Patterns Specific to Pediatric EEG

Detection and Severity Identification of Neonatal Seizure Using Deep Convolutional Neural Networks from Multichannel EEG Signal

Introduction

One of the most frequent neurological conditions in newborns is neonatal seizures, which may indicate severe neurological dysfunction. These seizures may have very subtle or very modest clinical indications because patterns like oscillatory (spike) trains begin with relatively low amplitude and gradually increase over time. This becomes very challenging and erroneous if clinical observation is the primary basis for identifying newborn seizures. In this study, a diagnosis system using deep convolutional neural networks is proposed to determine and classify the severity level of neonatal seizures using multichannel neonatal EEG data.

Methods

Datasets from publicly accessible online sources were used to compile clinical multichannel EEG datasets. Various preprocessing steps were taken, including the conversion of 2D time series data to equivalent waveform pictures. The proposed models have undergone training, and evaluations of their performance were conducted.

Results

The proposed CNN was used to perform binary classification with an accuracy of 92.6%, F1-score of 92.7%, specificity of 92.8%, and precision of 92.6%. To detect newborn seizures, this model is utilized. Using the proposed CNN model, multiclassification was performed with accuracy rates of 88.6%, specificity rates of 92.18%, F1-score rates of 85.61%, and precision rates of 88.9%. The results demonstrated that the suggested strategy can assist medical professionals in making accurate diagnoses close to healthcare institutions.

Conclusion

The developed system was capable of detecting neonatal seizures and has the potential to be used as a decision-making tool in resource-limited areas with a scarcity of expert neurologists.

Non-epileptic paroxysmal events at pediatric video-electroencephalography monitoring unit over a 15-year period

OBJECTIVE

Non-epileptic paroxysmal events (NEPEs) are common in pediatric patients and may be misdiagnosed as epileptic seizures. We aimed to study the distribution of NEPEs across age groups and with different comorbidities, and to correlate the patients' presenting symptoms with their final diagnosis after video-EEG.

METHODS

We retrospectively analyzed video-EEG recordings of children aged one month to 18 years who were admitted between March 2005 and March 2020. Patients who experienced any NEPE while under video-EEG monitorization were evaluated in this study. Subjects with concomitant epilepsy were also included. The patients were first divided into 14 groups according to the basic characteristics of symptoms they reported at admission. The events captured on video-EEG were then classified into six NEPE categories based on the nature of the events. These groups were compared according to video-EEG results.

RESULTS

We retrospectively evaluated 1338 records of 1173 patients. The final diagnosis was non-epileptic paroxysmal event in 226 (19.3%) of 1173 patients. The mean age of the patients was 105.4 ± 64.4 months at the time of the monitoring. The presenting symptoms were motor in 149/226 (65.9%) patients, with jerking being the most common (n = 40, 17.7%). Based on video-EEG, the most common NEPE was psychogenic non-epileptic seizures (PNES) (n = 66, 29.2%), and the most common PNES subtype was major motor movements (n = 19/66, 28.8%). Movement disorders (n = 46, 20.4%) were the second most common NEPE and the most common NEPE (n = 21/60, 35%) in children with developmental delay (n = 60). Other common NEPEs were physiological motor movements during sleep (n = 33, 14.6%), normal behavioral events (n = 31, 13.7%), and sleep disorders (n = 15, 6.6%). Almost half of the patients had a prior diagnosis of epilepsy (n = 105, 46.5%). Following the diagnosis of NEPE, antiseizure medication (ASM) was discontinued in 56 (24.8%) patients.

CONCLUSION

Non-epileptiform paroxysmal events can be difficult to distinguish from epileptic seizures in children, especially in patients with developmental delay, epilepsy, abnormal interictal EEG, or abnormal MRI findings. Correct diagnosis of NEPEs by video-EEG prevents unnecessary ASM exposure in children and guides appropriate management of NEPEs.

Electroencephalography findings in childhood epilepsy in a Saudi population: Yield, pattern and determinants of abnormality

OBJECTIVE

The study was designed to evaluate the yield, pattern, and factors that are independently associated with electroencephalography (EEG) abnormalities in childhood epilepsy in a Saudi population.

METHODS

We characterised the features of the first EEG and evaluated the associated factors in children with epilepsy in a Saudi population. The features of interictal epileptiform discharges (interictal epileptiform activity (IEA)) adopted by the International Federation of Societies for Electroencephalography and Clinical Neurophysiology were used in the study.

RESULT

A total of 756 paediatric patients, comprised of 427 men (56.5%) and 329 women (43.5%) with a clinical diagnosis of epilepsy, underwent EEG. Clinically, seizure was generalised in 619 (81.9%) patients and focal in 137 (18.1%). Among the patients, 397 (52.51%) had an abnormal EEG, while EEG was normal in 359 (47.49%) patients. Seizure frequency, gender, family history of epilepsy, and age were independent predictors of the presence of EEG abnormalities.

CONCLUSION

This study revealed a yield of 52% abnormal EEG findings in children with epilepsy. Age, gender, family history, and seizure frequency were independent predictors of the presence of EEG abnormalities in childhood epilepsy.

Integrating old and new complexity measures toward automated seizure detection from long-term video EEG recordings

Automated seizure detection in long-term video-EEG recordings is far from being integrated into common clinical practice. Here, we leverage classical and state-of-the-art complexity measures to robustly and automatically detect seizures from scalp recordings. Brain activity is scored through eight features, encompassing traditional time domain and novel measures of recurrence. A binary classification algorithm tailored to treat unbalanced dataset is used to determine whether a time window is ictal or non-ictal from its features. The application of the algorithm on a cohort of ten adult patients with focal refractory epilepsy indicates sensitivity, specificity, and accuracy of 90%, along with a true alarm rate of 95% and less than four false alarms per day. The proposed approach emphasizes ictal patterns against noisy background without the need of data preprocessing. Finally, we benchmark our approach against previous studies on two publicly available datasets, demonstrating the good performance of our algorithm.

•

Complexity measures are formulated to enhance classical time-domain statistics of EEG

•

The detection algorithm does not need ad-hoc data preprocessing to address artifacts

•

Focal seizures are detected 95% of the time with less than four false alarms per day

•

The approach offers a visual representation of a seizure as a time-evolving network

Automated diagnosis of encephalitis in pediatric patients using EEG rhythms and slow biphasic complexes

Slow biphasic complexes (SBC) have been identified in the EEG of patients suffering for inflammatory brain diseases. Their amplitude, location and frequency of appearance were found to correlate with the severity of encephalitis. Other characteristics of SBCs and of EEG traces of patients could reflect the grade of pathology. Here, EEG rhythms are investigated together with SBCs for a better characterization of encephalitis. EEGs have been acquired from pediatric patients: ten controls and ten encephalitic patients. They were split by neurologists into five classes of different severity of the pathology. The relative power of EEG rhythms was found to change significantly in EEGs labeled with different severity scores. Moreover, a significant variation was found in the last seconds before the appearance of an SBC. This information and quantitative indexes characterizing the SBCs were used to build a binary classification decision tree able to identify the classes of severity. True classification rate of the best model was 76.1% (73.5% with leave-one-out test). Moreover, the classification errors were among classes with similar severity scores (precision higher than 80% was achieved considering three instead of five classes). Our classification method may be a promising supporting tool for clinicians to diagnose, assess and make the follow-up of patients with encephalitis.