4.5 Article

Seizure forecasting: Where do we stand?

Related references

Note: Only part of the references are listed.
Article Clinical Neurology

Seizure occurrence is linked to multiday cycles in diverse physiological signals

Nicholas M. Gregg et al.

Summary: This study investigated the relationships between various physiological signals, brain activity, and seizure timing using multimodal wearable devices. The findings showed that seizure timing is associated with daily and multiday cycles in multiple physiological processes. This research contributes to a better understanding of factors influencing seizure risk and provides a time-varying approach for personalized epilepsy care.

EPILEPSIA (2023)

Editorial Material Clinical Neurology

Seizure prediction: Time for new, multimodal and ultra-long-term approaches

Andreas Schulze-Bonhage

CLINICAL NEUROPHYSIOLOGY (2022)

Article Clinical Neurology

Seizure forecasting: Bifurcations in the long and winding road

Maxime O. Baud et al.

Summary: Seizure forecasting, although challenging, has seen significant advancements in recent years. The emerging science of seizure timing informs the best forecasting strategies for upcoming clinical trials.

EPILEPSIA (2022)

Article Clinical Neurology

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

Tal Pal Attia et al.

Summary: This study presents a generalized approach for forecasting seizures in epilepsy patients using recurrent neural networks and deep learning classifiers. The results show that the cross-patient classifiers achieved better than chance performance in four out of six patients, indicating the potential of this method for seizure prediction.

EPILEPSIA (2022)

Article Clinical Neurology

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

Pedro F. Viana et al.

Summary: This study demonstrates the feasibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. Promising results were achieved in predicting seizures in three to five out of six patients, with significant performance and sensitivity, closely following the circadian patterns of seizure occurrence. Further development of a prospective seizure forecasting trial using minimally invasive EEG is encouraged.

EPILEPSIA (2022)

Article Multidisciplinary Sciences

A straightforward edge centrality concept derived from generalizing degree and strength

Timo Broehl et al.

Summary: Vertex degree, the number of edges incident to a vertex, is a fundamental concept in network theory. While there is no analogous concept for edge centrality, we propose the concept of nearest-neighbor edge centrality and demonstrate its suitability in identifying central edges in real-world networks.

SCIENTIFIC REPORTS (2022)

Review Biophysics

Seizures detection using multimodal signals: a scoping review

Fangyi Chen et al.

Summary: This scoping review aims to depict current research activities associated with the implementation of portable, wearable devices for seizure detection or prediction and inform future direction in continuous seizure tracking in ambulatory settings. The overall performance of non-cerebral physiological signals based seizure detection systems is promising, especially for motor seizures and seizures accompanied with intense ictal autonomic changes.

PHYSIOLOGICAL MEASUREMENT (2022)

Article Clinical Neurology

Learning to generalize seizure forecasts

Marc G. Leguia et al.

Summary: The study found that seizure forecasting based on multidien cycles of interictal epileptiform activity (IEA) can generalize across patients and greatly reduce the amount of data needed for individual seizure prediction. Furthermore, it demonstrated that this generalization is independent of the method used to record seizures or IEA.

EPILEPSIA (2022)

Article Clinical Neurology

Seizure forecasting and cyclic control of seizures

Rachel E. Stirling et al.

Summary: Epilepsy is a unique neurological condition characterized by recurrent seizures, with causes, biomarkers, triggers, and patterns varying across individuals. Despite decades of research on seizure prediction algorithms, their utility and effectiveness in clinical settings have not been thoroughly investigated, while seizure forecasts providing probability of seizures at any time may be more feasible theoretically. Recent advances in seizure forecasting include improvements in algorithms through machine learning and exploration of non-EEG-based measures of seizure susceptibility.

EPILEPSIA (2021)

Article Clinical Neurology

Forecasting seizure risk in adults with focal epilepsy: a development and validation study

Timothee Proix et al.

Summary: This study demonstrates the feasibility of forecasting seizure probabilities days in advance using implanted device-recorded multidien IEA cycles. It provides a basis for prospective clinical trials to determine how individuals with epilepsy can benefit from long-term seizure forecasting.

LANCET NEUROLOGY (2021)

Article Biochemical Research Methods

Assessing criticality in pre-seizure single-neuron activity of human epileptic cortex

Annika Hagemann et al.

Summary: The study examined the mechanism of epilepsy seizures from the perspective of collective neural dynamics in the brain. It found no evidence supporting the hypothesis that epilepsy involves a transition to supercritical collective neural dynamics, with results indicating that epileptic brain operates in a stable regime. Although epileptic seizures are characterized by unstable neural activity, the cortex of epilepsy patients tends to exhibit stable dynamics during seizure-free intervals, questioning how recurring instability arises despite this stable default state.

PLOS COMPUTATIONAL BIOLOGY (2021)

Article Clinical Neurology

Seizure Cycles in Focal Epilepsy

Marc G. Leguia et al.

Summary: This study aimed to establish the prevalence, strength, and temporal patterns of seizure cycles in focal epilepsy patients over timescales of hours to years. The results revealed different types of seizure cycles, with high prevalence of circadian, multidien, and circannual cycles, which can help explain the natural variability in seizure timing.

JAMA NEUROLOGY (2021)

Article Multidisciplinary Sciences

Ambulatory seizure forecasting with a wrist-worn device using long-short term memory deep learning

Mona Nasseri et al.

Summary: The study developed a seizure forecasting system using noninvasive wearable devices and achieved better performance than random prediction for most epilepsy patients tested. This provides clear evidence that direct seizure forecasts are possible using wearable devices in the ambulatory setting for many epilepsy patients.

SCIENTIFIC REPORTS (2021)

Article Emergency Medicine

Why do healthcare professionals fail to escalate as per the early warning system (EWS) protocol? A qualitative evidence synthesis of the barriers and facilitators of escalation

S. M. O'Neill et al.

Summary: This qualitative evidence synthesis identified the barriers and facilitators to the escalation of care according to EWS protocols among healthcare professionals from seven countries. The findings revealed individual yet inter-related factors such as lack of standardization, resources, accountability, and professional behaviors that hinder or promote escalation according to EWS protocols.

BMC EMERGENCY MEDICINE (2021)

Article Clinical Neurology

Increased branched-chain amino acids at baseline and hours before a spontaneous seizure in the human epileptic brain

Caroline Ong et al.

Summary: This study monitored extracellular brain chemistry dynamics in patients with refractory epilepsy and found that branched-chain amino acids (BCAAs) and glutamate were chronically elevated in brain regions of seizure onset and propagation. Interestingly, isoleucine increased significantly above baseline as early as 3 hours before a spontaneous seizure, suggesting a potential role of BCAAs in the pathogenesis of spontaneous seizures.

EPILEPSIA (2021)

Article Medicine, General & Internal

Multiday cycles of heart rate are associated with seizure likelihood: An observational cohort study

Philippa J. Karoly et al.

Summary: The study found circadian and multiday rhythms in both healthy individuals and those with epilepsy, with heart rate cycles showing similarities to multiday epileptic rhythms. The relationship between heart rate and seizures may have significant implications for epilepsy therapy, including seizure forecasting. Understanding the link between multiday cycles in the heart and brain can shed new light on endogenous physiological rhythms in humans.

EBIOMEDICINE (2021)

Review Clinical Neurology

Seizure Diaries and Forecasting With Wearables: Epilepsy Monitoring Outside the Clinic

Benjamin H. Brinkmann et al.

Summary: The development of wearable devices in epilepsy monitoring shows promise in detecting and recording seizure activity, but the large volume of data acquired by these devices requires computer-assisted review. User acceptability of such devices is crucial, and identifying seizure semiologies beyond tonic-clonic seizures remains a challenge. Non-invasive scalp EEG and minimally invasive subscalp EEG have shown potential in measuring seizure activity, but continuous, secure transmission of data and user adherence are essential considerations.

FRONTIERS IN NEUROLOGY (2021)

Article Clinical Neurology

Seizure Forecasting: Patient and Caregiver Perspectives

Caitlin L. L. Grzeskowiak et al.

Summary: Accurate seizure forecasting is becoming possible with recent advancements in machine learning and EEG technology. Large-scale data curation and new data element collection have uncovered possibilities for personalized algorithm development. Insights from surveys by the Epilepsy Foundation show that unpredictability of seizures has a significant impact on the lives of individuals with epilepsy and their caregivers.

FRONTIERS IN NEUROLOGY (2021)

Article Clinical Neurology

Forecasting Seizure Likelihood With Wearable Technology

Rachel E. Stirling et al.

Summary: The study utilized machine learning models combined with wearable device data to predict epileptic seizures, showing promising potential. It was found that wearable devices can be used to produce personalized seizure forecasts, particularly when biomarkers of seizure and epileptic activity cycles are utilized.

FRONTIERS IN NEUROLOGY (2021)

Review Engineering, Biomedical

Machine Learning for Predicting Epileptic Seizures Using EEG Signals: A Review

Khansa Rasheed et al.

Summary: Artificial intelligence and machine learning techniques are being utilized to advance clinical practice, particularly in early prediction of epileptic seizures. However, challenges such as inadequate data remain, requiring further research to address.

IEEE REVIEWS IN BIOMEDICAL ENGINEERING (2021)

Editorial Material Behavioral Sciences

Incorporating the regulatory science of patient input for the epilepsy community

Sonya B. Dumanis et al.

EPILEPSY & BEHAVIOR (2020)

Article Clinical Neurology

Forecasting cycles of seizure likelihood

Philippa J. Karoly et al.

EPILEPSIA (2020)

Review Clinical Neurology

Controversies on the network theory of epilepsy: Debates held during the ICTALS 2019 conference

Hitten P. Zaveri et al.

SEIZURE-EUROPEAN JOURNAL OF EPILEPSY (2020)

Article Multidisciplinary Sciences

Critical slowing down as a biomarker for seizure susceptibility

Matias Maturana et al.

NATURE COMMUNICATIONS (2020)

Article Clinical Neurology

Development and Validation of Forecasting Next Reported Seizure Using e-Diaries

Daniel M. Goldenholz et al.

ANNALS OF NEUROLOGY (2020)

Article Clinical Neurology

Circadian and multiday seizure periodicities, and seizure clusters in canine epilepsy

Nicholas M. Gregg et al.

BRAIN COMMUNICATIONS (2020)

Article Multidisciplinary Sciences

Traceability and dynamical resistance of precursor of extreme events

Thorsten Rings et al.

SCIENTIFIC REPORTS (2019)

Article Mathematics, Applied

No evidence for critical slowing down prior to human epileptic seizures

Theresa Wilkat et al.

CHAOS (2019)

Article Multidisciplinary Sciences

Multi-day rhythms modulate seizure risk in epilepsy

Maxime O. Baud et al.

NATURE COMMUNICATIONS (2018)

Article Clinical Neurology

Circadian and circaseptan rhythms in human epilepsy: a retrospective cohort study

Philippa J. Karoly et al.

LANCET NEUROLOGY (2018)

Review Clinical Neurology

Seizure prediction - ready for a new era

Levin Kuhlmann et al.

NATURE REVIEWS NEUROLOGY (2018)

Review Clinical Neurology

Seizure self-prediction: Myth or missed opportunity?

Michael Mackay et al.

SEIZURE-EUROPEAN JOURNAL OF EPILEPSY (2017)

Article Clinical Neurology

The circadian profile of epilepsy improves seizure forecasting

Philippa J. Karoly et al.

BRAIN (2017)

Article Computer Science, Artificial Intelligence

Seizures Start without Common Signatures of Critical Transition

Piotr Milanowski et al.

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS (2016)

Article Multidisciplinary Sciences

Predictability of uncontrollable multifocal seizures - towards new treatment options

Klaus Lehnertz et al.

SCIENTIFIC REPORTS (2016)

Article Psychology, Multidisciplinary

Biases in probabilistic category learning in relation to social anxiety

Anna Abraham et al.

FRONTIERS IN PSYCHOLOGY (2015)

Article Mathematics, Applied

Evolving networks in the human epileptic brain

Klaus Lehnertz et al.

PHYSICA D-NONLINEAR PHENOMENA (2014)

Review Behavioral Sciences

Network hubs in the human brain

Martijn P. van den Heuvel et al.

TRENDS IN COGNITIVE SCIENCES (2013)

Review Clinical Neurology

Epilepsy as a Disorder of Cortical Network Organization

Mark A. Kramer et al.

NEUROSCIENTIST (2012)

Article Multidisciplinary Sciences

Evidence of an inhibitory restraint of seizure activity in humans

Catherine A. Schevon et al.

NATURE COMMUNICATIONS (2012)

Article Clinical Neurology

Premonitory features and seizure self-prediction: Artifact or real?

Andreas Schulze-Bonhage et al.

EPILEPSY RESEARCH (2011)

Article Mathematics, Applied

Long-term variability of global statistical properties of epileptic brain networks

Marie-Therese Kuhnert et al.

CHAOS (2010)

Article Neurosciences

Complex network measures of brain connectivity: Uses and interpretations

Mikail Rubinov et al.

NEUROIMAGE (2010)

Article Clinical Neurology

Seizure prediction: Any better than chance?

Ralph G. Andrzejak et al.

CLINICAL NEUROPHYSIOLOGY (2009)

Review Neurosciences

Complex brain networks: graph theoretical analysis of structural and functional systems

Edward T. Bullmore et al.

NATURE REVIEWS NEUROSCIENCE (2009)

Article Engineering, Biomedical

The statistics of a practical seizure warning system

David E. Snyder et al.

JOURNAL OF NEURAL ENGINEERING (2008)

Article Neurosciences

A stochastic framework for evaluating seizure prediction algorithms using hidden Markov models

Stephen Wong et al.

JOURNAL OF NEUROPHYSIOLOGY (2007)

Review Clinical Neurology

Seizure prediction: the long and winding road

Florian Mormann et al.

BRAIN (2007)

Article Medicine, General & Internal

Health professionals' and service users' interpretation of screening test results: experimental study

Ros Bramwell et al.

BMJ-BRITISH MEDICAL JOURNAL (2006)

Review Physics, Multidisciplinary

Complex networks: Structure and dynamics

S. Boccaletti et al.

PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS (2006)

Article Clinical Neurology

On the predictability of epileptic seizures

F Mormann et al.

CLINICAL NEUROPHYSIOLOGY (2005)

Article Physics, Fluids & Plasmas

Testing the null hypothesis of the nonexistence of a preseizure state

RG Andrzejak et al.

PHYSICAL REVIEW E (2003)