach should follow the steps of the research and development process, take into account the temporal requirements characteristic of seizure management, focus on the themes of autonomy and self-management, and be guided by disease experts. If co-design practices are to continue to contribute to their development, they must also meet the scientific requirements of validity and reproducibility.

Seizure Detection, Prediction, and Forecasting

SUMMARY

Among the many fears associated with seizures, patients with epilepsy are greatly frustrated and distressed over seizure's apparent unpredictable occurrence. However, increasing evidence have emerged over the years to support that seizure occurrence is not a random phenomenon as previously presumed; it has a cyclic rhythm that oscillates over multiple timescales. The pattern in rises and falls of seizure rate that varies over 24 hours, weeks, months, and years has become a target for the development of innovative devices that intend to detect, predict, and forecast seizures. This article will review the different tools and devices available or that have been previously studied for seizure detection, prediction, and forecasting, as well as the associated challenges and limitations with the utilization of these devices. Although there is strong evidence for rhythmicity in seizure occurrence, very little is known about the mechanism behind this oscillation. This article concludes with early insights into the regulations that may potentially drive this cyclical variability and future directions.

An approach to detect and predict epileptic seizures with high accuracy using convolutional neural networks and single-lead-ECG signal

One of the epileptic patients' challenges is to detect the time of seizures and the possibility of predicting. This research aims to provide an algorithm based on deep learning to detect and predict the time of seizure from one to two minutes before its occurrence. The proposed Convolutional Neural Network (CNN) can detect and predict the occurrence of focal epilepsy seizures through single-lead-ECG signal processing instead of using EEG signals. The structure of the proposed CNN for seizure detection and prediction is the same. Considering the requirements of a wearable system, after a few light pre-processing steps, the ECG signal can be used as input to the neural network without any manual feature extraction step. The desired neural network learns purposeful features according to the labelled ECG signals and then performs the classification of these signals. Training of 39-layer CNN for seizure detection and prediction has been done separately. The proposed method can detect seizures with an accuracy of 98.84% and predict them with an accuracy of 94.29%. With this approach, the ECG signal can be a promising indicator for the construction of portable systems for monitoring the status of epileptic patients.

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.

EEG epilepsy seizure prediction: the post-processing stage as a chronology

Almost one-third of epileptic patients fail to achieve seizure control through anti-epileptic drug administration. In the scarcity of completely controlling a patient's epilepsy, seizure prediction plays a significant role in clinical management and providing new therapeutic options such as warning or intervention devices. Seizure prediction algorithms aim to identify the preictal period that Electroencephalogram (EEG) signals can capture. However, this period is associated with substantial heterogeneity, varying among patients or even between seizures from the same patient. The present work proposes a patient-specific seizure prediction algorithm using post-processing techniques to explore the existence of a set of chronological events of brain activity that precedes epileptic seizures. The study was conducted with 37 patients with Temporal Lobe Epilepsy (TLE) from the EPILEPSIAE database. The designed methodology combines univariate linear features with a classifier based on Support Vector Machines (SVM) and two post-processing techniques to handle pre-seizure temporality in an easily explainable way, employing knowledge from network theory. In the Chronological Firing Power approach, we considered the preictal as a sequence of three brain activity events separated in time. In the Cumulative Firing Power approach, we assumed the preictal period as a sequence of three overlapping events. These methodologies were compared with a control approach based on the typical machine learning pipeline. We considered a Seizure Prediction horizon (SPH) of 5 mins and analyzed several values for the Seizure Occurrence Period (SOP) duration, between 10 and 55 mins. Our results showed that the Cumulative Firing Power approach may improve the seizure prediction performance. This new strategy performed above chance for 62% of patients, whereas the control approach only validated 49% of its models.

Heterogeneous correlate and potential diagnostic biomarker of tinnitus based on nonlinear dynamics of resting-state EEG recordings

Tinnitus is a heterogeneous condition of hearing a rattling sound when there is no auditory stimulus. This rattling sound is associated with abnormal synchronous oscillations in auditory and non-auditory cortical areas. Since tinnitus is a highly heterogeneous condition with no objective detection criteria, it is necessary to search for indicators that can be compared between and within participants for diagnostic purposes. This study introduces heterogeneous though comparable indicators of tinnitus through investigation of spontaneous fluctuations in resting-state brain dynamics. The proposed approach uses nonlinear measures of chaos theory, to detect tinnitus and cross correlation patterns to reflect many of the previously reported neural correlates of tinnitus. These indicators may serve as effective measures of tinnitus risk even at early ages before any symptom is reported. The approach quantifies differences in oscillatory brain dynamics of tinnitus and normal subjects. It demonstrates that the left temporal areas of subjects with tinnitus exhibit larger lyapunov exponent indicating irregularity of brain dynamics in these regions. More complex dynamics is further recognized in tinnitus cases through entropy. We use this evidence to distinguish tinnitus patients from normal participants. Besides, we illustrate that certain anticorrelation patterns appear in these nonlinear measures across temporal and frontal areas in the brain perhaps corresponding to increased/decreased connectivity in certain brain networks and a shift in the balance of excitation and inhibition in tinnitus. Additionally, the main correlations are lost in tinnitus participants compared to control group suggesting involvement of distinct neural mechanisms in generation and persistence of tinnitus.

Soft Bioelectronics for Neuroengineering: New Horizons in the Treatment of Brain Tumor and Epilepsy

Soft bioelectronic technologies for neuroengineering have shown remarkable progress, which include novel soft material technologies and device design strategies. Such technological advances that are initiated from fundamental brain science are applied to clinical neuroscience and provided meaningful promises for significant improvement in the diagnosis efficiency and therapeutic efficacy of various brain diseases recently. System-level integration strategies in consideration of specific disease circumstances can enhance treatment effects further. Here, recent advances in soft implantable bioelectronics for neuroengineering, focusing on materials and device designs optimized for the treatment of intracranial disease environments, are reviewed. Various types of soft bioelectronics for neuroengineering are categorized and exemplified first, and then details for the sensing and stimulating device components are explained. Next, application examples of soft implantable bioelectronics to clinical neuroscience, particularly focusing on the treatment of brain tumor and epilepsy are reviewed. Finally, an ideal system of soft intracranial bioelectronics such as closed-loop-type fully-integrated systems is presented, and the remaining challenges for their clinical translation are discussed.

Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time-Frequency EEG Images

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to human error. Recognizing this limitation, the rise in deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time-frequency domain along with pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time-frequency (CWT) images processed using autoencoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: a remarkable 100% accuracy in most of the binary classifications, exceeding 95% accuracy in three-class and four-class challenges, and a commendable rate, exceeding 93.5% for the five-class classification.

Seizure forecasting: Bifurcations in the long and winding road

To date, the unpredictability of seizures remains a source of suffering for people with epilepsy, motivating decades of research into methods to forecast seizures. Originally, only few scientists and neurologists ventured into this niche endeavor, which, given the difficulty of the task, soon turned into a long and winding road. Over the past decade, however, our narrow field has seen a major acceleration, with trials of chronic electroencephalographic devices and the subsequent discovery of cyclical patterns in the occurrence of seizures. Now, a burgeoning science of seizure timing is emerging, which in turn informs best forecasting strategies for upcoming clinical trials. Although the finish line might be in view, many challenges remain to make seizure forecasting a reality. This review covers the most recent scientific, technical, and medical developments, discusses methodology in detail, and sets a number of goals for future studies.

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.

From basic sciences and engineering to epileptology: A translational approach

Collaborative efforts between basic scientists, engineers, and clinicians are enabling translational epileptology. In this article, we summarize the recent advances presented at the International Conference for Technology and Analysis of Seizures (ICTALS 2022): (1) novel developments of structural magnetic resonance imaging; (2) latest electroencephalography signal-processing applications; (3) big data for the development of clinical tools; (4) the emerging field of hyperdimensional computing; (5) the new generation of artificial intelligence (AI)-enabled neuroprostheses; and (6) the use of collaborative platforms to facilitate epilepsy research translation. We highlight the promise of AI reported in recent investigations and the need for multicenter data-sharing initiatives.

Seizure forecasting: Where do we stand?

A lot of mileage has been made recently on the long and winding road toward seizure forecasting. Here we briefly review some selected milestones passed along the way, which were discussed at the International Conference for Technology and Analysis of Seizures-ICTALS 2022-convened at the University of Bern, Switzerland. Major impetus was gained recently from wearable and implantable devices that record not only electroencephalography, but also data on motor behavior, acoustic signals, and various signals of the autonomic nervous system. This multimodal monitoring can be performed for ultralong timescales covering months or years. Accordingly, features and metrics extracted from these data now assess seizure dynamics with a greater degree of completeness. Most prominently, this has allowed the confirmation of the long-suspected cyclical nature of interictal epileptiform activity, seizure risk, and seizures. The timescales cover daily, multi-day, and yearly cycles. Progress has also been fueled by approaches originating from the interdisciplinary field of network science. Considering epilepsy as a large-scale network disorder yielded novel perspectives on the pre-ictal dynamics of the evolving epileptic brain. In addition to discrete predictions that a seizure will take place in a specified prediction horizon, the community broadened the scope to probabilistic forecasts of a seizure risk evolving continuously in time. This shift of gears triggered the incorporation of additional metrics to quantify the performance of forecasting algorithms, which should be compared to the chance performance of constrained stochastic null models. An imminent task of utmost importance is to find optimal ways to communicate the output of seizure-forecasting algorithms to patients, caretakers, and clinicians, so that they can have socioeconomic impact and improve patients' well-being.

Seizure forecasting using minimally invasive, ultra-long-term subcutaneous EEG: Generalizable cross-patient models

This study describes a generalized cross-patient seizure-forecasting approach using recurrent neural networks with ultra-long-term subcutaneous EEG (sqEEG) recordings. Data from six patients diagnosed with refractory epilepsy and monitored with an sqEEG device were used to develop a generalized algorithm for seizure forecasting using long short-term memory (LSTM) deep-learning classifiers. Electrographic seizures were identified by a board-certified epileptologist. One-minute data segments were labeled as preictal or interictal based on their relationship to confirmed seizures. Data were separated into training and testing data sets, and to compensate for the unbalanced data ratio in training, noise-added copies of preictal data segments were generated to expand the training data set. The mean and standard deviation (SD) of the training data were used to normalize all data, preserving the pseudo-prospective nature of the analysis. Different architecture classifiers were trained and tested using a leave-one-patient-out cross-validation method, and the area under the receiver-operating characteristic (ROC) curve (AUC) was used to evaluate the performance classifiers. The importance of each input signal was evaluated using a leave-one-signal-out method with repeated training and testing for each classifier. Cross-patient classifiers achieved performance significantly better than chance in four of the six patients and an overall mean AUC of 0.602 ± 0.126 (mean ± SD). A time in warning of 37.386% ± 5.006% (mean ± std) and sensitivity of 0.691 ± 0.068 (mean ± std) were observed for patients with better than chance results. Analysis of input channels showed a significant contribution (p < .05) by the Fourier transform of signals channels to overall classifier performance. The relative contribution of input signals varied among patients and architectures, suggesting that the inclusion of all signals contributes to robustness in a cross-patient classifier. These early results show that it is possible to forecast seizures training with data from different patients using two-channel ultra-long-term sqEEG.

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).

Machine Learning Interpretability Methods to Characterize Brain Network Dynamics in Epilepsy

The rapid adoption of machine learning (ML) algorithms in a wide range of biomedical applications has highlighted issues of trust and the lack of understanding regarding the results generated by ML algorithms. Recent studies have focused on developing interpretable ML models and establish guidelines for transparency and ethical use, ensuring the responsible integration of machine learning in healthcare. In this study, we demonstrate the effectiveness of ML interpretability methods to provide important insights into the dynamics of brain network interactions in epilepsy, a serious neurological disorder affecting more than 60 million persons worldwide. Using high-resolution intracranial electroencephalogram (EEG) recordings from a cohort of 16 patients, we developed high accuracy ML models to categorize these brain activity recordings into either seizure or non-seizure classes followed by a more complex task of delineating the different stages of seizure progression to different parts of the brain as a multi-class classification task. We applied three distinct types of interpretability methods to the high-accuracy ML models to gain an understanding of the relative contributions of different categories of brain interaction patterns, including multi-focii interactions, which play an important role in distinguishing between different states of the brain. The results of this study demonstrate for the first time that post-hoc interpretability methods enable us to understand why ML algorithms generate a given set of results and how variations in value of input values affect the accuracy of the ML algorithms. In particular, we show in this study that interpretability methods can be used to identify brain regions and interaction patterns that have a significant impact on seizure events. The results of this study highlight the importance of the integrated implementation of ML algorithms together with interpretability methods in aberrant brain network studies and the wider domain of biomedical research.

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.

Utilizing risk-controlling prediction calibration to reduce false alarm rates in epileptic seizure prediction

Introduction

Epilepsy is a neurological disease characterized by sudden, unprovoked seizures. The unexpected nature of epileptic seizures is a major component of the disease burden. Predicting seizure onset and alarming patients may allow timely intervention, which would improve clinical outcomes and patient quality of life. Currently, algorithms aiming to predict seizures suffer from a high false alarm rate, rendering them unsuitable for clinical use.

Methods

We adopted here a risk-controlling prediction calibration method called Learn then Test to reduce false alarm rates of seizure prediction. This method calibrates the output of a "black-box" model to meet a specified false alarm rate requirement. The method was initially validated on synthetic data and subsequently tested on publicly available electroencephalogram (EEG) records from 15 patients with epilepsy by calibrating the outputs of a deep learning model.

Results and discussion

Validation showed that the calibration method rigorously controlled the false alarm rate at a user-desired level after our adaptation. Real data testing showed an average of 92% reduction in the false alarm rate, at the cost of missing four of nine seizures of six patients. Better-performing prediction models combined with the proposed method may facilitate the clinical use of real-time seizure prediction systems.

Computational modeling allows unsupervised classification of epileptic brain states across species

Current advances in epilepsy treatment aim to personalize and responsively adjust treatment parameters to overcome patient heterogeneity in treatment efficiency. For tailoring treatment to the individual and the current brain state, tools are required that help to identify the patient- and time-point-specific parameters of epilepsy. Computational modeling has long proven its utility in gaining mechanistic insight. Recently, the technique has been introduced as a diagnostic tool to predict individual treatment outcomes. In this article, the Wendling model, an established computational model of epilepsy dynamics, is used to automatically classify epileptic brain states in intracranial EEG from patients (n = 4) and local field potential recordings from in vitro rat data (high-potassium model of epilepsy, n = 3). Five-second signal segments are classified to four types of brain state in epilepsy (interictal, preonset, onset, ictal) by comparing a vector of signal features for each data segment to four prototypical feature vectors obtained by Wendling model simulations. The classification result is validated against expert visual assessment. Model-driven brain state classification achieved a classification performance significantly above chance level (mean sensitivity 0.99 on model data, 0.77 on rat data, 0.56 on human data in a four-way classification task). Model-driven prototypes showed similarity with data-driven prototypes, which we obtained from real data for rats and humans. Our results indicate similar electrophysiological patterns of epileptic states in the human brain and the animal model that are well-reproduced by the computational model, and captured by a key set of signal features, enabling fully automated and unsupervised brain state classification in epilepsy.

Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.

Model Parameter Estimation As Features to Predict the Duration of Epileptic Seizures From Onset

The durations of epileptic seizures are linked to severity and risk for patients. It is unclear if the spatiotemporal evolution of a seizure has any relationship with its duration. Understanding such mechanisms may help reveal treatments for reducing the duration of a seizure. Here, we present a novel method to predict whether a seizure is going to be short or long at its onset using features that can be interpreted in the parameter space of a brain model. The parameters of a Jansen-Rit neural mass model were tracked given intracranial electroencephalography (iEEG) signals, and were processed as time series features using MINIROCKET. By analysing 2954 seizures from 10 patients, patient-specific classifiers were built to predict if a seizure would be short or long given 7 s of iEEG at seizure onset. The method achieved an area under the receiver operating characteristic curve (AUC) greater than 0.6 for five of 10 patients. The behaviour in the parameter space has shown different mechanisms are associated with short/long seizures.Clinical relevance-This shows that it is possible to classify whether a seizure will be short or long based on its early characteristics. Timely interventions and treatments can be applied if the duration of the seizures can be predicted.

Distance to Criticality Undergoes Critical Transition Before Epileptic Seizure Attacks

Epilepsy is a common neurological disorder characterized by recurring seizures, but its underlying mechanisms remain poorly understood. Despite extensive research, there are still gaps in our knowledge about the relationship between brain dynamics and seizures. In this study, our aim is to address these gaps by proposing a novel approach to assess the role of brain network dynamics in the onset of seizures. Specifically, we investigate the relationship between brain dynamics and seizures by tracking the distance to criticality. Our hypothesis is that this distance plays a crucial role in brain state changes and that seizures may be related to critical transitions of this distance. To test this hypothesis, we develop a method to measure the evolution of the brain network's distance to the critical dynamic systems (i.e., the distance to the tipping point, DTP) using dynamic network biomarker theory and random matrix theory. The results show that the DTP of the brain decreases significantly immediately after onset of an epileptic seizure, suggesting that the brain loses its well-defined quasi-critical state during seizures. We refer to this phenomenon as the "criticality of the criticality" (COC). Furthermore, we observe that DTP exhibits a shape transition before and after the onset of the seizures. This phenomenon suggests the possibility of early warning signal (EWS) identification in the dynamic sequence of DTP, which could be utilized for seizure prediction. Our results show that the Hurst exponent, skewness, kurtosis, autocorrelation, and variance of the DTP sequence are potential EWS features. This study advances our understanding of the relationship between brain dynamics and seizures and highlights the potential for using criticality-based measures to predict and prevent seizures.

Predictive Models for Health Deterioration: Understanding Disease Pathways for Personalized Medicine

Artificial intelligence (AI) and machine learning (ML) methods are currently widely employed in medicine and healthcare. A PubMed search returns more than 100,000 articles on these topics published between 2018 and 2022 alone. Notwithstanding several recent reviews in various subfields of AI and ML in medicine, we have yet to see a comprehensive review around the methods' use in longitudinal analysis and prediction of an individual patient's health status within a personalized disease pathway. This review seeks to fill that gap. After an overview of the AI and ML methods employed in this field and of specific medical applications of models of this type, the review discusses the strengths and limitations of current studies and looks ahead to future strands of research in this field. We aim to enable interested readers to gain a detailed impression of the research currently available and accordingly plan future work around predictive models for deterioration in health status.

On temporal scale-free non-periodic stimulation and its mechanisms as an infinite improbability drive of the brain's functional connectogram

Rationalized development of electrical stimulation (ES) therapy is of paramount importance. Not only it will foster new techniques and technologies with increased levels of safety, efficacy, and efficiency, but it will also facilitate the translation from basic research to clinical practice. For such endeavor, design of new technologies must dialogue with state-of-the-art neuroscientific knowledge. By its turn, neuroscience is transitioning-a movement started a couple of decades earlier-into adopting a new conceptual framework for brain architecture, in which time and thus temporal patterns plays a central role in the neuronal representation of sampled data from the world. This article discusses how neuroscience has evolved to understand the importance of brain rhythms in the overall functional architecture of the nervous system and, consequently, that neuromodulation research should embrace this new conceptual framework. Based on such support, we revisit the literature on standard (fixed-frequency pulsatile stimuli) and mostly non-standard patterns of ES to put forward our own rationale on how temporally complex stimulation schemes may impact neuromodulation strategies. We then proceed to present a low frequency, on average (thus low energy), scale-free temporally randomized ES pattern for the treatment of experimental epilepsy, devised by our group and termed NPS (Non-periodic Stimulation). The approach has been shown to have robust anticonvulsant effects in different animal models of acute and chronic seizures (displaying dysfunctional hyperexcitable tissue), while also preserving neural function. In our understanding, accumulated mechanistic evidence suggests such a beneficial mechanism of action may be due to the natural-like characteristic of a scale-free temporal pattern that may robustly compete with aberrant epileptiform activity for the recruitment of neural circuits. Delivering temporally patterned or random stimuli within specific phases of the underlying oscillations (i.e., those involved in the communication within and across brain regions) could both potentiate and disrupt the formation of neuronal assemblies with random probability. The usage of infinite improbability drive here is obviously a reference to the "The Hitchhiker's Guide to the Galaxy" comedy science fiction classic, written by Douglas Adams. The parallel is that dynamically driving brain functional connectogram, through neuromodulation, in a manner that would not favor any specific neuronal assembly and/or circuit, could re-stabilize a system that is transitioning to fall under the control of a single attractor. We conclude by discussing future avenues of investigation and their potentially disruptive impact on neurotechnology, with a particular interest in NPS implications in neural plasticity, motor rehabilitation, and its potential for clinical translation.

Cell-free DNA-based liquid biopsies in neurology

This article reviews recent developments in the application of cell-free DNA-based liquid biopsies to neurological diseases. Over the past few decades, an explosion of interest in the use of accessible biofluids to identify and track molecular disease has revolutionized the fields of oncology, prenatal medicine and others. More recently, technological advances in signal detection have allowed for informative analysis of biofluids that are typically sparse in cells and other circulating components, such as CSF. In parallel, advancements in epigenetic profiling have allowed for novel applications of liquid biopsies to diseases without characteristic mutational profiles, including many degenerative, autoimmune, inflammatory, ischaemic and infectious disorders. These events have paved the way for a wide array of neurological conditions to benefit from enhanced diagnostic, prognostic, and treatment abilities through the use of liquid biomarkers: a 'liquid biopsy' approach. This review includes an overview of types of liquid biopsy targets with a focus on circulating cell-free DNA, methods used to identify and probe potential liquid biomarkers, and recent applications of such biomarkers to a variety of complex neurological conditions including CNS tumours, stroke, traumatic brain injury, Alzheimer's disease, epilepsy, multiple sclerosis and neuroinfectious disease. Finally, the challenges of translating liquid biopsies to use in clinical neurology settings-and the opportunities for improvement in disease management that such translation may provide-are discussed.

An overview of machine learning methods in enabling IoMT-based epileptic seizure detection

The healthcare industry is rapidly automating, in large part because of the Internet of Things (IoT). The sector of the IoT devoted to medical research is sometimes called the Internet of Medical Things (IoMT). Data collecting and processing are the fundamental components of all IoMT applications. Machine learning (ML) algorithms must be included into IoMT immediately due to the vast quantity of data involved in healthcare and the value that precise forecasts have. In today's world, together, IoMT, cloud services, and ML techniques have become effective tools for solving many problems in the healthcare sector, such as epileptic seizure monitoring and detection. One of the biggest hazards to people's lives is epilepsy, a lethal neurological condition that has become a global issue. To prevent the deaths of thousands of epileptic patients each year, there is a critical necessity for an effective method for detecting epileptic seizures at their earliest stage. Numerous medical procedures, including epileptic monitoring, diagnosis, and other procedures, may be carried out remotely with the use of IoMT, which will reduce healthcare expenses and improve services. This article seeks to act as both a collection and a review of the different cutting-edge ML applications for epilepsy detection that are presently being combined with IoMT.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

Perceived seizure risk in epilepsy â€" Chronic electronic surveys with and without concurrent EEG

Objective

Previous studies suggested that patients with epilepsy might be able to fore-cast their own seizures. We sought to assess the relationships of premonitory symptoms and perceived seizure risk with future and recent self-reported and EEG-confirmed seizures in the subjects living with epilepsy in their natural home environments.

Methods

We collected long-term e-surveys from ambulatory patients with and without concurrent EEG recordings. Information obtained from the e-surveys included medication compliance, 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 device seizure forecasting literature using a mathematical formula converting OR to equivalent area under the curve (AUC).

Results

Sixty-nine subjects returned 12,590 e-survey entries, with four subjects acquiring concurrent EEG recordings. Univariate analysis revealed increased stress (OR = 2.52, 95% CI = [1.52, 4.14], p < 0.001) and decreased mood (0.32, [0.13, 0.82], 0.02) were associated with increased relative odds of future self-reported seizures. On multivariate analysis, previous self-reported seizures (4.24, [2.69, 6.68], < 0.001) were most strongly associated with future self-reported seizures, and high perceived seizure risk (3.30, [1.97, 5.52], < 0.001) remained significant when prior self-reported seizures were added to the model. No significant association was found between e-survey responses and subsequent EEG seizures.

Significance

It appears that patients may tend to self-forecast seizures that occur in sequential groupings. Our results suggest 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.

Key points

Long-term e-surveys data and concurrent EEG signals were collected across three study sites to assess the ability of the patients to self-forecast their seizures.Patients may tend to self-forecast self-reported seizures that occur in sequential groupings.Factors, such as mood and stress, may not be independent premonitory symptoms but may be the consequence of recent seizures.No ability to self-forecast EEG confirmed seizures was observed in a small cohort with concurrent EEG validation.A mathematic relation between OR and AUC provides a means to compare forecasting performance between survey and device studies.

Pro-Ictal State in Human Temporal Lobe Epilepsy

BACKGROUND: Studies of continuous electroencephalography (EEG) suggest that seizures in individuals with focal-onset epilepsies preferentially occur during periods of heightened risk, typified by pathologic brain activities, termed pro-ictal states; however, the presence of (pathologic) pro-ictal states among a plethora of otherwise physiologic (e.g., sleep–wake cycle) states has not been established. METHODS: We studied a prospective, consecutive series of 15 patients with temporal lobe epilepsy who underwent limbic thalamic recordings in addition to routine (cortical) intracranial EEG for seizure localization. For each participant, pro-ictal (45 minutes before seizure onset) and interictal (4 hours removed from all seizures) EEG segments were divided into 10-minute, nonoverlapping windows, which were randomly distributed into training and validation cohorts in a 1:1 ratio. A deep neural classifier was applied to distinguish pro-ictal from interictal brain activities in a patient-specific fashion. RESULTS: We analyzed 1800 patient-hours of continuous thalamocortical EEG. Distinct pro-ictal states were detected in each participant. The median area under the receiver-operating characteristic curve of the classifier was 0.92 (interquartile range, 0.90–0.96). Pro-ictal states were distinguished at least 45 minutes before seizure onset in 13 of 15 participants; in 2 of 15 participants, they were distinguished up to 35 minutes prior. CONCLUSIONS: On the basis of thalamocortical EEG, pro-ictal states — pathologic brain activities during periods of heightened seizure risk — could be identified in patients with temporal lobe epilepsy and were detected, in our small sample, more than one half hour before seizure onset.

Amortized Bayesian inference on generative dynamical network models of epilepsy using deep neural density estimators

Whole-brain modeling of epilepsy combines personalized anatomical data with dynamical models of abnormal activities to generate spatio-temporal seizure patterns as observed in brain imaging data. Such a parametric simulator is equipped with a stochastic generative process, which itself provides the basis for inference and prediction of the local and global brain dynamics affected by disorders. However, the calculation of likelihood function at whole-brain scale is often intractable. Thus, likelihood-free algorithms are required to efficiently estimate the parameters pertaining to the hypothetical areas, ideally including the uncertainty. In this study, we introduce the simulation-based inference for the virtual epileptic patient model (SBI-VEP), enabling us to amortize the approximate posterior of the generative process from a low-dimensional representation of whole-brain epileptic patterns. The state-of-the-art deep learning algorithms for conditional density estimation are used to readily retrieve the statistical relationships between parameters and observations through a sequence of invertible transformations. We show that the SBI-VEP is able to efficiently estimate the posterior distribution of parameters linked to the extent of the epileptogenic and propagation zones from sparse intracranial electroencephalography recordings. The presented Bayesian methodology can deal with non-linear latent dynamics and parameter degeneracy, paving the way for fast and reliable inference on brain disorders from neuroimaging modalities.

Epileptic-network-based prediction and control of seizures in humans

Epilepsy is now conceptualized as a network disease. The epileptic brain network comprises structurally and functionally connected cortical and subcortical brain regions - spanning lobes and hemispheres -, whose connections and dynamics evolve in time. With this concept, focal and generalized seizures as well as other related pathophysiological phenomena are thought to emerge from, spread via, and be terminated by network vertices and edges that also generate and sustain normal, physiological brain dynamics. Research over the last years has advanced concepts and techniques to identify and characterize the evolving epileptic brain network and its constituents on various spatial and temporal scales. Network-based approaches further our understanding of how seizures emerge from the evolving epileptic brain network, and they provide both novel insights into pre-seizure dynamics and important clues for success or failure of measures for network-based seizure control and prevention. In this review, we summarize the current state of knowledge and address several important challenges that would need to be addressed to move network-based prediction and control of seizures closer to clinical translation.

EEG datasets for seizure detection and prediction- A review

Electroencephalogram (EEG) datasets from epilepsy patients have been used to develop seizure detection and prediction algorithms using machine learning (ML) techniques with the aim of implementing the learned model in a device. However, the format and structure of publicly available datasets are different from each other, and there is a lack of guidelines on the use of these datasets. This impacts the generatability, generalizability, and reproducibility of the results and findings produced by the studies. In this narrative review, we compiled and compared the different characteristics of the publicly available EEG datasets that are commonly used to develop seizure detection and prediction algorithms. We investigated the advantages and limitations of the characteristics of the EEG datasets. Based on our study, we identified 17 characteristics that make the EEG datasets unique from each other. We also briefly looked into how certain characteristics of the publicly available datasets affect the performance and outcome of a study, as well as the influences it has on the choice of ML techniques and preprocessing steps required to develop seizure detection and prediction algorithms. In conclusion, this study provides a guideline on the choice of publicly available EEG datasets to both clinicians and scientists working to develop a reproducible, generalizable, and effective seizure detection and prediction algorithm.

Ordinal methods for a characterization of evolving functional brain networks

Ordinal time series analysis is based on the idea to map time series to ordinal patterns, i.e., order relations between the values of a time series and not the values themselves, as introduced in 2002 by C. Bandt and B. Pompe. Despite a resulting loss of information, this approach captures meaningful information about the temporal structure of the underlying system dynamics as well as about properties of interactions between coupled systems. This-together with its conceptual simplicity and robustness against measurement noise-makes ordinal time series analysis well suited to improve characterization of the still poorly understood spatiotemporal dynamics of the human brain. This minireview briefly summarizes the state-of-the-art of uni- and bivariate ordinal time-series-analysis techniques together with applications in the neurosciences. It will highlight current limitations to stimulate further developments, which would be necessary to advance characterization of evolving functional brain networks.

Thalamic neuromodulation in epilepsy: A primer for emerging circuit-based therapies

INTRODUCTION

Epilepsy is a common, often debilitating disease of hyperexcitable neural networks. While medically intractable cases may benefit from surgery, there may be no single, well-localized focus for resection or ablation. In such cases, approaching the disease from a network-based perspective may be beneficial.

AREAS COVERED

Herein, the authors provide a narrative review of normal thalamic anatomy and physiology and propose general strategies for preventing and/or aborting seizures by modulating this structure. Additionally, they make specific recommendations for targeting the thalamus within different contexts, motivated by a more detailed discussion of its distinct nuclei and their respective connectivity. By describing important principles governing thalamic function and its involvement in seizure networks, the authors aim to provide a primer for those now entering this fast-growing field of thalamic neuromodulation for epilepsy.

EXPERT OPINION

The thalamus is critically involved with the function of many cortical and subcortical areas, suggesting it may serve as a compelling node for preventing or aborting seizures, and so it has increasingly been targeted for the surgical treatment of epilepsy. As various thalamic neuromodulation strategies for seizure control are developed, there is a need to ground such interventions in a mechanistic, circuit-based framework.

Daily resting-state intracranial EEG connectivity for seizure risk forecasts

Forecasting seizure risk aims to detect proictal states in which seizures would be more likely to occur. Classical seizure prediction models are trained over long-term electroencephalographic (EEG) recordings to detect specific preictal changes for each seizure, independently of those induced by shifts in states of vigilance. A daily single measure-during a vigilance-controlled period-to estimate the risk of upcoming seizure(s) would be more convenient. Here, we evaluated whether intracranial EEG connectivity (phase-locking value), estimated from daily vigilance-controlled resting-state recordings, could allow distinguishing interictal (no seizure) from preictal (seizure within the next 24 h) states. We also assessed its relevance for daily forecasts of seizure risk using machine learning models. Connectivity in the theta band was found to provide the best prediction performances (area under the curve ≥ .7 in 80% of patients), with accurate daily and prospective probabilistic forecasts (mean Brier score and Brier skill score of .13 and .72, respectively). More efficient ambulatory clinical application could be considered using mobile EEG or chronic implanted devices.

Machine learning seizure prediction: one problematic but accepted practice

Objective.Epilepsy is one of the most common neurological disorders and can have a devastating effect on a person's quality of life. As such, the search for markers which indicate an upcoming seizure is a critically important area of research which would allow either on-demand treatment or early warning for people suffering with these disorders. There is a growing body of work which uses machine learning methods to detect pre-seizure biomarkers from electroencephalography (EEG), however the high prediction rates published do not translate into the clinical setting. Our objective is to investigate a potential reason for this.Approach.We conduct an empirical study of a commonly used data labelling method for EEG seizure prediction which relies on labelling small windows of EEG data in temporal groups then selecting randomly from those windows to validate results. We investigate a confound for this approach for seizure prediction and demonstrate the ease at which it can be inadvertently learned by a machine learning system.Main results.We find that non-seizure signals can create decision surfaces for machine learning approaches which can result in false high prediction accuracy on validation datasets. We prove this by training an artificial neural network to learn fake seizures (fully decoupled from biology) in real EEG.Significance.The significance of our findings is that many existing works may be reporting results based on this confound and that future work should adhere to stricter requirements in mitigating this confound. The problematic, but commonly accepted approach in the literature for seizure prediction labelling is potentially preventing real advances in developing solutions for these sufferers. By adhering to the guidelines in this paper future work in machine learning seizure prediction is more likely to be clinically relevant.