Philippa J. Karoly

Interictal spikes and epileptic seizures: their relationship and underlying rhythmicity

We report on a quantitative analysis of electrocorticography data from a study that acquired continuous ambulatory recordings in humans over extended periods of time. The objectives were to examine patterns of seizures and spontaneous interictal spikes, their relationship to each other, and the nature of periodic variation. The recorded data were originally acquired for the purpose of seizure prediction, and were subsequently analysed in further detail. A detection algorithm identified potential seizure activity and a template matched filter was used to locate spikes. Seizure events were confirmed manually and classified as either clinically correlated, electroencephalographically identical but not clinically correlated, or subclinical. We found that spike rate was significantly altered prior to seizure in 9 out of 15 subjects. Increased pre-ictal spike rate was linked to improved predictability; however, spike rate was also shown to decrease before seizure (in 6 out of the 9 subjects). The probability distribution of spikes and seizures were notably similar, i.e. at times of high seizure likelihood the probability of epileptic spiking also increased. Both spikes and seizures showed clear evidence of circadian regulation and, for some subjects, there were also longer term patterns visible over weeks to months. Patterns of spike and seizure occurrence were highly subject-specific. The pre-ictal decrease in spike rate is not consistent with spikes promoting seizures. However, the fact that spikes and seizures demonstrate similar probability distributions suggests they are not wholly independent processes. It is possible spikes actively inhibit seizures, or that a decreased spike rate is a secondary symptom of the brain approaching seizure. If spike rate is modulated by common regulatory factors as seizures then spikes may be useful biomarkers of cortical excitability.

Estimation of effective connectivity via data-driven neural modeling

This research introduces a new method for functional brain imaging via a process of model inversion. By estimating parameters of a computational model, we are able to track effective connectivity and mean membrane potential dynamics that cannot be directly measured using electrophysiological measurements alone. The ability to track the hidden aspects of neurophysiology will have a profound impact on the way we understand and treat epilepsy. For example, under the assumption the model captures the key features of the cortical circuits of interest, the framework will provide insights into seizure initiation and termination on a patient-specific basis. It will enable investigation into the effect a particular drug has on specific neural populations and connectivity structures using minimally invasive measurements. The method is based on approximating brain networks using an interconnected neural population model. The neural population model is based on a neural mass model that describes the functional activity of the brain, capturing the mesoscopic biophysics and anatomical structure. The model is made subject-specific by estimating the strength of intra-cortical connections within a region and inter-cortical connections between regions using a novel Kalman filtering method. We demonstrate through simulation how the framework can be used to track the mechanisms involved in seizure initiation and termination.

Seizure Prediction: Science Fiction or Soon to Become Reality?

This review highlights recent developments in the field of epileptic seizure prediction. We argue that seizure prediction is possible; however, most previous attempts have used data with an insufficient amount of information to solve the problem. The review discusses four methods for gaining more information above standard clinical electrophysiological recordings. We first discuss developments in obtaining long-term data that enables better characterisation of signal features and trends. Then, we discuss the usage of electrical stimulation to probe neural circuits to obtain robust information regarding excitability. Following this, we present a review of developments in high-resolution micro-electrode technologies that enable neuroimaging across spatial scales. Finally, we present recent results from data-driven model-based analyses, which enable imaging of seizure generating mechanisms from clinical electrophysiological measurements. It is foreseeable that the field of seizure prediction will shift focus to a more probabilistic forecasting approach leading to improvements in the quality of life for the millions of people who suffer uncontrolled seizures. However, a missing piece of the puzzle is devices to acquire long-term high-quality data. When this void is filled, seizure prediction will become a reality.

A forward-looking review of seizure prediction

Purpose of review Seizure prediction has made important advances over the last decade, with the recent demonstration that prospective seizure prediction is possible, though there remain significant obstacles to broader application. In this review, we will describe insights gained from long-term trials, with the aim of identifying research goals for the next decade. Recent findings Unexpected results from these studies, including strong and highly individual relationships between spikes and seizures, diurnal patterns of seizure activity, and the coexistence of different seizure populations within individual patients exhibiting distinctive dynamics, have caused us to re-evaluate many prior assumptions in seizure prediction studies and suggest alternative strategies that could be employed in the search for algorithms providing greater clinical utility. Advances in analytical approaches, particularly deep-learning techniques, harbour great promise and in combination with less-invasive systems with sufficiently power-efficient computational capacity will bring broader clinical application within reach. Summary We conclude the review with an exercise in wishful thinking, which asks what the ideal seizure prediction dataset would look like and how these data should be manipulated to maximize benefits for patients. The motivation for structuring the review in this way is to create a forward-looking, optimistic critique of the existing methodologies.

Human focal seizures are characterized by populations of fixed duration and interval.

We report on a quantitative analysis of data from a study that acquired continuous long‐term ambulatory human electroencephalography (EEG) data over extended periods. The objectives were to examine the seizure duration and interseizure interval (ISI), their relationship to each other, and the effect of these features on the clinical manifestation of events.

The circadian profile of epilepsy improves seizure forecasting

It is now established that epilepsy is characterized by periodic dynamics that increase seizure likelihood at certain times of day, and which are highly patient-specific. However, these dynamics are not typically incorporated into seizure prediction algorithms due to the difficulty of estimating patient-specific rhythms from relatively short-term or unreliable data sources. This work outlines a novel framework to develop and assess seizure forecasts, and demonstrates that the predictive power of forecasting models is improved by circadian information. The analyses used long-term, continuous electrocorticography from nine subjects, recorded for an average of 320 days each. We used a large amount of out-of-sample data (a total of 900 days for algorithm training, and 2879 days for testing), enabling the most extensive post hoc investigation into seizure forecasting. We compared the results of an electrocorticography-based logistic regression model, a circadian probability, and a combined electrocorticography and circadian model. For all subjects, clinically relevant seizure prediction results were significant, and the addition of circadian information (combined model) maximized performance across a range of outcome measures. These results represent a proof-of-concept for implementing a circadian forecasting framework, and provide insight into new approaches for improving seizure prediction algorithms. The circadian framework adds very little computational complexity to existing prediction algorithms, and can be implemented using current-generation implant devices, or even non-invasively via surface electrodes using a wearable application. The ability to improve seizure prediction algorithms through straightforward, patient-specific modifications provides promise for increased quality of life and improved safety for patients with epilepsy.

A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery

This work describes a generalized method for classifying motor-related neural signals for a brain-computer interface (BCI), based on a stochastic machine learning method. The method differs from the various feature extraction and selection techniques employed in many other BCI systems. The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge. Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure. The results showed that the average performance of the new algorithm outperformed other published methods using the Berlin BCI IV (2008) competition dataset and was comparable to the best results in the Berlin BCI II (2002–3) competition dataset. The new method was also applied to electroencephalography (EEG) data recorded from five subjects undertaking a hand squeeze task and demonstrated high levels of accuracy with a mean classification accuracy of 78.9% after five-fold cross-validation. Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System

Background Seizure prediction can increase independence and allow preventative treatment for patients with epilepsy. We present a proof-of-concept for a seizure prediction system that is accurate, fully automated, patient-specific, and tunable to an individuals needs. Methods Intracranial electroencephalography (iEEG) data of ten patients obtained from a seizure advisory system were analyzed as part of a pseudoprospective seizure prediction study. First, a deep learning classifier was trained to distinguish between preictal and interictal signals. Second, classifier performance was tested on held-out iEEG data from all patients and benchmarked against the performance of a random predictor. Third, the prediction system was tuned so sensitivity or time in warning could be prioritized by the patient. Finally, a demonstration of the feasibility of deployment of the prediction system onto an ultra-low power neuromorphic chip for autonomous operation on a wearable device is provided. Results The prediction system achieved mean sensitivity of 69% and mean time in warning of 27%, significantly surpassing an equivalent random predictor for all patients by 42%. Conclusion This study demonstrates that deep learning in combination with neuromorphic hardware can provide the basis for a wearable, real-time, always-on, patient-specific seizure warning system with low power consumption and reliable long-term performance.

Simulating clinical trials with and without intracranial EEG data

It is currently unknown whether knowledge of clinically silent (electrographic) seizures improves the statistical efficiency of clinical trials.

Postictal suppression and seizure durations: A patient-specific, long-term iEEG analysis

We report on patient‐specific durations of postictal periods in long‐term intracranial electroencephalography (iEEG) recordings. The objective was to investigate the relationship between seizure duration and postictal suppression duration.