Prediction of Seizure Recurrence. A Note of Caution

Feasibility of cardiac-based seizure detection and prediction: A systematic review of non-invasive wearable sensor-based studies

A reliable seizure detection or prediction device can potentially reduce the morbidity and mortality associated with epileptic seizures. Previous findings indicating alterations in cardiac activity during seizures suggest the usefulness of cardiac parameters for seizure detection or prediction. This study aims to examine available studies on seizure detection and prediction based on cardiac parameters using non-invasive wearable devices. The Embase, PubMed, and Scopus databases were used to systematically search according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Human studies that evaluated seizure detection or prediction based on cardiac parameters collected using wearable devices were included. The QUADAS-2 tool and proposed standards for validation for seizure detection devices were used for quality assessment. Twenty-four articles were identified and included in the analysis. Twenty studies evaluated seizure detection algorithms, and four studies focused on seizure prediction. Most studies used either a wrist-worn or chest-worn device for data acquisition. Among the seizure detection studies, cardiac parameters utilized for the algorithms mainly included heart rate (HR) (n = 11) or a combination of HR and heart rate variability (HRV) (n = 6). HR-based seizure detection studies collectively reported a sensitivity range of 56%-100% and a false alarm rate (FAR) of 0.02-8/h, with most studies performing retrospective validation of the algorithms. Three of the seizure prediction studies retrospectively validated multimodal algorithms, combining cardiac features with other physiological signals. Only one study prospectively validated their seizure prediction algorithm using HRV extracted from ECG data collected from a custom wearable device. These studies have demonstrated the feasibility of using cardiac parameters for seizure detection and prediction with wearable devices, with varying algorithmic performance. Many studies are in the proof-of-principle stage, and evidence for real-time detection or prediction is currently limited. Future studies should prioritize further refinement of the algorithm performance with prospective validation using large-scale longitudinal data. PLAIN LANGUAGE SUMMARY: This systematic review highlights the potential use of wearable devices, like wristbands, for detecting and predicting seizures via the measurement of heart activity. By reviewing 24 articles, it was found that most studies focused on using heart rate and changes in heart rate for seizure detection. There was a lack of studies looking at seizure prediction. The results were promising but most studies were not conducted in real-time. Therefore, more real-time studies are needed to verify the usage of heart activity-related wearable devices to detect seizures and even predict them, which will be beneficial to people with epilepsy.

Structure and function in artificial, zebrafish and human neural networks

Network science provides a set of tools for the characterization of the structure and functional behavior of complex systems. Yet a major problem is to quantify how the structural domain is related to the dynamical one. In other words, how the diversity of dynamical states of a system can be predicted from the static network structure? Or the reverse problem: starting from a set of signals derived from experimental recordings, how can one discover the network connections or the causal relations behind the observed dynamics? Despite the advances achieved over the last two decades, many challenges remain concerning the study of the structure-dynamics interplay of complex systems. In neuroscience, progress is typically constrained by the low spatio-temporal resolution of experiments and by the lack of a universal inferring framework for empirical systems. To address these issues, applications of network science and artificial intelligence to neural data have been rapidly growing. In this article, we review important recent applications of methods from those fields to the study of the interplay between structure and functional dynamics of human and zebrafish brain. We cover the selection of topological features for the characterization of brain networks, inference of functional connections, dynamical modeling, and close with applications to both the human and zebrafish brain. This review is intended to neuroscientists who want to become acquainted with techniques from network science, as well as to researchers from the latter field who are interested in exploring novel application scenarios in neuroscience.

Weak self-supervised learning for seizure forecasting: a feasibility study

This paper proposes an artificial intelligence system that continuously improves over time at event prediction using initially unlabelled data by using self-supervised learning. Time-series data are inherently autocorrelated. By using a detection model to generate weak labels on the fly, which are concurrently used as targets to train a prediction model on a time-shifted input data stream, this autocorrelation can effectively be harnessed to reduce the burden of manual labelling. This is critical in medical patient monitoring, as it enables the development of personalized forecasting models without demanding the annotation of long sequences of physiological signal recordings. We perform a feasibility study on seizure prediction, which is identified as an ideal test case, as pre-ictal brainwaves are patient-specific, and tailoring models to individual patients is known to improve forecasting performance significantly. Our self-supervised approach is used to train individualized forecasting models for 10 patients, showing an average relative improvement in sensitivity by 14.30% and a reduction in false alarms by 19.61% in early seizure forecasting. This proof-of-concept on the feasibility of using a continuous stream of time-series neurophysiological data paves the way towards a low-power neuromorphic neuromodulation system.

The Interplay Between Neuroinfections, the Immune System and Neurological Disorders: A Focus on Africa

Neurological disorders related to neuroinfections are highly prevalent in Sub-Saharan Africa (SSA), constituting a major cause of disability and economic burden for patients and society. These include epilepsy, dementia, motor neuron diseases, headache disorders, sleep disorders, and peripheral neuropathy. The highest prevalence of human immunodeficiency virus (HIV) is in SSA. Consequently, there is a high prevalence of neurological disorders associated with HIV infection such as HIV-associated neurocognitive disorders, motor disorders, chronic headaches, and peripheral neuropathy in the region. The pathogenesis of these neurological disorders involves the direct role of the virus, some antiretroviral treatments, and the dysregulated immune system. Furthermore, the high prevalence of epilepsy in SSA (mainly due to perinatal causes) is exacerbated by infections such as toxoplasmosis, neurocysticercosis, onchocerciasis, malaria, bacterial meningitis, tuberculosis, and the immune reactions they elicit. Sleep disorders are another common problem in the region and have been associated with infectious diseases such as human African trypanosomiasis and HIV and involve the activation of the immune system. While most headache disorders are due to benign primary headaches, some secondary headaches are caused by infections (meningitis, encephalitis, brain abscess). HIV and neurosyphilis, both common in SSA, can trigger long-standing immune activation in the central nervous system (CNS) potentially resulting in dementia. Despite the progress achieved in preventing diseases from the poliovirus and retroviruses, these microbes may cause motor neuron diseases in SSA. The immune mechanisms involved in these neurological disorders include increased cytokine levels, immune cells infiltration into the CNS, and autoantibodies. This review focuses on the major neurological disorders relevant to Africa and neuroinfections highly prevalent in SSA, describes the interplay between neuroinfections, immune system, neuroinflammation, and neurological disorders, and how understanding this can be exploited for the development of novel diagnostics and therapeutics for improved patient care.

Seizure Susceptibility Prediction in Uncontrolled Epilepsy

Epileptic seizure forecasting, combined with the delivery of preventative therapies, holds the potential to greatly improve the quality of life for epilepsy patients and their caregivers. Forecasting seizures could prevent some potentially catastrophic consequences such as injury and death in addition to several potential clinical benefits it may provide for patient care in hospitals. The challenge of seizure forecasting lies within the seemingly unpredictable transitions of brain dynamics into the ictal state. The main body of computational research on determining seizure risk has been focused solely on prediction algorithms, which involves a challenging issue of balancing sensitivity and false alarms. There have been some studies on identifying potential biomarkers for seizure forecasting; however, the questions of “What are the true biomarkers for seizure prediction” or even “Is there a valid biomarker for seizure prediction?” are yet to be fully answered. In this paper, we introduce a tool to facilitate the exploration of the potential biomarkers. We confirm using our tool that interictal slowing activities are a promising biomarker for epileptic seizure susceptibility prediction.

Prolonged and short epileptiform discharges have an opposite relationship with the sleep-wake cycle in patients with JME: Implications for EEG recording protocols

In a recent study, we found that during 20.55 ± 1.60 h of artifact-free ambulatory EEG recordings, epileptiform discharges (EDs) longer than 2.68 s occurred exclusively in patients with Juvenile Myoclonic Epilepsy (JME) who experienced seizure recurrence within a year after the EEG. Here we expanded this analysis, exploring whether long EDs (>2.68 s), and short ones, were uniformly distributed during the day. Lastly, we evaluated the temporal distribution of seizure relapses. By Friedman test, we demonstrated that hourly frequencies of both short and long EDs were dependent on the hours of day and sleep-wake cycle factors, with an opposite trend. Short EDs were found mostly during the night (with two peaks at 1 AM and 6 AM), and sleep, dropping at the wake onset (p < 0.001). Conversely, long EDs surged at the wake onset (0.001), remaining frequent during the whole wake period, when compared to sleep (p = 0.002). Of note, this latter pattern mirrored that of seizures, which occurred exclusively during the wake period, and in 9 out of 13 cases at the wake onset. We therefore suggested that short and long EDs could reflect distinct pathophysiological phenomena. Extended wake EEG recordings, possibly including the awakening, could be extremely useful in clinical practice, as well as in further studies, with the ambitious goal of predicting seizure recurrences.