Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings.

There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings. To overcome this, we hosted a kaggle.com competition to crowdsource the development of seizure detection algorithms using intracranial electroencephalography from canines and humans with epilepsy. The top three performing algorithms from the contest were then validated on out-of-sample patient data including standard clinical data and continuous ambulatory human data obtained over several years using the implantable NeuroVista seizure advisory system. Two hundred teams of data scientists from all over the world participated in the kaggle.com competition. The top performing teams submitted highly accurate algorithms with consistent performance in the out-of-sample validation study. The performance of these seizure detection algorithms, achieved using freely available code and data, sets a new reproducible benchmark for personalized seizure detection. We have also shared a 'plug and play' pipeline to allow other researchers to easily use these algorithms on their own datasets. The success of this competition demonstrates how sharing code and high quality data results in the creation of powerful translational tools with significant potential to impact patient care.

Data integration: Combined imaging and electrophysiology data in the cloud.

There has been an increasing effort to correlate electrophysiology data with imaging in patients with refractory epilepsy over recent years. IEEG.org provides a free-access, rapidly growing archive of imaging data combined with electrophysiology data and patient metadata. It currently contains over 1200 human and animal datasets, with multiple data modalities associated with each dataset (neuroimaging, EEG, EKG, de-identified clinical and experimental data, etc.). The platform is developed around the concept that scientific data sharing requires a flexible platform that allows sharing of data from multiple file formats. IEEG.org provides high- and low-level access to the data in addition to providing an environment in which domain experts can find, visualize, and analyze data in an intuitive manner. Here, we present a summary of the current infrastructure of the platform, available datasets and goals for the near future.

The SPARC DRC: Building a Resource for the Autonomic Nervous System Community.

The Data and Resource Center (DRC) of the NIH-funded SPARC program is developing databases, connectivity maps, and simulation tools for the mammalian autonomic nervous system. The experimental data and mathematical models supplied to the DRC by the SPARC consortium are curated, annotated and semantically linked via a single knowledgebase. A data portal has been developed that allows discovery of data and models both via semantic search and via an interface that includes Google Map-like 2D flatmaps for displaying connectivity, and 3D anatomical organ scaffolds that provide a common coordinate framework for cross-species comparisons. We discuss examples that illustrate the data pipeline, which includes data upload, curation, segmentation (for image data), registration against the flatmaps and scaffolds, and finally display via the web portal, including the link to freely available online computational facilities that will enable neuromodulation hypotheses to be investigated by the autonomic neuroscience community and device manufacturers.

IRIS: A Modular Platform for Continuous Monitoring and Caretaker Notification in the Intensive Care Unit.

OBJECTIVE: New approaches are needed to interpret large amounts of physiologic data continuously recorded in the ICU. We developed and prospectively validated a versatile platform (IRIS) for real-time ICU physiologic monitoring, clinical decision making, and caretaker notification. METHODS: IRIS was implemented in the neurointensive care unit to stream multimodal time series data, including EEG, intracranial pressure (ICP), and brain tissue oxygenation (PbtO2), from ICU monitors to an analysis server. IRIS was applied for 364 patients undergoing continuous EEG, 26 patients undergoing burst suppression monitoring, and four patients undergoing intracranial pressure and brain tissue oxygen monitoring. Custom algorithms were used to identify periods of elevated ICP, compute burst suppression ratios (BSRs), and detect faulty or disconnected EEG electrodes. Hospital staff were notified of clinically relevant events using our secure API to route alerts through a password-protected smartphone application. RESULTS: Sustained increases in ICP and concordant decreases in PbtO2 were reliably detected using user-defined thresholds and alert throttling. BSR trends computed by the platform correlated highly with manual neurologist markings (r2 0.633-0.781; p < 0.0001). The platform identified EEG electrodes with poor signal quality with 95% positive predictive value, and reduced latency of technician response by 93%. CONCLUSION: This study validates a flexible real-time platform for monitoring and interpreting ICU data and notifying caretakers of actionable results, with potential to reduce the manual burden of continuous monitoring services on care providers. SIGNIFICANCE: This work represents an important step toward facilitating translational medical data analytics to improve patient care and reduce health care costs.

The effect of increased intracranial EEG sampling rates in clinical practice.

OBJECTIVE: Recent research suggests that high frequency intracranial EEG (iEEG) may improve localization of epileptic networks. This study aims to determine whether recording macroelectrode iEEG with higher sampling rates improves seizure localization in clinical practice. METHODS: 14 iEEG seizures from 10 patients recorded with >2000 Hz sampling rate were downsampled to four sampling rates: 100, 200, 500, 1000 Hz. In the 56 seizures, seizure onset time and location was marked by 5 independent, blinded EEG experts. RESULTS: When reading iEEG under clinical conditions, there was no consistent difference in time or localization of seizure onset or number of electrodes involved in the seizure onset zone with sampling rates varying from 100 to 1000 Hz. Stratification of patients by outcome did not improve with higher sampling rate. CONCLUSION: When utilizing standard clinical protocols, there was no benefit to acquiring iEEGs with sampling rate >100 Hz. Significant variability was noted in EEG marking both within and between individual expert EEG readers. SIGNIFICANCE: Although commercial equipment is capable of sampling much faster than 100 Hz, tools allowing visualization of subtle high frequency activity such as HFOs will be required to improve patient care. Quantitative methods may decrease reader variability, and potentially improve patient outcomes.

Millimeter-scale epileptiform spike propagation patterns and their relationship to seizures.

OBJECTIVE: Current mapping of epileptic networks in patients prior to epilepsy surgery utilizes electrode arrays with sparse spatial sampling (∼1.0 cm inter-electrode spacing). Recent research demonstrates that sub-millimeter, cortical-column-scale domains have a role in seizure generation that may be clinically significant. We use high-resolution, active, flexible surface electrode arrays with 500 µm inter-electrode spacing to explore epileptiform local field potential (LFP) spike propagation patterns in two dimensions recorded from subdural micro-electrocorticographic signals in vivo in cat. In this study, we aimed to develop methods to quantitatively characterize the spatiotemporal dynamics of epileptiform activity at high-resolution. APPROACH: We topically administered a GABA-antagonist, picrotoxin, to induce acute neocortical epileptiform activity leading up to discrete electrographic seizures. We extracted features from LFP spikes to characterize spatiotemporal patterns in these events. We then tested the hypothesis that two-dimensional spike patterns during seizures were different from those between seizures. MAIN RESULTS: We showed that spatially correlated events can be used to distinguish ictal versus interictal spikes. SIGNIFICANCE: We conclude that sub-millimeter-scale spatiotemporal spike patterns reveal network dynamics that are invisible to standard clinical recordings and contain information related to seizure-state.

Correction: Forecasting Seizures Using Bivariate Intracranial EEG Measures and SVM in Naturally Occurring Canine Epilepsy.

[This corrects the article DOI: 10.1371/journal.pone.0133900.].

Collaborating and sharing data in epilepsy research.

Technological advances are dramatically advancing translational research in Epilepsy. Neurophysiology, imaging, and metadata are now recorded digitally in most centers, enabling quantitative analysis. Basic and translational research opportunities to use these data are exploding, but academic and funding cultures prevent this potential from being realized. Research on epileptogenic networks, antiepileptic devices, and biomarkers could progress rapidly if collaborative efforts to digest this "big neuro data" could be organized. Higher temporal and spatial resolution data are driving the need for novel multidimensional visualization and analysis tools. Crowd-sourced science, the same that drives innovation in computer science, could easily be mobilized for these tasks, were it not for competition for funding, attribution, and lack of standard data formats and platforms. As these efforts mature, there is a great opportunity to advance Epilepsy research through data sharing and increase collaboration between the international research community.

Forecasting Seizures Using Intracranial EEG Measures and SVM in Naturally Occurring Canine Epilepsy.

Management of drug resistant focal epilepsy would be greatly assisted by a reliable warning system capable of alerting patients prior to seizures to allow the patient to adjust activities or medication. Such a system requires successful identification of a preictal, or seizure-prone state. Identification of preictal states in continuous long- duration intracranial electroencephalographic (iEEG) recordings of dogs with naturally occurring epilepsy was investigated using a support vector machine (SVM) algorithm. The dogs studied were implanted with a 16-channel ambulatory iEEG recording device with average channel reference for a mean (st. dev.) of 380.4 (+87.5) days producing 220.2 (+104.1) days of intracranial EEG recorded at 400 Hz for analysis. The iEEG records had 51.6 (+52.8) seizures identified, of which 35.8 (+30.4) seizures were preceded by more than 4 hours of seizure-free data. Recorded iEEG data were stratified into 11 contiguous, non-overlapping frequency bands and binned into one-minute synchrony features for analysis. Performance of the SVM classifier was assessed using a 5-fold cross validation approach, where preictal training data were taken from 90 minute windows with a 5 minute pre-seizure offset. Analysis of the optimal preictal training time was performed by repeating the cross validation over a range of preictal windows and comparing results. We show that the optimization of feature selection varies for each subject, i.e. algorithms are subject specific, but achieve prediction performance significantly better than a time-matched Poisson random predictor (p<0.05) in 5/5 dogs analyzed.

Investigating membrane breakdown of neuronal cells exposed to nonuniform electric fields by finite-element modeling and experiments.

High electric field strengths may induce high cell membrane potentials. At a certain breakdown level the membrane potential becomes constant due to the transition from an insulating state into a high conductivity and high permeability state. Pores are thought to be created through which molecules may be transported into and out of the cell interior. Membrane rupture may follow due to the expansion of pores or the creation of many small pores across a certain part of the membrane surface. In nonuniform electric fields, it is difficult to predict the electroporated membrane area. Therefore, in this study the induced membrane potential and the membrane area where this potential exceeds the breakdown level is investigated by finite-element modeling. Results from experiments in which the collapse of neuronal cells was detected were combined with the computed field strengths in order to investigate membrane breakdown and membrane rupture. It was found that in nonuniform fields membrane rupture is position dependent, especially at higher breakdown levels. This indicates that the size of the membrane site that is affected by electroporation determines rupture.

Real-time control of hind limb functional electrical stimulation using feedback from dorsal root ganglia recordings.

OBJECTIVE: Functional electrical stimulation (FES) approaches often utilize an open-loop controller to drive state transitions. The addition of sensory feedback may allow for closed-loop control that can respond effectively to perturbations and muscle fatigue. APPROACH: We evaluated the use of natural sensory nerve signals obtained with penetrating microelectrode arrays in lumbar dorsal root ganglia (DRG) as real-time feedback for closed-loop control of FES-generated hind limb stepping in anesthetized cats. MAIN RESULTS: Leg position feedback was obtained in near real-time at 50 ms intervals by decoding the firing rates of more than 120 DRG neurons recorded simultaneously. Over 5 m of effective linear distance was traversed during closed-loop stepping trials in each of two cats. The controller compensated effectively for perturbations in the stepping path when DRG sensory feedback was provided. The presence of stimulation artifacts and the quality of DRG unit sorting did not significantly affect the accuracy of leg position feedback obtained from the linear decoding model as long as at least 20 DRG units were included in the model. SIGNIFICANCE: This work demonstrates the feasibility and utility of closed-loop FES control based on natural neural sensors. Further work is needed to improve the controller and electrode technologies and to evaluate long-term viability.

Online feedback control of functional electrical stimulation using dorsal root ganglia recordings.

In neuroprostheses that use functional electrical stimulation (FES) to restore motor function, closed-loop feedback control may compensate for muscle fatigue, perturbations and nonlinearities in the behavior of the effected muscles. Kinematic state information is naturally represented in the firing rates of primary afferent neurons, which may be recorded with multi-electrode arrays at the level of the dorsal root ganglia (DRG). Previous work in cats has shown that it is feasible to estimate the kinematic state of the hind limb with a multivariate linear regression model of the neural activity in the DRG. In this study we extend these results to estimate the limb state in real-time during intramuscular stimulation in an anesthetized cat. Furthermore, we used the limb state estimates as feedback to a finite state FES controller to generate rudimentary walking behavior. This work demonstrates the feasibility of using DRG activity in a closed-loop FES system.