Anticipation of epileptic seizures from standard EEG recordings

Utility and rationale for continuous EEG monitoring: a primer for the general intensivist

This review offers a comprehensive guide for general intensivists on the utility of continuous EEG (cEEG) monitoring for critically ill patients. Beyond the primary role of EEG in detecting seizures, this review explores its utility in neuroprognostication, monitoring neurological deterioration, assessing treatment responses, and aiding rehabilitation in patients with encephalopathy, coma, or other consciousness disorders. Most seizures and status epilepticus (SE) events in the intensive care unit (ICU) setting are nonconvulsive or subtle, making cEEG essential for identifying these otherwise silent events. Imaging and invasive approaches can add to the diagnosis of seizures for specific populations, given that scalp electrodes may fail to identify seizures that may be detected by depth electrodes or electroradiologic findings. When cEEG identifies SE, the risk of secondary neuronal injury related to the time-intensity "burden" often prompts treatment with anti-seizure medications. Similarly, treatment may be administered for seizure-spectrum activity, such as periodic discharges or lateralized rhythmic delta slowing on the ictal-interictal continuum (IIC), even when frank seizures are not evident on the scalp. In this setting, cEEG is utilized empirically to monitor treatment response. Separately, cEEG has other versatile uses for neurotelemetry, including identifying the level of sedation or consciousness. Specific conditions such as sepsis, traumatic brain injury, subarachnoid hemorrhage, and cardiac arrest may each be associated with a unique application of cEEG; for example, predicting impending events of delayed cerebral ischemia, a feared complication in the first two weeks after subarachnoid hemorrhage. After brief training, non-neurophysiologists can learn to interpret quantitative EEG trends that summarize elements of EEG activity, enhancing clinical responsiveness in collaboration with clinical neurophysiologists. Intensivists and other healthcare professionals also play crucial roles in facilitating timely cEEG setup, preventing electrode-related skin injuries, and maintaining patient mobility during monitoring.

Heterogeneous correlate and potential diagnostic biomarker of tinnitus based on nonlinear dynamics of resting-state EEG recordings

Tinnitus is a heterogeneous condition of hearing a rattling sound when there is no auditory stimulus. This rattling sound is associated with abnormal synchronous oscillations in auditory and non-auditory cortical areas. Since tinnitus is a highly heterogeneous condition with no objective detection criteria, it is necessary to search for indicators that can be compared between and within participants for diagnostic purposes. This study introduces heterogeneous though comparable indicators of tinnitus through investigation of spontaneous fluctuations in resting-state brain dynamics. The proposed approach uses nonlinear measures of chaos theory, to detect tinnitus and cross correlation patterns to reflect many of the previously reported neural correlates of tinnitus. These indicators may serve as effective measures of tinnitus risk even at early ages before any symptom is reported. The approach quantifies differences in oscillatory brain dynamics of tinnitus and normal subjects. It demonstrates that the left temporal areas of subjects with tinnitus exhibit larger lyapunov exponent indicating irregularity of brain dynamics in these regions. More complex dynamics is further recognized in tinnitus cases through entropy. We use this evidence to distinguish tinnitus patients from normal participants. Besides, we illustrate that certain anticorrelation patterns appear in these nonlinear measures across temporal and frontal areas in the brain perhaps corresponding to increased/decreased connectivity in certain brain networks and a shift in the balance of excitation and inhibition in tinnitus. Additionally, the main correlations are lost in tinnitus participants compared to control group suggesting involvement of distinct neural mechanisms in generation and persistence of tinnitus.

The role of trained and untrained dogs in the detection and warning of seizures

Seizure unpredictability plays a major role in disability and decreased quality of life in people with epilepsy. Dogs have been used to assist people with disabilities and have shown promise in detecting seizures. There have been reports of trained seizure-alerting dogs (SADs) successfully detecting when a seizure is occurring or indicating imminent seizures, allowing patients to take preventative measures. Untrained pet dogs have also shown the ability to detect seizures and provide comfort and protection during and after seizures. Dogs' exceptional olfactory abilities and sensitivity to human cues could contribute to their seizure-detection capabilities. This has been supported by studies in which dogs have distinguished between epileptic seizure and non-seizure sweat samples, probably though the detection of volatile organic compounds (VOCs). However, the existing literature has limitations, with a lack of well-controlled, prospective studies and inconsistencies in reported timings of alerting behaviours. More research is needed to standardize reporting and validate the results. Advances in VOC profiling could aid in distinguishing seizure types and developing rapid and unbiased seizure detection methods. In conclusion, using dogs in epilepsy management shows considerable promise, but further research is needed to fully validate their effectiveness and potential as valuable companions for people with epilepsy.

Preictal neuronal and vascular activity precedes the onset of childhood absence seizure: direct current potential shifts and their correlation with hemodynamic activity

SIGNIFICANCE AIMS

The neurovascular mechanisms underlying the initiation of absence seizures and their dynamics are still not well understood. The objective of this study was to better noninvasively characterize the dynamics of the neuronal and vascular network at the transition from the interictal state to the ictal state of absence seizures and back to the interictal state using a combined electroencephalography (EEG), functional near-infrared spectroscopy (fNIRS), and diffuse correlation spectroscopy (DCS) approach. The second objective was to develop hypotheses about the neuronal and vascular mechanisms that propel the networks to the 3-Hz spikes and wave discharges (SWDs) observed during absence seizures.

APPROACHES

We evaluated the simultaneous changes in electrical (neuronal) and optical dynamics [hemodynamic, with changes in (Hb) and cerebral blood flow] of 8 pediatric patients experiencing 25 typical childhood absence seizures during the transition from the interictal state to the absence seizure by simultaneously performing EEG, fNIRS, and DCS.

RESULTS

Starting from ∼ 20    s before the onset of the SWD, we observed a transient direct current potential shift that correlated with alterations in functional fNIRS and DCS measurements of the cerebral hemodynamics detecting the preictal changes.

DISCUSSION

Our noninvasive multimodal approach highlights the dynamic interactions between the neuronal and vascular compartments that take place in the neuronal network near the time of the onset of absence seizures in a very specific cerebral hemodynamic environment. These noninvasive approaches contribute to a better understanding of the electrical hemodynamic environment prior to seizure onset. Whether this may ultimately be relevant for diagnostic and therapeutic approaches requires further evaluation.

Identification and classification of epileptic EEG signals using invertible constant-Qtransform-based deep convolutional neural network

Context.Epilepsy is the most widespread disorder of the nervous system, affecting humans of all ages and races. The most common diagnostic test in epilepsy is the electroencephalography (EEG).Objective.In this paper, a novel automated deep learning approach based on integrating a pre-trained convolutional neural network (CNN) structure, called AlexNet, with the constant-Qnon-stationary Gabor transform (CQ-NSGT) algorithm is proposed for classifying seizure versus seizure-free EEG records.Approach.The CQ-NSGT method is introduced to transform the input 1D EEG signal into 2D spectrogram which is sent to the AlexNet CNN model. The AlexNet architecture is utilized to capture the discriminating features of the 2D image corresponding to each EEG signal in order to distinguish seizure and non-seizure subjects using multi-layer perceptron algorithm.Main results. The robustness of the introduced CQ-NSGT technique in transforming the 1D EEG signals into 2D spectrograms is assessed by comparing its classification results with the continuous wavelet transform method, and the results elucidate the high performance of the CQ-NSGT technique. The suggested epileptic seizure classification framework is investigated with clinical EEG data acquired from the Bonn University database, and the experimental results reveal the superior performance of the proposed framework over other state-of-the-art approaches with an accuracy of 99.56%, sensitivity of 99.12%, specificity of 99.67%, and precision of 98.69%.Significance.This elucidates the importance of the proposed automated system in helping neurologists to accurately interpret and classify epileptic EEG records without necessitating tedious visual inspection or massive data analysis for long-term EEG signals.

Classification of EEG Signals for Prediction of Epileptic Seizures

Epilepsy is a common brain disorder that causes patients to face multiple seizures in a single day. Around 65 million people are affected by epilepsy worldwide. Patients with focal epilepsy can be treated with surgery, whereas generalized epileptic seizures can be managed with medications. It has been noted that in more than 30% of cases, these medications fail to control epileptic seizures, resulting in accidents and limiting the patient’s life. Predicting epileptic seizures in such patients prior to the commencement of an oncoming seizure is critical so that the seizure can be treated with preventive medicines before it occurs. Electroencephalogram (EEG) signals of patients recorded to observe brain electrical activity during a seizure can be quite helpful in predicting seizures. Researchers have proposed methods that use machine and/or deep learning techniques to predict epileptic seizures using scalp EEG signals; however, prediction of seizures with increased accuracy is still a challenge. Therefore, we propose a three-step approach. It includes preprocessing of scalp EEG signals with PREP pipeline, which is a more sophisticated alternative to basic notch filtering. This method uses a regression-based technique to further enhance the SNR, with a combination of handcrafted, i.e., statistical features such as temporal mean, variance, and skewness, and automated features using CNN, followed by classification of interictal state and preictal state segments using LSTM to predict seizures. We train and validate our proposed technique on the CHB-MIT scalp EEG dataset and achieve accuracy of 94%, sensitivity of 93.8%, and 91.2% specificity. The proposed technique achieves better sensitivity and specificity than existing methods.

Random Neural Network Based Epileptic Seizure Episode Detection Exploiting Electroencephalogram Signals

Epileptic seizures are caused by abnormal electrical activity in the brain that manifests itself in a variety of ways, including confusion and loss of awareness. Correct identification of epileptic seizures is critical in the treatment and management of patients with epileptic disorders. One in four patients present resistance against seizures episodes and are in dire need of detecting these critical events through continuous treatment in order to manage the specific disease. Epileptic seizures can be identified by reliably and accurately monitoring the patients' neuro and muscle activities, cardiac activity, and oxygen saturation level using state-of-the-art sensing techniques including electroencephalograms (EEGs), electromyography (EMG), electrocardiograms (ECGs), and motion or audio/video recording that focuses on the human head and body. EEG analysis provides a prominent solution to distinguish between the signals associated with epileptic episodes and normal signals; therefore, this work aims to leverage on the latest EEG dataset using cutting-edge deep learning algorithms such as random neural network (RNN), convolutional neural network (CNN), extremely random tree (ERT), and residual neural network (ResNet) to classify multiple variants of epileptic seizures from non-seizures. The results obtained highlighted that RNN outperformed all other algorithms used and provided an overall accuracy of 97%, which was slightly improved after cross validation.

An Overview of EEG-based Machine Learning Methods in Seizure Prediction and Opportunities for Neurologists in this Field

The unpredictability of epileptic seizures is one of the most problematic aspects of the field of epilepsy. Methods or devices capable of detecting seizures minutes before they occur may help prevent injury or even death and significantly improve the quality of life. Machine learning (ML) is an emerging technology that can markedly enhance algorithm performance by interpreting data. ML has gained increasing attention from medical researchers in recent years. Its epilepsy applications range from the localization of the epileptic region, predicting the medical or surgical outcome of epilepsy, and automated electroencephalography (EEG) analysis to seizure prediction. While ML has good prospects with regard to detecting epileptic seizures via EEG signals, many clinicians are still unfamiliar with this field. This work briefly summarizes the history and recent significant progress made in this field and clarifies the essential components of the automatic seizure detection system using ML methodologies for clinicians. This review also proposes how neurologists can actively contribute to ensure improvements in seizure prediction using EEG-based ML.

An Effective Dual Self-Attention Residual Network for Seizure Prediction

As one of the most challenging data analysis tasks in chronic brain diseases, epileptic seizure prediction has attracted extensive attention from many researchers. Seizure prediction, can greatly improve patients' quality of life in many ways, such as preventing accidents and reducing harm that may occur during epileptic seizures. This work aims to develop a general method for predicting seizures in specific patients through exploring the time-frequency correlation of features obtained from multi-channel EEG signals. We convert the original EEG signals into spectrograms that represent time-frequency characteristics by applying short-time Fourier transform (STFT) to the EEG signals. For the first time, we propose a dual self-attention residual network (RDANet) that combines a spectrum attention module integrating local features with global features, with a channel attention module mining the interdependence between channel mappings to achieve better forecasting performance. Our proposed approach achieved a sensitivity of 89.33%, a specificity of 93.02%, an AUC of 91.26% and an accuracy of 92.07% on 13 patients from the public CHB-MIT scalp EEG dataset. Our experiments show that different EEG signal prediction segment lengths are an important factor affecting prediction performance. Our proposed method is competitive and achieves good robustness without patient-specific engineering.

Focal lesions induce large-scale percolation of sleep-like intracerebral activity in awake humans

Focal cortical lesions are known to result in large-scale functional alterations involving distant areas; however, little is known about the electrophysiological mechanisms underlying these network effects. Here, we addressed this issue by analysing the short and long distance intracranial effects of controlled structural lesions in humans. The changes in Stereo-Electroencephalographic (SEEG) activity after Radiofrequency-Thermocoagulation (RFTC) recorded in 21 epileptic subjects were assessed with respect to baseline resting wakefulness and sleep activity. In addition, Cortico-Cortical Evoked Potentials (CCEPs) recorded before the lesion were employed to interpret these changes with respect to individual long-range connectivity patterns. We found that small structural ablations lead to the generation and large-scale propagation of sleep-like slow waves within the awake brain. These slow waves match those recorded in the same subjects during sleep, are prevalent in perilesional areas, but can percolate up to distances of 60 mm through specific long-range connections, as predicted by CCEPs. Given the known impact of slow waves on information processing and cortical plasticity, demonstrating their intrusion and percolation within the awake brain add key elements to our understanding of network dysfunction after cortical injuries.

Zero-crossing patterns reveal subtle epileptiform discharges in the scalp EEG

Clinical diagnosis of epilepsy depends heavily on the detection of interictal epileptiform discharges (IEDs) from scalp electroencephalographic (EEG) signals, which by purely visual means is far from straightforward. Here, we introduce a simple signal analysis procedure based on scalp EEG zero-crossing patterns which can extract the spatiotemporal structure of scalp voltage fluctuations. We analyzed simultaneous scalp and intracranial EEG recordings from patients with pharmacoresistant temporal lobe epilepsy. Our data show that a large proportion of intracranial IEDs manifest only as subtle, low-amplitude waveforms below scalp EEG background and could, therefore, not be detected visually. We found that scalp zero-crossing patterns allow detection of these intracranial IEDs on a single-trial level with millisecond temporal precision and including some mesial temporal discharges that do not propagate to the neocortex. Applied to an independent dataset, our method discriminated accurately between patients with epilepsy and normal subjects, confirming its practical applicability.

Canine detection of volatile organic compounds unique to human epileptic seizure

OBJECTIVE

Literature accounts of service dogs alerting patients prior to their seizures are a mix of historically poor quality data and confounding diagnoses. In a group of epilepsy patients, Canine Assistants and Florida International University characterized a unique scent combination of volatile organic compounds present during the immediate postictal period, but never at other times. The current study was designed to confirm prospectively if this unique scent, and potential biomarker, can: (1) be detected in an epilepsy monitoring unit (EMU), (2) whether this scent is present with nonepileptic seizures, and (3) whether this scent also precedes the clinical-electrographic seizure.

METHODS

Following consent and approval, sweat samples taken from EMU admissions at Denver Health Medical Center were sent to Canine Assistants in Georgia. Their team of service dogs, who had been imprinted to recognize the unique scent, were then asked to process these sweat samples in a simple yes/no identification paradigm.

RESULTS

Sixty unique subjects were enrolled over a two-year period. In the first part of this study, a total of 298 ictal sweat samples of 680 total observations were collected. The dogs had a 93.7% (OR: 14.89, 95% CI: 9.27, 23.90) probability of correctly distinguishing between ictal and interictal sweat samples. In the nonepileptic seizure population, 18 of the 19 NES events that were accompanied by sweat sample collections were not associated with identification of the unique seizure scent. In the second part of the study, in which subjects had samples collected every hour, dogs identified the unique seizure scent presence before 78.7% of all seizures captured, at a probability of 82.2% (OR: 4.60, 95% CI: 0.98, 21.69) of a positive detection predicting a seizure. The average duration of the warning phase of the scent was 68.2 min. The average duration of the tail phase of the scent faded after 81 min.

SIGNIFICANCE

This study confirms the unique seizure scent identified by Canine Assistants and FIU may be collected and recognized by dogs trained to do so, in a prospective manner. A significant number of seizures appear to be associated with the unique scent presence prior to clinical-electrical onset of the seizure itself, and therefore further study of this biomarker is warranted.

Altered Functional Connectivity after Epileptic Seizure Revealed by Scalp EEG

Epileptic seizures are considered to be a brain network dysfunction, and chronic recurrent seizures can cause severe brain damage. However, the functional brain network underlying recurrent epileptic seizures is still left unveiled. This study is aimed at exploring the differences in a related brain activity before and after chronic repetitive seizures by investigating the power spectral density (PSD), fuzzy entropy, and functional connectivity in epileptic patients. The PSD analysis revealed differences between the two states at local area, showing postseizure energy accumulation. Besides, the fuzzy entropies of preseizure in the frontal, central, and temporal regions are higher than that of postseizure. Additionally, attenuated long-range connectivity and enhanced local connectivity were also found. Moreover, significant correlations were found between network metrics (i.e., characteristic path length and clustering coefficient) and individual seizure number. The PSD, fuzzy entropy, and network analysis may indicate that the brain is gradually impaired along with the occurrence of epilepsy, and the accumulated effect of brain impairment is observed in individuals with consecutive epileptic bursts. The findings of this study may provide helpful insights into understanding the network mechanism underlying chronic recurrent epilepsy.

Roughness-Length-Based Characteristic Analysis of Intracranial EEG and Epileptic Seizure Prediction

To identify precursors of epileptic seizures, an EEG characteristic analysis is carried out based on a roughness-length method, where fractal dimensions and intercept values are extracted to measure the structure complexity and the amplitude roughness of EEG signals in different phases. Using the significant changes of the fractal dimension and intercept in the preictal phase with respect to those in the interictal phase, a patient-specific seizure prediction algorithm is then proposed by combining with a gradient boosting classifier. The probabilistic outputs of the trained gradient boosting classifier are further processed by threshold comparison and rule-based judgment to distinguish preictal EEG from interictal EEG and to generate seizure alerts. The prediction algorithm was evaluated on 20 patients’ intracranial EEG recordings from the Freiburg EEG database, which contains the preictal periods of 65 seizures and 499[Formula: see text]h interictal EEG. Setting the seizure prediction horizon as 2[Formula: see text]min, averaged sensitivity values of 90.42% and 91.67% with averaged false prediction rates of 0.12/h and 0.10/h were achieved for seizure occurrence periods of 30 and 50[Formula: see text]min, respectively. These results demonstrate the ability of fractal dimension and intercept metrics in predicting the occurrence of seizures.

Deep Convolutional Neural Network Based Interictal-Preictal Electroencephalography Prediction: Application to Focal Cortical Dysplasia Type-II

We aimed to differentiate between the interictal and preictal states in epilepsy patients with focal cortical dysplasia (FCD) type-II using deep learning-based classifiers based on intracranial electroencephalography (EEG). We also investigated the practical conditions for high interictal-preictal discriminability in terms of spatiotemporal EEG characteristics and data size efficiency. Intracranial EEG recordings of nine epilepsy patients with FCD type-II (four female, five male; mean age: 10.7 years) were analyzed. Seizure onset and channel ranking were annotated by two epileptologists. We performed three consecutive interictal-preictal classification steps by varying the preictal length, number of electrodes, and sampling frequency with convolutional neural networks (CNN) using 30 s time-frequency data matrices. Classification performances were evaluated based on accuracy, F1 score, precision, and recall with respect to the above-mentioned three parameters. We found that (1) a 5 min preictal length provided the best classification performance, showing a remarkable enhancement of >13% on average compared to that with the 120 min preictal length; (2) four electrodes provided considerably high classification performance with a decrease of only approximately 1% on average compared to that with all channels; and (3) there was minimal performance change when quadrupling the sampling frequency from 128 Hz. Patient-specific performance variations were noticeable with respect to the preictal length, and three patients showed above-average performance enhancements of >28%. However, performance enhancements were low with respect to both the number of electrodes and sampling frequencies, and some patients showed at most 1–2% performance change. CNN-based classifiers from intracranial EEG recordings using a small number of electrodes and efficient sampling frequency are feasible for predicting the interictal-preictal state transition preceding seizures in epilepsy patients with FCD type-II. Preictal lengths affect the predictability in a patient-specific manner; therefore, pre-examinations for optimal preictal length will be helpful in seizure prediction.

Performance analysis of EEG seizure detection features

Automatic detection of epileptic seizures can serve as a valuable clinical tool which involves a more objective and computationally efficient method for the analysis of EEG data in order to generate increasingly accurate and reliable results. Automatic seizure detection is also an important component of closed-loop responsive cortical stimulation systems. The goal of this study is to evaluate EEG-based features recently proposed for seizure detection to discover the optimum ones for a reliable seizure detection system. We extracted seizure detection features from intracranial EEG signals that were recorded during invasive pre-surgical epilepsy monitoring of people with drug resistant focal epilepsy at the Epilepsy Center of the University Hospital of Freiburg. Features from time, frequency and phase space domains as well as similarity/dissimilarity features were considered. The performance of each feature was investigated using the statistical test ANOVA. Performance analysis was conducted separately on the recordings from the channels within the seizure-onset zone (SOZ-in) and the recordings from the channels outside the seizure-onset zone (SOZ-out). Similarity/dissimilarity features that measure dynamic properties of the EEG signal and the evolving phenomena of the seizures could significantly separate ictal (during seizure) states from pre-ictal (before seizure) states (p < 0.01). Among them, our proposed feature, Bhattacharyya-based dissimilarity index (BBDI), successfully passed Tukey's post-hoc test as well suggesting that it can distinguish both pre-ictal and post-ictal (after seizure) periods from ictal period. BBDI was further applied to detect epileptic seizures and achieved area under the curve of the receiver-operator characteristic (ROC) equal to 0.96 and 0.94 for SOZ-in and SOZ-out channels, respectively. No significant difference (p = 0.59) was observed in the performance of features between SOZ-in recordings and SOZ-out recordings. The discriminative value of EEG seizure detection features was determined by statistical tests. As a result, the best features to be selected for a reliable seizure detection system designed for people with drug-resistant focal epilepsy were suggested, which include similarity/dissimilarity indices.

Innovations in the Neurosurgical Management of Epilepsy

Technical limitations and clinical challenges have historically limited the diagnostic tools and treatment methods available for surgical approaches to the management of epilepsy. By contrast, recent technological innovations in several areas hold significant promise in improving outcomes and decreasing morbidity. We review innovations in the neurosurgical management of epilepsy in several areas, including wireless recording and stimulation systems (particularly responsive neurostimulation [NeuroPace]), conformal electrodes for high-resolution electrocorticography, robot-assisted stereotactic surgery, optogenetics and optical imaging methods, novel positron emission tomography ligands, and new applications of focused ultrasonography. Investigation into genetic causes of and susceptibilities to epilepsy has introduced a new era of precision medicine, enabling the understanding of cell signaling mechanisms underlying epileptic activity as well as patient-specific molecularly targeted treatment options. We discuss the emerging path to individualized treatment plans, predicted outcomes, and improved selection of effective interventions, on the basis of these developments.

Transition of brain networks from an interictal to a preictal state preceding a seizure revealed by scalp EEG network analysis

Epilepsy is a neurological disorder in the brain that is characterized by unprovoked seizures. Epileptic seizures are attributed to abnormal synchronous neuronal activity in the brain. To detect the seizure as early as possible, the identification of specific electroencephalogram (EEG) dynamics is of great importance in investigating the transition of brain activity as the epileptic seizure approaches. In this study, we investigated the transition of brain activity from interictal to preictal states preceding a seizure by combining EEG network and clustering analyses together in different frequency bands. The findings of this study demonstrated the best clustering performance of k-medoids in the beta band; in addition, compared to the interictal state, the preictal state experienced increased synchronization of EEG network connectivity, characterized by relatively higher network properties. These findings can provide helpful insight into the mechanism of epilepsy, which can also be used in the prediction of epileptic seizures and subsequent intervention.

Improved Patient-Independent System for Detection of Electrical Onset of Seizures

PURPOSE

To design a non-patient-specific system to detect the electrical onset of seizures in patients with temporal lobe epilepsy.

METHODS

We used EEG data from 29 seizures of 18 temporal lobe epilepsy patients who underwent multiday video-scalp EEG monitoring as part of their presurgical evaluations. We segmented each data set into preictal and ictal phases, and identified spectral entropy, spectral energy, and signal energy as useful features for discriminating normal and seizure conditions. The performance of five different classifiers was analyzed using these features to design an automated detection system.

RESULTS

Among the five classifiers, decision tree, k-nearest neighbor, and support vector machine performed with sensitivity (specificity) of 79% (81%), 75% (85%), and 80% (86%), respectively. The other two, linear discriminant algorithm and Naive Bayes classifiers, performed with sensitivity (specificity) of 54% (94%), 47% (96%), respectively.

CONCLUSIONS

The support vector machine-based seizure detection system showed better detection capability in terms of sensitivity and specificity measures as compared to linear discriminant algorithm, Naive Bayes, decision tree, and k-nearest neighbor classifiers.

CONCLUSIONS

Our study shows that a generalized system to detect the electrical onset of seizures in temporal lobe epilepsy using scalp-recorded EEG is possible. If confirmed on a larger data set, our findings may have significant implications for the management of seizures, especially in patients with drug-resistant epilepsy.

Patient-specific seizure prediction based on heart rate variability and recurrence quantification analysis

Epilepsy is often associated with modifications in autonomic nervous system, which usually precede the onset of seizures of several minutes. Thus, there is a great interest in identifying these modifications enough time in advance to prevent a dangerous effect and to intervene. In addition, these changes can be a risk factor for epileptic patients and can increase the possibility of death. Notably autonomic changes associated to seizures are highly depended of seizure type, localization and lateralization. The aim of this study was to develop a patient-specific approach to predict seizures using electrocardiogram (ECG) features. Specifically, from the RR series, both time and frequency variables and features obtained by the recurrence quantification analysis were used. The algorithm was applied in a dataset of 15 patients with 38 different types of seizures. A feature selection step, was used to identify those features that were more significant in discriminating preictal and interictal phases. A preictal interval of 15 minutes was selected. A support vector machine (SVM) classifier was then built to classify preictal and interictal phases. First, a classifier was set up to classify preictal and interictal segments of each patient and an average sensibility of 89.06% was obtained, with a number of false positive per hour (FP/h) of 0.41. Then, in those patients who had at least 3 seizures, a double-cross-validation approach was used to predict unseen seizures on the basis of a training on previous ones. The results were quite variable according to seizure type, achieving the best performance in patients with more stereotypical seizure. The results of the proposed approach show that it is feasible to predict seizure in advance, considering patient-specific, and possible seizure specific, characteristics.

Sample entropy analysis for the estimating depth of anaesthesia through human EEG signal at different levels of unconsciousness during surgeries

Estimating the depth of anaesthesia (DoA) in operations has always been a challenging issue due to the underlying complexity of the brain mechanisms. Electroencephalogram (EEG) signals are undoubtedly the most widely used signals for measuring DoA. In this paper, a novel EEG-based index is proposed to evaluate DoA for 24 patients receiving general anaesthesia with different levels of unconsciousness. Sample Entropy (SampEn) algorithm was utilised in order to acquire the chaotic features of the signals. After calculating the SampEn from the EEG signals, Random Forest was utilised for developing learning regression models with Bispectral index (BIS) as the target. Correlation coefficient, mean absolute error, and area under the curve (AUC) were used to verify the perioperative performance of the proposed method. Validation comparisons with typical nonstationary signal analysis methods (i.e., recurrence analysis and permutation entropy) and regression methods (i.e., neural network and support vector machine) were conducted. To further verify the accuracy and validity of the proposed methodology, the data is divided into four unconsciousness-level groups on the basis of BIS levels. Subsequently, analysis of variance (ANOVA) was applied to the corresponding index (i.e., regression output). Results indicate that the correlation coefficient improved to 0.72 ± 0.09 after filtering and to 0.90 ± 0.05 after regression from the initial values of 0.51 ± 0.17. Similarly, the final mean absolute error dramatically declined to 5.22 ± 2.12. In addition, the ultimate AUC increased to 0.98 ± 0.02, and the ANOVA analysis indicates that each of the four groups of different anaesthetic levels demonstrated significant difference from the nearest levels. Furthermore, the Random Forest output was extensively linear in relation to BIS, thus with better DoA prediction accuracy. In conclusion, the proposed method provides a concrete basis for monitoring patients’ anaesthetic level during surgeries.

Prediction and detection of seizures from simultaneous thalamic and scalp electroencephalography recordings

OBJECTIVE The authors explored the feasibility of seizure detection and prediction using signals recorded from the anterior thalamic nucleus, a major target for deep brain stimulation (DBS) in the treatment of epilepsy. METHODS Using data from 5 patients (13 seizures in total), the authors performed a feasibility study and analyzed the performance of a seizure prediction and detection algorithm applied to simultaneously acquired scalp and thalamic electroencephalography (EEG). The thalamic signal was obtained from DBS electrodes. The applied algorithm used the similarity index as a nonlinear measure for seizure identification, with patient-specific channel and threshold selection. Receiver operating characteristic (ROC) curves were calculated using data from all patients and channels to compare the performance between DBS and EEG recordings. RESULTS Thalamic DBS recordings were associated with a mean prediction rate of 84%, detection rate of 97%, and false-alarm rate of 0.79/hr. In comparison, scalp EEG recordings were associated with a mean prediction rate of 71%, detection rate of 100%, and false-alarm rate of 1.01/hr. From the ROC curves, when considering all channels, DBS outperformed EEG for both detection and prediction of seizures. CONCLUSIONS This is the first study to compare automated seizure detection and prediction from simultaneous thalamic and scalp EEG recordings. The authors have demonstrated that signals recorded from DBS leads are more robust than EEG recordings and can be used to predict and detect seizures. These results indicate feasibility for future designs of closed-loop anterior nucleus DBS systems for the treatment of epilepsy.

Detection of Epileptic Seizures Using Phase-Amplitude Coupling in Intracranial Electroencephalography

Seizure detection using intracranial electroencephalography (iEEG) contributes to improved treatment of patients with refractory epilepsy. For that purpose, a feature of iEEG to characterize the ictal state with high specificity and sensitivity is necessary. We evaluated the use of phase–amplitude coupling (PAC) of iEEG signals over a period of 24 h to detect the ictal and interictal states. PAC was estimated by using a synchronisation index (SI) for iEEG signals from seven patients with refractory temporal lobe epilepsy. iEEG signals of the ictal state was characterised by a strong PAC between the phase of β and the amplitude of high γ. Furthermore, using SI values, the ictal state was successfully detected with significantly higher accuracy than by using the amplitude of high γ alone. In conclusion, PAC accurately distinguished the ictal state from the interictal state.

Seizure Prediction Using Undulated Global and Local Features

In this study, a seizure prediction method is proposed based on a patient-specific approach by extracting undulated global and local features of preictal/ictal and interictal periods of EEG signals. The proposed method consists of feature extraction, classification, and regularization. The undulated global feature is extracted using phase correlation between two consecutive epochs of EEG signals and an undulated local feature is extracted using the fluctuation and deviation of EEG signals within the epoch. These features are further used for classification of preictal/ictal and interictal EEG signals. A regularization technique is applied on the classified outputs for the reduction of false alarms and improvement of the overall prediction accuracy (PA). The experimental results confirm that the proposed method provides high PA (i.e., 95.4%) with low false positive per hour using intracranial EEG signals in different brain locations of 21 patients from a benchmark dataset. Combining global and local features enables the transition point to be determined between different types of signals with greater accuracy, resulting successful versus unsuccessful prediction of seizure. The theoretical contribution of this study may provide an opportunity for the development of a clinical device to predict forthcoming seizure in real time.

Automatic detection of rapid eye movements (REMs): A machine learning approach

BACKGROUND

Rapid eye movements (REMs) are a defining feature of REM sleep. The number of discrete REMs over time, or REM density, has been investigated as a marker of clinical psychopathology and memory consolidation. However, human detection of REMs is a time-consuming and subjective process. Therefore, reliable, automated REM detection software is a valuable research tool.

NEW METHOD

We developed an automatic REM detection algorithm combining a novel set of extracted features and the 'AdaBoost' classification algorithm to detect the presence of REMs in Electrooculogram data collected from the right and left outer canthi (ROC/LOC). Algorithm performance measures of Recall (percentage of REMs detected) and Precision (percentage of REMs detected that are true REMs) were calculated and compared to the gold standard of human detection by three expert sleep scorers. REM detection by four non-experts were also investigated and compared to expert raters and the algorithm.

RESULTS

The algorithm performance (78.1% Recall, 82.6% Precision) surpassed that of the average (expert & non-expert) single human detection performance (76% Recall, 83% Precision). Agreement between non-experts (Cronbach Alpha=0.65) is markedly lower than experts (Cronbach Alpha=0.80).

COMPARISON WITH EXISTING METHOD(S)

By following reported methods, we implemented all previously published LOC and ROC based detection algorithms on our dataset. Our algorithm performance exceeded all others.

CONCLUSIONS

The automatic detection algorithm presented is a viable and efficient method of REM detection as it reliably matches the performance of human scorers and outperforms all other known LOC- and ROC-based detection algorithms.

Epileptic Pattern Recognition and Discovery of the Local Field Potential in Amygdala Kindling Process

Epileptogenesis, which occurs in an epileptic brain, is an important focus for epilepsy. The spectral analysis has been popularly applied to study the electrophysiological activities. However, the resolution is dominated by the window function of the algorithm used and the sample size. In this report, a temporal waveform analysis method is proposed to investigate the relationship of electrophysiological discharges and motor outcomes with a kindling process. Wistar rats were subjected to electrical amygdala kindling to induce temporal lobe epilepsy. During the kindling process, different morphologies of afterdischarges (ADs) were found and a recognition method, using template matching techniques combined with morphological comparators, was developed to automatically detect the epileptic patterns. The recognition results were compared to manually labeled results, and 79%-91% sensitivity was found. In addition, the initial ADs (the first 10 s) of different seizure stages were specifically utilized for recognition, and an average of 85% sensitivity was achieved. Our study provides an alternative viewpoint away from frequency analysis and time-frequency analysis to investigate epileptogenesis in an epileptic brain. The recognition method can be utilized as a preliminary inspection tool to identify remarkable changes in a patient's electrophysiological activities for clinical use. Moreover, we demonstrate the feasibility of predicting behavioral seizure stages from the early epileptiform discharges.

Interval analysis of interictal EEG: pathology of the alpha rhythm in focal epilepsy

The contemporary use of interictal scalp electroencephalography (EEG) in the context of focal epilepsy workup relies on the visual identification of interictal epileptiform discharges. The high-specificity performance of this marker comes, however, at a cost of only moderate sensitivity. Zero-crossing interval analysis is an alternative to Fourier analysis for the assessment of the rhythmic component of EEG signals. We applied this method to standard EEG recordings of 78 patients divided into 4 subgroups: temporal lobe epilepsy (TLE), frontal lobe epilepsy (FLE), psychogenic nonepileptic seizures (PNES) and nonepileptic patients with headache. Interval-analysis based markers were capable of effectively discriminating patients with epilepsy from those in control subgroups (AUC~0.8) with diagnostic sensitivity potentially exceeding that of visual analysis. The identified putative epilepsy-specific markers were sensitive to the properties of the alpha rhythm and displayed weak or non-significant dependences on the number of antiepileptic drugs (AEDs) taken by the patients. Significant AED-related effects were concentrated in the theta interval range and an associated marker allowed for identification of patients on AED polytherapy (AUC~0.9). Interval analysis may thus, in perspective, increase the diagnostic yield of interictal scalp EEG. Our findings point to the possible existence of alpha rhythm abnormalities in patients with epilepsy.

Online Epileptic Seizure Prediction Using Wavelet-Based Bi-Phase Correlation of Electrical Signals Tomography

Considerable efforts have been made in order to predict seizures. Among these methods, the ones that quantify synchronization between brain areas, are the most important methods. However, to date, a practically acceptable result has not been reported. In this paper, we use a synchronization measurement method that is derived according to the ability of bi-spectrum in determining the nonlinear properties of a system. In this method, first, temporal variation of the bi-spectrum of different channels of electro cardiography (ECoG) signals are obtained via an extended wavelet-based time-frequency analysis method; then, to compare different channels, the bi-phase correlation measure is introduced. Since, in this way, the temporal variation of the amount of nonlinear coupling between brain regions, which have not been considered yet, are taken into account, results are more reliable than the conventional phase-synchronization measures. It is shown that, for 21 patients of FSPEEG database, bi-phase correlation can discriminate the pre-ictal and ictal states, with very low false positive rates (FPRs) (average: 0.078/h) and high sensitivity (100%). However, the proposed seizure predictor still cannot significantly overcome the random predictor for all patients.

On the proper selection of preictal period for seizure prediction

Supervised machine learning-based seizure prediction methods consider preictal period as an important prerequisite parameter during training. However, the exact length of the preictal state is unclear and varies from seizure to seizure. We propose a novel statistical approach for proper selection of the preictal period, which can also be considered either as a measure of predictability of a seizure or as the prediction capability of an understudy feature. The optimal preictal periods (OPPs) obtained from the training samples can be used for building a more accurate classifier model. The proposed method uses amplitude distribution histograms of features extracted from electroencephalogram (EEG) recordings. To evaluate this method, we extract spectral power features in different frequency bands from monopolar and space-differential EEG signals of 18 patients suffering from pharmacoresistant epilepsy. Furthermore, comparisons among monopolar channels with space-differential channels, as well as intracranial EEG (iEEG) and surface EEG (sEEG) signals, indicate that while monopolar signals perform better in iEEG recordings, no significant difference is noticeable in sEEG recordings.

A low computation cost method for seizure prediction

The dynamic changes of electroencephalograph (EEG) signals in the period prior to epileptic seizures play a major role in the seizure prediction. This paper proposes a low computation seizure prediction algorithm that combines a fractal dimension with a machine learning algorithm. The presented seizure prediction algorithm extracts the Higuchi fractal dimension (HFD) of EEG signals as features to classify the patient's preictal or interictal state with Bayesian linear discriminant analysis (BLDA) as a classifier. The outputs of BLDA are smoothed by a Kalman filter for reducing possible sporadic and isolated false alarms and then the final prediction results are produced using a thresholding procedure. The algorithm was evaluated on the intracranial EEG recordings of 21 patients in the Freiburg EEG database. For seizure occurrence period of 30 min and 50 min, our algorithm obtained an average sensitivity of 86.95% and 89.33%, an average false prediction rate of 0.20/h, and an average prediction time of 24.47 min and 39.39 min, respectively. The results confirm that the changes of HFD can serve as a precursor of ictal activities and be used for distinguishing between interictal and preictal epochs. Both HFD and BLDA classifier have a low computational complexity. All of these make the proposed algorithm suitable for real-time seizure prediction.

Deep brain stimulation in the treatment of neurological and psychiatric disease

Deep brain stimulation has become a topic of intense interest both from a clinical and basic science perspective. Its indications, currently including Parkinson's disease, tremor and dystonia, may expand in the future to include not only other movement disorders but also epilepsy, obsessive-compulsive disorder and other neuropsychiatric conditions. The mechanism(s) of action of deep brain stimulation have only recently begun to be characterized and have already yielded surprises that may open the door to a greater expansion of the indications for this novel and powerful therapeutic intervention.

Widespread EEG changes precede focal seizures

The process by which the brain transitions into an epileptic seizure is unknown. In this study, we investigated whether the transition to seizure is associated with changes in brain dynamics detectable in the wideband EEG, and whether differences exist across underlying pathologies. Depth electrode ictal EEG recordings from 40 consecutive patients with pharmacoresistant lesional focal epilepsy were low-pass filtered at 500 Hz and sampled at 2,000 Hz. Predefined EEG sections were selected immediately before (immediate preictal), and 30 seconds before the earliest EEG sign suggestive of seizure activity (baseline). Spectral analysis, visual inspection and discrete wavelet transform were used to detect standard (delta, theta, alpha, beta and gamma) and high-frequency bands (ripples and fast ripples). At the group level, each EEG frequency band activity increased significantly from baseline to the immediate preictal section, mostly in a progressive manner and independently of any modification in the state of vigilance. Preictal increases in each frequency band activity were widespread, being observed in the seizure-onset zone and lesional tissue, as well as in remote regions. These changes occurred in all the investigated pathologies (mesial temporal atrophy/sclerosis, local/regional cortical atrophy, and malformations of cortical development), but were more pronounced in mesial temporal atrophy/sclerosis. Our findings indicate that a brain state change with distinctive features, in the form of unidirectional changes across the entire EEG bandwidth, occurs immediately prior to seizure onset. We postulate that these changes might reflect a facilitating state of the brain which enables a susceptible region to generate seizures.

Fast monitoring of epileptic seizures using recurrence time statistics of electroencephalography

Epilepsy is a relatively common brain disorder which may be very debilitating. Currently, determination of epileptic seizures often involves tedious, time-consuming visual inspection of electroencephalography (EEG) data by medical experts. To better monitor seizures and make medications more effective, we propose a recurrence time based approach to characterize brain electrical activity. Recurrence times have a number of distinguished properties that make it very effective for forewarning epileptic seizures as well as studying propagation of seizures: (1) recurrence times amount to periods of periodic signals, (2) recurrence times are closely related to information dimension, Lyapunov exponent, and Kolmogorov entropy of chaotic signals, (3) recurrence times embody Shannon and Renyi entropies of random fields, and (4) recurrence times can readily detect bifurcation-like transitions in dynamical systems. In particular, property (4) dictates that unlike many other non-linear methods, recurrence time method does not require the EEG data be chaotic and/or stationary. Moreover, the method only contains a few parameters that are largely signal-independent, and hence, is very easy to use. The method is also very fast—it is fast enough to on-line process multi-channel EEG data with a typical PC. Therefore, it has the potential to be an excellent candidate for real-time monitoring of epileptic seizures in a clinical setting.

Increase trend of correlation and phase synchrony of microwire iEEG before macroseizure onset

Micro/macrowire intracranial EEG (iEEG) signals recorded from implanted micro/macroelectrodes in epileptic patients have received great attention and are considered to include much information of neuron activities in seizure transition compared to scalp EEG from cortical electrodes. Microelectrode is contacted more close to neurons than macroelectrode and it is more sensitive to neuron activity changes than macroelectrode. Microwire iEEG recordings are inevitably advantageous over macrowire iEEG recordings to reveal neuronal mechanisms contributing to the generation of seizures. In this study, we investigate the seizure generation from microwire iEEG recordings and discuss synchronization of microwire iEEGs in four frequency bands: alpha (1-30 Hz), gamma (30-80 Hz), ripple (80-250 Hz), and fast ripple (>250 Hz) via two measures: correlation and phase synchrony. We find that an increase trend of correlation or phase synchrony exists before the macroseizure onset mostly in gamma and ripple bands where the duration of the preictal states varied in different seizures ranging up to a few seconds (minutes). This finding is contrast to the well-known result that a decrease of synchronization in macro domains exists before the macroseizure onset. The finding demonstrates that it is only when the seizure has recruited enough surrounding brain tissue does the signal become strong enough to be observed on the clinical macroelectrode and as a result support the hypothesis of progressive coalescence of microseizure domains. The potential ramifications of such an early detection of microscale seizure activity may open a new window on treatment by making possible disruption of seizure activity before it becomes fully established.