Automatic EEG spike detection

Quantitative Electroencephalography Objectivity and Reliability in the Diagnosis and Management of Traumatic Brain Injury: A Systematic Review

Background. Persons with a history of traumatic brain injury (TBI) may exhibit short- and long-term cognitive deficits as well as psychiatric symptoms. These symptoms often reflect functional anomalies in the brain that are not detected by standard neuroimaging. In this context, quantitative electroencephalography (qEEG) is more suitable to evaluate non-normative activity in a wide range of clinical settings. Method. We searched the literature using the "Medline" and "Web of Science" online databases. The search was concluded on February 23, 2023, and revised on July 12, 2023. It returned 134 results from Medline and 4 from Web of Science. We then applied the PRISMA method, which led to the selection of 31 articles, the most recent one published in March 2023. Results. The qEEG method can detect functional anomalies in the brain occurring immediately after and even years after injury, revealing in most cases abnormal power variability and increases in slow (delta and theta) versus decreases in fast (alpha, beta, and gamma) frequency activity. Moreover, other findings show that reduced beta coherence between frontoparietal regions is associated with slower processing speed in patients with recent mild TBI (mTBI). More recently, machine learning (ML) research has developed highly reliable models and algorithms for the detection of TBI, some of which are already integrated into commercial qEEG equipment. Conclusion. Accumulating evidence indicates that the qEEG method may improve the diagnosis and management of TBI, in many cases revealing long-term functional anomalies in the brain or even neuroanatomical insults that are not revealed by standard neuroimaging. While FDA clearance has been obtained only for some of the commercially available equipment, the qEEG method allows for systematic, cost-effective, non-invasive, and reliable investigations at emergency departments. Importantly, the automated implementation of intelligent algorithms based on multimodally acquired, clinically relevant measures may play a key role in increasing diagnosis reliability.

[Automatic detection of epileptiform potentials and seizures in the EEG]

Automatic computer-based algorithms for the detection of epileptiform potentials and seizure patterns on EEG facilitate a time-saving, objective method of quantitative EEG interpretation which is available 7/24. For the automatic detection of interictal epileptiform potentials sensitivities range from 65 to 99% with false positive detections of 0,09 to 13,4 per minute. Recent studies documented equal or even better performance of automatic spike detection programs compared with experienced human EEG readers. The seizure detection problem-one of the major problems in clinical epileptology-consists of the fact that the majority of focal onset seizures with impaired awareness and of seizures arising out of sleep occur unnoticed by patients and their caregivers. Automatic seizure detection systems could facilitate objective seizure documentation and thus help to solve the seizure detection problem. Furthermore, seizure detection systems may help to prevent seizure-related injuries and sudden unexpected death in epilepsy (SUDEP), and could be an integral part of novel, seizure-triggered on-demand therapies in epilepsy. During long-term video-EEG monitoring seizure detection systems could improve patient safety, provide a time-saving objective and reproducible analysis of seizure patterns and facilitate automatic computer-based patient testing during seizures. Sensitivities of seizure detection systems range from 75 to 90% with extratemporal seizures being more difficult to detect than temporal seizures. The false positive alarm rate ranges from 0,1 to 5 per 24 hours. Finally, machine learning algorithms, especially deep learning approaches, open a new highly promising era in automatic spike and seizure detection.

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.

Time- and frequency-resolved covariance analysis for detection and characterization of seizures from intracraneal EEG recordings

The amount of power in different frequency bands of the electroencephalogram (EEG) carries information about the behavioral state of a subject. Hence, neurologists treating epileptic patients monitor the temporal evolution of the different bands. We propose a covariance-based method to detect and characterize epileptic seizures operating on the band-filtered EEG signal. The algorithm is unsupervised and performs a principal component analysis of intra-cranial EEG recordings, detecting transient fluctuations of the power in each frequency band. Its simplicity makes it suitable for online implementation. Good sampling of the non-ictal periods is required, while no demands are imposed on the amount of data during ictal activity. We tested the method with 32 seizures registered in 5 patients. The area below the resulting receiver-operating characteristic curves was 87% for the detection of seizures and 91% for the detection of recruited electrodes. To identify the behaviorally relevant correlates of the physiological signal, we identified transient changes in the variance of each band that were correlated with the degree of loss of consciousness, the latter assessed by the so-called Consciousness Seizure Scale, summarizing the performance of the subject in a number of behavioral tests requested during seizures. We concluded that those crisis with maximal impairment of consciousness tended to exhibit an increase in variance approximately 40 s after seizure onset, with predominant power in the theta and alpha bands and reduced delta and beta activity.

Automatische Erkennung von epilepsietypischen Potenzialen und Anfällen im EEG

Die Elektroenzephalografie (EEG) ist der wichtigste apparative Eckpfeiler in der Diagnostik und Therapieführung bei Epilepsien. Die visuelle EEG-Befundung stellt dabei nach wie vor den Goldstandard dar. Automatische computerunterstützte Methoden zur Detektion und Quantifizierung von interiktalen epilepsietypischen Potenzialen und Anfällen unterstützen eine zeitsparende, objektive, rasch und jederzeit verfügbare quantitative EEG-Befundung.

The impact of signal normalization on seizure detection using line length features

Accurate automated seizure detection remains a desirable but elusive target for many neural monitoring systems. While much attention has been given to the different feature extractions that can be used to highlight seizure activity in the EEG, very little formal attention has been given to the normalization that these features are routinely paired with. This normalization is essential in patient-independent algorithms to correct for broad-level differences in the EEG amplitude between people, and in patient-dependent algorithms to correct for amplitude variations over time. It is crucial, however, that the normalization used does not have a detrimental effect on the seizure detection process. This paper presents the first formal investigation into the impact of signal normalization techniques on seizure discrimination performance when using the line length feature to emphasize seizure activity. Comparing five normalization methods, based upon the mean, median, standard deviation, signal peak and signal range, we demonstrate differences in seizure detection accuracy (assessed as the area under a sensitivity-specificity ROC curve) of up to 52 %. This is despite the same analysis feature being used in all cases. Further, changes in performance of up to 22 % are present depending on whether the normalization is applied to the raw EEG itself or directly to the line length feature. Our results highlight the median decaying memory as the best current approach for providing normalization when using line length features, and they quantify the under-appreciated challenge of providing signal normalization that does not impair seizure detection algorithm performance.

Traumatic brain injury detection using electrophysiological methods

Measuring neuronal activity with electrophysiological methods may be useful in detecting neurological dysfunctions, such as mild traumatic brain injury (mTBI). This approach may be particularly valuable for rapid detection in at-risk populations including military service members and athletes. Electrophysiological methods, such as quantitative electroencephalography (qEEG) and recording event-related potentials (ERPs) may be promising; however, the field is nascent and significant controversy exists on the efficacy and accuracy of the approaches as diagnostic tools. For example, the specific measures derived from an electroencephalogram (EEG) that are most suitable as markers of dysfunction have not been clearly established. A study was conducted to summarize and evaluate the statistical rigor of evidence on the overall utility of qEEG as an mTBI detection tool. The analysis evaluated qEEG measures/parameters that may be most suitable as fieldable diagnostic tools, identified other types of EEG measures and analysis methods of promise, recommended specific measures and analysis methods for further development as mTBI detection tools, identified research gaps in the field, and recommended future research and development thrust areas. The qEEG study group formed the following conclusions: (1) Individual qEEG measures provide limited diagnostic utility for mTBI. However, many measures can be important features of qEEG discriminant functions, which do show significant promise as mTBI detection tools. (2) ERPs offer utility in mTBI detection. In fact, evidence indicates that ERPs can identify abnormalities in cases where EEGs alone are non-disclosing. (3) The standard mathematical procedures used in the characterization of mTBI EEGs should be expanded to incorporate newer methods of analysis including non-linear dynamical analysis, complexity measures, analysis of causal interactions, graph theory, and information dynamics. (4) Reports of high specificity in qEEG evaluations of TBI must be interpreted with care. High specificities have been reported in carefully constructed clinical studies in which healthy controls were compared against a carefully selected TBI population. The published literature indicates, however, that similar abnormalities in qEEG measures are observed in other neuropsychiatric disorders. While it may be possible to distinguish a clinical patient from a healthy control participant with this technology, these measures are unlikely to discriminate between, for example, major depressive disorder, bipolar disorder, or TBI. The specificities observed in these clinical studies may well be lost in real world clinical practice. (5) The absence of specificity does not preclude clinical utility. The possibility of use as a longitudinal measure of treatment response remains. However, efficacy as a longitudinal clinical measure does require acceptable test-retest reliability. To date, very few test-retest reliability studies have been published with qEEG data obtained from TBI patients or from healthy controls. This is a particular concern because high variability is a known characteristic of the injured central nervous system.

Visual systems for interactive exploration and mining of large-scale neuroimaging data archives

While technological advancements in neuroimaging scanner engineering have improved the efficiency of data acquisition, electronic data capture methods will likewise significantly expedite the populating of large-scale neuroimaging databases. As they do and these archives grow in size, a particular challenge lies in examining and interacting with the information that these resources contain through the development of compelling, user-driven approaches for data exploration and mining. In this article, we introduce the informatics visualization for neuroimaging (INVIZIAN) framework for the graphical rendering of, and dynamic interaction with the contents of large-scale neuroimaging data sets. We describe the rationale behind INVIZIAN, detail its development, and demonstrate its usage in examining a collection of over 900 T1-anatomical magnetic resonance imaging (MRI) image volumes from across a diverse set of clinical neuroimaging studies drawn from a leading neuroimaging database. Using a collection of cortical surface metrics and means for examining brain similarity, INVIZIAN graphically displays brain surfaces as points in a coordinate space and enables classification of clusters of neuroanatomically similar MRI images and data mining. As an initial step toward addressing the need for such user-friendly tools, INVIZIAN provides a highly unique means to interact with large quantities of electronic brain imaging archives in ways suitable for hypothesis generation and data mining.

Utilising noise to improve an interictal spike detector

Dithering is the process of intentionally adding artificially generated noise to an otherwise uncorrupted signal to actually improve the performance of an end overall system. This article demonstrates that a dithering procedure can be used to improve the performance of an EEG interictal spike detection algorithm. Using a previously reported algorithm, by adding varying amounts of artificially generated noise to the input EEG signals the effect on the algorithm detection performance is investigated. A new stochastic resonance result is found whereby the spike detection performance improves by up to 4.3% when small amounts of corrupting noise, below 20μV(RMS), are added to the input data. This result is of use for improving the detection performance of algorithms, and the result also affects the dynamic range required for the hardware implementation of such algorithms in low power, portable EEG systems.

Discriminating between ADHD adults and controls using independent ERP components and a support vector machine: a validation study

BACKGROUND

There are numerous event-related potential (ERP) studies in relation to attention-deficit hyperactivity disorder (ADHD), and a substantial number of ERP correlates of the disorder have been identified. However, most of the studies are limited to group differences in children. Independent component analysis (ICA) separates a set of mixed event-related potentials into a corresponding set of statistically independent source signals, which are likely to represent different functional processes. Using a support vector machine (SVM), a classification method originating from machine learning, this study aimed at investigating the use of such independent ERP components in differentiating adult ADHD patients from non-clinical controls by selecting a most informative feature set. A second aim was to validate the predictive power of the SVM classifier by means of an independent ADHD sample recruited at a different laboratory.

METHODS

Two groups of age-matched adults (75 ADHD, 75 controls) performed a visual two stimulus go/no-go task. ERP responses were decomposed into independent components, and a selected set of independent ERP component features was used for SVM classification.

RESULTS

Using a 10-fold cross-validation approach, classification accuracy was 91%. Predictive power of the SVM classifier was verified on the basis of the independent ADHD sample (17 ADHD patients), resulting in a classification accuracy of 94%. The latency and amplitude measures which in combination differentiated best between ADHD patients and non-clinical subjects primarily originated from independent components associated with inhibitory and other executive operations.

CONCLUSIONS

This study shows that ERPs can substantially contribute to the diagnosis of ADHD when combined with up-to-date methods.

Classification of ADHD patients on the basis of independent ERP components using a machine learning system

BACKGROUND

In the context of sensory and cognitive-processing deficits in ADHD patients, there is considerable evidence of altered event related potentials (ERP). Most of the studies, however, were done on ADHD children. Using the independent component analysis (ICA) method, ERPs can be decomposed into functionally different components. Using the classification method of support vector machine, this study investigated whether features of independent ERP components can be used for discrimination of ADHD adults from healthy subjects.

METHODS

Two groups of age- and sex-matched adults (74 ADHD, 74 controls) performed a visual two stimulus GO/NOGO task. ERP responses were decomposed into independent components by means of ICA. A feature selection algorithm defined a set of independent component features which was entered into a support vector machine.

RESULTS

The feature set consisted of five latency measures in specific time windows, which were collected from four different independent components. The independent components involved were a novelty component, a sensory related and two executive function related components. Using a 10-fold cross-validation approach, classification accuracy was 92%.

CONCLUSIONS

This study was a first attempt to classify ADHD adults by means of support vector machine which indicates that classification by means of non-linear methods is feasible in the context of clinical groups. Further, independent ERP components have been shown to provide features that can be used for characterizing clinical populations.