Analog seizure detection and performance evaluation

Computationally efficient neural network classifiers for next generation closed loop neuromodulation therapy - a case study in epilepsy

This work explores the potential utility of neural network classifiers for real-time classification of field-potential based biomarkers in next-generation responsive neuromodulation systems. Compared to classical filter-based classifiers, neural networks offer an ease of patient-specific parameter tuning, promising to reduce the burden of programming on clinicians. The paper explores a compact, feed-forward neural network architecture of only dozens of units for seizure-state classification in refractory epilepsy. The proposed classifier offers comparable accuracy to filterclassifiers on clinician-labeled data, while reducing detection latency. As a trade-off to classical methods, the paper focuses on keeping the complexity of the architecture minimal, to accommodate the on-board computational constraints of implantable pulse generator systems.

Clinical relevance—A neural network-based classifier is presented for responsive neurostimulation, with comparable accuracy to classical methods at reduced latency.

DyNeuMo Mk-2: An Investigational Circadian-Locked Neuromodulator with Responsive Stimulation for Applied Chronobiology

Deep brain stimulation (DBS) for Parkinson's disease, essential tremor and epilepsy is an established palliative treatment. DBS uses electrical neuromodulation to suppress symptoms. Most current systems provide a continuous pattern of fixed stimulation, with clinical follow-ups to refine settings constrained to normal office hours. An issue with this management strategy is that the impact of stimulation on circadian, i.e. sleep-wake, rhythms is not fully considered; either in the device design or in the clinical follow-up. Since devices can be implanted in brain targets that couple into the reticular activating network, impact on wakefulness and sleep can be significant. This issue will likely grow as new targets are explored, with the potential to create entraining signals that are uncoupled from environmental influences. To address this issue, we have designed a new brain-machine-interface for DBS that combines a slow-adaptive circadian-based stimulation pattern with a fast-acting pathway for responsive stimulation, demonstrated here for seizure management. In preparation for first-in-human research trials to explore the utility of multi-timescale automated adaptive algorithms, design and prototyping was carried out in line with ISO risk management standards, ensuring patient safety. The ultimate aim is to account for chronobiology within the algorithms embedded in brain-machine-interfaces and in neuromodulation technology more broadly.

Reliability Analysis of an Epileptic Seizure Detector Powered by an Energy Harvester

Due to a limited lifetime of a battery, energy harvesters have been studied as alternative energy sources for implantable biomedical devices such as an implantable stimulator for epileptic seizure suppression. However, energy harvesters have weakness in providing stable power. We designed a neural recording circuit powered solely by a piezoelectric energy harvester, and applied its output to a seizure detector to analyze the reliability of the recorded signal. Performance of the seizure detector was evaluated. We found that the average time differences between with and without voltage variances were about 0.05 s under regular vibrations and about 0.07 s under irregular vibrations, respectively. The ratio of average true positive alarm period varied within about 0.02% under regular vibrations and 0.029% under irregular vibrations, respectively. The ratio of average false positive alarm period varied within about 0.004% under regular vibrations and 0.014% under irregular vibrations, respectively. This paper presents a reliability analysis of an epileptic seizure detector with a neural signal recording circuit powered by a piezoelectric energy harvester. The results showed that a supply voltage variance within ±10% could be acceptable for reliable operation of a seizure detector.

Closed-Loop Neurostimulators: A Survey and A Seizure-Predicting Design Example for Intractable Epilepsy Treatment

First, existing commercially available open-loop and closed-loop implantable neurostimulators are reviewed and compared in terms of their targeted application, physical size, system-level features, and performance as a medical device. Next, signal processing algorithms as the primary strength point of the closed-loop neurostimulators are reviewed, and various design and implementation requirements and trade-offs are discussed in details along with quantitative examples. The review results in a set of guidelines for algorithm selection and evaluation. Second, the implementation of an inductively-powered seizure-predicting microsystem for monitoring and treatment of intractable epilepsy is presented. The miniaturized system is comprised of two miniboards and a power receiver coil. The first board hosts a 24-channel neurostimulator system on chip fabricated in a [Formula: see text] CMOS technology and performs neural recording, on-chip digital signal processing, and electrical stimulation. The second board communicates recorded brain signals as well as signal processing results wirelessly. The multilayer flexible coil receives inductively-transmitted power. The system is sized at 2 × 2 × 0.7 [Formula: see text] and weighs 6 g. The approach is validated in the control of chronic seizures in vivo in freely moving rats.

Analysis of epileptic seizures with complex network

Epilepsy is a disease of abnormal neural activities involving large area of brain networks. Until now the nature of functional brain network associated with epilepsy is still unclear. Recent researches indicate that the small world or scale-free attributes and the occurrence of highly clustered connection patterns could represent a general organizational principle in the human brain functional network. In this paper, we seek to find whether the small world or scale-free property of brain network is correlated with epilepsy seizure formation. A mass neural model was adopted to generate multiple channel EEG recordings based on regular, small world, random, and scale-free network models. Whether the connection patterns of cortical networks are directly associated with the epileptic seizures was investigated. The results showed that small world and scale-free cortical networks are highly correlated with the occurrence of epileptic seizures. In particular, the property of small world network is more significant during the epileptic seizures.

Coercively adjusted auto regression model for forecasting in epilepsy EEG

Recently, data with complex characteristics such as epilepsy electroencephalography (EEG) time series has emerged. Epilepsy EEG data has special characteristics including nonlinearity, nonnormality, and nonperiodicity. Therefore, it is important to find a suitable forecasting method that covers these special characteristics. In this paper, we propose a coercively adjusted autoregression (CA-AR) method that forecasts future values from a multivariable epilepsy EEG time series. We use the technique of random coefficients, which forcefully adjusts the coefficients with −1 and 1. The fractal dimension is used to determine the order of the CA-AR model. We applied the CA-AR method reflecting special characteristics of data to forecast the future value of epilepsy EEG data. Experimental results show that when compared to previous methods, the proposed method can forecast faster and accurately.

Epileptic seizure detection with the local field potential of anterior thalamic of rats aiming at real time application

Treating epilepsy with deep brain stimulation (DBS) is attracting more and more attention these years, especially the close loop method that gives stimuli when needed so that the implanted device will work longer. People have tried to detect seizure with electrocorticogram (ECoG), but the extra implants put more risks to it. We plan to detect seizure with local field potential (LFP) that recorded with depth electrodes of traditional DBS. To prove the validation of this method, we recorded local field potential (LFP) of anterior thalamic (ANT) of rats who have been induced to acute temporal lobe epilepsy (TLE) by kainic acid injected in hippocampus, and succeeded in detecting electrographic onset (EO) in these data. A variation of generic Osorio-Frei algorithm (GOFA) was used as the detection method with some adjustments which mainly focus on increasing calculation speed and decreasing number of total calculations to meet the future need of transplanting to battery powered embedded medical device.

A novel low-power-implantable epileptic seizure-onset detector

A novel implantable low-power integrated circuit is proposed for real-time epileptic seizure detection. The presented chip is part of an epilepsy prosthesis device that triggers focal treatment to disrupt seizure progression. The proposed chip integrates a front-end preamplifier, voltage-level detectors, digital demodulators, and a high-frequency detector. The preamplifier uses a new chopper stabilizer topology that reduces instrumentation low-frequency and ripple noises by modulating the signal in the analog domain and demodulating it in the digital domain. Moreover, each voltage-level detector consists of an ultra-low-power comparator with an adjustable threshold voltage. The digitally integrated high-frequency detector is tunable to recognize the high-frequency activities for the unique detection of seizure patterns specific to each patient. The digitally controlled circuits perform accurate seizure detection. A mathematical model of the proposed seizure detection algorithm was validated in Matlab and circuits were implemented in a 2 mm(2) chip using the CMOS 0.18- μm process. The proposed detector was tested by using intracerebral electroencephalography (icEEG) recordings from seven patients with drug-resistant epilepsy. The seizure signals were assessed by the proposed detector and the average seizure detection delay was 13.5 s, well before the onset of clinical manifestations. The measured total power consumption of the detector is 51 μW.

Phase-Synchronization Early Epileptic Seizure Detector VLSI Architecture

A low-power VLSI processor architecture that computes in real time the magnitude and phase-synchronization of two input neural signals is presented. The processor is a part of an envisioned closed-loop implantable microsystem for adaptive neural stimulation. The architecture uses three CORDIC processing cores that require shift-and-add operations but no multiplication. The 10-bit processor synthesized and prototyped in a standard 1.2 V 0.13 μm CMOS technology utilizes 41,000 logic gates. It dissipates 3.6 μW per input pair, and provides 1.7 kS/s per-channel throughput when clocked at 2.5 MHz. The power scales linearly with the number of input channels or the sampling rate. The efficacy of the processor in early epileptic seizure detection is validated on human intracranial EEG data.

Epileptic seizure onset detection prior to clinical manifestation

In this paper, we present the design of an epilepticseizure detector. This circuit is part of an implantable device used to continuously record intracerebral electroencephalographic signals through subdural and depth electrodes. The implemented seizure detector is based on a detection algorithm validated in Matlab tools and the circuits were implemented using CMOS 0.18-microm process. The proposed system was tested using intracerebral EEG recordings from two patients with drug-resistant epilepsy. Four seizures were assessed by the proposed CMOS building blocks and the required delays to detect these seizures were 3, 8, 11, and 11 sec, respectively after electric onset. The simulated total power consumption of the detector was 6.71 microW. Together, these preliminary results indicate the possibility of building implantable ultra-low power seizure-detection devices.

Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection

Fractal dimension (FD) is a natural measure of the irregularity of a curve. In this study the performances of three waveform FD estimation algorithms (i.e. Katz's, Higuchi's and the k-nearest neighbour (k-NN) algorithm) were compared in terms of their ability to detect the onset of epileptic seizures in scalp electroencephalogram (EEG). The selection of parameters involved in FD estimation, evaluation of the accuracy of the different algorithms and assessment of their robustness in the presence of noise were performed based on synthetic signals of known FD. When applied to scalp EEG data, Katz's and Higuchi's algorithms were found to be incapable of producing consistent changes of a single type (either a drop or an increase) during seizures. On the other hand, the k-NN algorithm produced a drop, starting close to the seizure onset, in most seizures of all patients. The k-NN algorithm outperformed both Katz's and Higuchi's algorithms in terms of robustness in the presence of noise and seizure onset detection ability. The seizure detection methodology, based on the k-NN algorithm, yielded in the training data set a sensitivity of 100% with 10.10 s mean detection delay and a false positive rate of 0.27 h(-1), while the corresponding values in the testing data set were 100%, 8.82 s and 0.42 h(-1), respectively. The above detection results compare favourably to those of other seizure onset detection methodologies applied to scalp EEG in the literature. The methodology described, based on the k-NN algorithm, appears to be promising for the detection of the onset of epileptic seizures based on scalp EEG.

Dynamic channel selection to reduce computational burden in seizure detection

Ambulatory physiological monitoring devices benefit patients, medical staff and hospitals by allowing patients to return home with the devices for monitoring. The main problem associated with designing such devices is that of power consumption. Wireless communications and complex processing are generally part of such devices and are power hungry components. These problems are magnified when dealing with EEG signals, with relatively high data rates, multiple channels, and advanced signal processing techniques required. This paper proposes a method to dynamically select EEG channels in the REACT seizure detection system based on information already available in the system, hence keeping any added computational complexity very low. Using the techniques computational effort can be reduced by up to 65% with no effect on the REACT seizure detection performance.

Non-invasive computerized system for automatically initiating vagus nerve stimulation following patient-specific detection of seizures or epileptiform discharges

OBJECTIVE

To demonstrate the feasibility of using a computerized system to detect the onset of a seizure and, in response, initiate Vagus nerve stimulation (VNS) in patients with medically refractory epilepsy.

METHODS

We designed and built a non-invasive, computerized system that automatically initiates VNS following the real-time detection of a pre-identified seizure or epileptiform discharge. The system detects these events through patient-specific analysis of the scalp electroencephalogram (EEG) and electrocardiogram (ECG) signals.

RESULTS

We evaluated the performance of the system on 5 patients (A-E). For patients A and B the computerized system initiated VNS in response to seizures; for patients C and D the system initiated VNS in response to epileptiform discharges; and for patient E neither seizures nor epileptiform discharges were observed during the evaluation period. During the 81 hour clinical test of the system on patient A, the computerized system detected 5/5 seizures and initiated VNS within 5 seconds of the appearance of ictal discharges in the EEG; VNS did not seem to alter the electrographic or behavioral characteristics of the seizures in this case. During the same testing session the computerized system initiated false stimulations at the rate of 1 false stimulus every 2.5 hours while the subject was at rest and not ambulating. During the 26 hour clinical test of the system on patient B, the computerized system detected 1/1 seizures and initiated VNS within 16 seconds of the appearance of ictal discharges; VNS did not alter the electrographic duration of the seizure but decreased anxiety and increased awareness during the post-seizure recovery phase. During the same testing session the computerized system did not declare any false detections.

SIGNIFICANCE

Initiating Vagus nerve stimulation soon after the onset of a seizure may abort or ameliorate seizure symptoms in some patients; unfortunately, a significant number of patients cannot initiate VNS by themselves following the start of a seizure. A system that automatically couples automated detection of seizure onset to initiation of VNS may be helpful for seizure treatment.