A review of signal processing and machine learning techniques for interictal epileptiform discharge detection

Brain interictal epileptiform discharges (IEDs), as one of the hallmarks of epileptic brain, are transient events captured by electroencephalogram (EEG). IEDs are generated by seizure networks, and they occur between seizures (interictal periods). The development of a robust method for IED detection could be highly informative for clinical treatment procedures and epileptic patient management. Since 1972, different machine learning techniques, from template matching to deep learning, have been developed to automatically detect IEDs from scalp EEG (scEEG) and intracranial EEG (iEEG). While the scEEG signals suffer from low information details and high attenuation of IEDs due to the high skull electrical impedance, the iEEG signals recorded using implanted electrodes enjoy higher details and are more suitable for identifying the IEDs. In this review paper, we group IED detection techniques into six categories: (1) template matching, (2) feature representation (mimetic, time-frequency, and nonlinear features), (3) matrix decomposition, (4) tensor factorization, (5) neural networks, and (6) estimation of the iEEG from the concurrent scEEG followed by detection and classification. The methods are compared quantitatively (e.g., in terms of accuracy, sensitivity, and specificity), and their general advantages and limitations are described. Finally, current limitations and possible future research paths related to this field are mentioned.

Magnetoencephalography-based approaches to epilepsy classification

Epilepsy is a chronic central nervous system disorder characterized by recurrent seizures. Not only does epilepsy severely affect the daily life of the patient, but the risk of premature death in patients with epilepsy is three times higher than that of the normal population. Magnetoencephalography (MEG) is a non-invasive, high temporal and spatial resolution electrophysiological data that provides a valid basis for epilepsy diagnosis, and used in clinical practice to locate epileptic foci in patients with epilepsy. It has been shown that MEG helps to identify MRI-negative epilepsy, contributes to clinical decision-making in recurrent seizures after previous epilepsy surgery, that interictal MEG can provide additional localization information than scalp EEG, and complete excision of the stimulation area defined by the MEG has prognostic significance for postoperative seizure control. However, due to the complexity of the MEG signal, it is often difficult to identify subtle but critical changes in MEG through visual inspection, opening up an important area of research for biomedical engineers to investigate and implement intelligent algorithms for epilepsy recognition. At the same time, the use of manual markers requires significant time and labor costs, necessitating the development and use of computer-aided diagnosis (CAD) systems that use classifiers to automatically identify abnormal activity. In this review, we discuss in detail the results of applying various different feature extraction methods on MEG signals with different classifiers for epilepsy detection, subtype determination, and laterality classification. Finally, we also briefly look at the prospects of using MEG for epilepsy-assisted localization (spike detection, high-frequency oscillation detection) due to the unique advantages of MEG for functional area localization in epilepsy, and discuss the limitation of current research status and suggestions for future research. Overall, it is hoped that our review will facilitate the reader to quickly gain a general understanding of the problem of MEG-based epilepsy classification and provide ideas and directions for subsequent research.

Six-Center Assessment of CNN-Transformer with Belief Matching Loss for Patient-Independent Seizure Detection in EEG

Neurologists typically identify epileptic seizures from electroencephalograms (EEGs) by visual inspection. This process is often time-consuming, especially for EEG recordings that last hours or days. To expedite the process, a reliable, automated, and patient-independent seizure detector is essential. However, developing a patient-independent seizure detector is challenging as seizures exhibit diverse characteristics across patients and recording devices. In this study, we propose a patient-independent seizure detector to automatically detect seizures in both scalp EEG and intracranial EEG (iEEG). First, we deploy a convolutional neural network with transformers and belief matching loss to detect seizures in single-channel EEG segments. Next, we extract regional features from the channel-level outputs to detect seizures in multi-channel EEG segments. At last, we apply post-processing filters to the segment-level outputs to determine seizures' start and end points in multi-channel EEGs. Finally, we introduce the minimum overlap evaluation scoring as an evaluation metric that accounts for minimum overlap between the detection and seizure, improving upon existing assessment metrics. We trained the seizure detector on the Temple University Hospital Seizure (TUH-SZ) dataset and evaluated it on five independent EEG datasets. We evaluate the systems with the following metrics: sensitivity (SEN), precision (PRE), and average and median false positive rate per hour (aFPR/h and mFPR/h). Across four adult scalp EEG and iEEG datasets, we obtained SEN of 0.617-1.00, PRE of 0.534-1.00, aFPR/h of 0.425-2.002, and mFPR/h of 0-1.003. The proposed seizure detector can detect seizures in adult EEGs and takes less than 15[Formula: see text]s for a 30[Formula: see text]min EEG. Hence, this system could aid clinicians in reliably identifying seizures expeditiously, allocating more time for devising proper treatment.

Enhanced effective connectivity from the middle frontal gyrus to the parietal lobe is associated with impaired mental rotation after total sleep deprivation: An electroencephalogram study

Sleep deprivation impairs cognitive functions, including attention, memory, and decision-making. Studies on the neuro-electro-physiological mechanisms underlying total sleep deprivation (TSD) that impairs spatial cognition are limited. Based on electroencephalogram (EEG) and Exact Low Resolution Brain Electromagnetic Tomography (eLORETA), this study focused on the effects of TSD on mental rotation and the cognitive neural mechanisms underlying its damage. Twenty-four healthy college students completed mental rotation tasks while resting and after 36 h of TSD; their EEG data were simultaneously recorded. The amplitude of P300 component associated with mental rotation was observed and localized through source reconstruction, while changes in effective connectivity between multiple brain regions associated with mental rotation cognitive processing were calculated using isolated effective coherence (iCoh) of eLORETA. Compared with the baseline before TSD, the amplitude of the P300 component related to mental rotation decreased. The task-state data of P300 were localized to the source of the difference in ERP current density, and it was found that the brain regions related to the difference in the decrease in P300 amplitude included the superior parietal lobule, precuneus, prefrontal lobe, and other related regions. Effective connectivity analysis found that TSD enhanced the effective connectivity from the left middle frontal gyrus to the left superior parietal lobule, left inferior parietal lobule, and left precuneus under the identical condition. Pearson correlation analysis showed a positive correlation between the decrease in accuracy of mental rotation and increase in effective connectivity. Thus, our study suggests that TSD impairs the ability of the mental rotation, showing a decrease in P300 amplitude and an enhanced effective connectivity between the middle frontal gyrus and the parietal lobe in the task state.

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Epilepsy, one of the most common neurological diseases in China, is notorious for its spontaneous, unprovoked and recurrent seizures. The etiology of epilepsy varies among individual patients, including congenital gene mutation, traumatic injury, infections, etc. This heterogeneity partly hampered the accurate diagnosis and choice of appropriate treatments. Encouragingly, great achievements have been achieved in computational science, making it become a key player in medical fields gradually and bringing new hope for rapid and accurate diagnosis as well as targeted therapies in epilepsy. Here, we historically review the advances of computerized applications in epilepsy-especially those tremendous findings achieved in China-for different purposes including seizure prediction, localization of epileptogenic zone, post-surgical prognosis, etc. Special attentions are paid to the great progress based on artificial intelligence (AI), which is more "sensitive", "smart" and "in-depth" than human capacities. At last, we give a comprehensive discussion about the disadvantages and limitations of current computerized applications for epilepsy and propose some future directions as further stepping stones to embrace "the era of AI" in epilepsy.

Noninvasive Detection of Hippocampal Epileptiform Activity on Scalp Electroencephalogram

Importance

The hippocampus is a highly epileptogenic brain region, yet over 90% of hippocampal epileptiform activity (HEA) cannot be identified on scalp electroencephalogram (EEG) by human experts. Currently, detection of HEA requires intracranial electrodes, which limits our understanding of the role of HEA in brain diseases.

Objective

To develop and validate a machine learning algorithm that accurately detects HEA from a standard scalp EEG, without the need for intracranial electrodes.

Design, Setting, and Participants

In this diagnostic study, conducted from 2008 to 2021, EEG data were used from patients with temporal lobe epilepsy (TLE) and healthy controls (HCs) to train and validate a deep neural network, HEAnet, to detect HEA on scalp EEG. Participants were evaluated at tertiary-level epilepsy centers at 2 academic hospitals: Massachusetts General Hospital (MGH) or Brigham and Women's Hospital (BWH). Included in the study were patients aged 12 to 78 years with a clinical diagnosis of TLE and HCs without epilepsy. Patients with TLE and HCs with a history of intracranial surgery were excluded from the study.

Exposures

Simultaneous intracranial EEG and/or scalp EEG.

Main Outcomes and Measures

Performance was assessed using cross-validated areas under the receiver operating characteristic curve (AUC ROC) and precision-recall curve (AUC PR) and additional clinically relevant metrics.

Results

HEAnet was trained and validated using data sets that were derived from a convenience sample of 141 eligible participants (97 with TLE and 44 HCs without epilepsy) whose retrospective EEG data were readily available. Data set 1 included the simultaneous scalp EEG and intracranial electrode recordings of 51 patients with TLE (mean [SD] age, 40.7 [15.9] years; 30 men [59%]) at MGH. An automatically generated training data set with 972 095 positive HEA examples was created, in addition to a held-out expert-annotated testing data set with 22 762 positive HEA examples. HEAnet's performance was validated on 2 independent scalp EEG data sets: (1) data set 2 (at MGH; 24 patients with TLE and 20 HCs; mean [SD] age, 42.3 [16.2] years; 17 men [39%]) and (2) data set 3 (at BWH; 22 patients with TLE and 24 HCs; mean [SD] age, 43.0 [14.4] years; 20 men [43%]). For single-event detection of HEA on data set 1, HEAnet achieved a mean (SD) AUC ROC of 0.89 (0.01) and a mean (SD) AUC PR of 0.39 (0.03). On external validation with data sets 2 and 3, HEAnet accurately distinguished TLE from HC (AUC ROC of 0.88 and 0.95, respectively) and predicted epilepsy lateralization with 100% and 92% accuracy, respectively. HEAnet tracked dynamic changes in HEA in response to seizure medication adjustments and performed comparably with human experts in diagnosing TLE from 1-hour scalp EEG recordings, diagnosing TLE in several individuals that experts missed. Without reducing specificity, addition of HEAnet to human expert EEG review increased sensitivity for diagnosing TLE in humans from 50% to 58% to 63% to 67%.

Conclusions and Relevance

Results of this diagnostic study suggest that HEAnet provides a novel, noninvasive, quantitative, and clinically relevant biomarker of hippocampal hyperexcitability in humans.

Higher-order tensor decomposition based scalp-to-intracranial EEG projection for detection of interictal epileptiform discharges

Objective.Interictal epileptiform discharges (IEDs) occur between two seizures onsets. IEDs are mainly captured by intracranial recordings and are often invisible over the scalp. This study proposes a model based on tensor factorization to map the time-frequency (TF) features of scalp EEG (sEEG) to the TF features of intracranial EEG (iEEG) in order to detect IEDs from over the scalp with high sensitivity.Approach.Continuous wavelet transform is employed to extract the TF features. Time, frequency, and channel modes of IED segments from iEEG recordings are concatenated into a four-way tensor. Tucker and CANDECOMP/PARAFAC decomposition techniques are employed to decompose the tensor into temporal, spectral, spatial, and segmental factors. Finally, TF features of both IED and non-IED segments from scalp recordings are projected onto the temporal components for classification.Main results.The model performance is obtained in two different approaches: within- and between-subject classification approaches. Our proposed method is compared with four other methods, namely a tensor-based spatial component analysis method, TF-based method, linear regression mapping model, and asymmetric-symmetric autoencoder mapping model followed by convolutional neural networks. Our proposed method outperforms all these methods in both within- and between-subject classification approaches by respectively achieving 84.2% and 72.6% accuracy values.Significance.The findings show that mapping sEEG to iEEG improves the performance of the scalp-based IED detection model. Furthermore, the tensor-based mapping model outperforms the autoencoder- and regression-based mapping models.

Electrophysiological Biomarkers of Epileptogenicity in Alzheimer's Disease

Cortical network hyperexcitability is an inextricable feature of Alzheimer’s disease (AD) that also might accelerate its progression. Seizures are reported in 10–22% of patients with AD, and subclinical epileptiform abnormalities have been identified in 21–42% of patients with AD without seizures. Accurate identification of hyperexcitability and appropriate intervention to slow the compromise of cognitive functions of AD might open up a new approach to treatment. Based on the results of several studies, epileptiform discharges, especially those with specific features (including high frequency, robust morphology, right temporal location, and occurrence during awake or rapid eye movement states), frequent small sharp spikes (SSSs), temporal intermittent rhythmic delta activities (TIRDAs), and paroxysmal slow wave events (PSWEs) recorded in long-term scalp electroencephalogram (EEG) provide sufficient sensitivity and specificity in detecting cortical network hyperexcitability and epileptogenicity of AD. In addition, magnetoencephalogram (MEG), foramen ovale (FO) electrodes, and computational approaches help to find subclinical seizures that are invisible on scalp EEGs. We performed a comprehensive analysis of the aforementioned electrophysiological biomarkers of AD-related seizures.

Incorporating Uncertainty in Data Labeling into Automatic Detection of Interictal Epileptiform Discharges from Concurrent Scalp-EEG via Multi-way Analysis

Interictal epileptiform discharges (IEDs) are elicited from an epileptic brain, whereas they can also be due to other neurological abnormalities. The diversity in their morphologies, their strengths, and their sources within the brain cause a great deal of uncertainty in their labeling by clinicians. The aim of this study is therefore to exploit and incorporate this uncertainty (the probability of the waveform being an IED) in the IED detection system which combines spatial component analysis (SCA) with the IED probabilities referred to as SCA-IEDP-based method. For comparison, we also propose and study SCA-based method in which probability of the waveform being an IED is ignored. The proposed models are employed to detect IEDs in two different classification approaches: (1) subject-dependent and (2) subject-independent classification approaches. The proposed methods are compared with two other state-of-the-art methods namely, time-frequency features and tensor factorization methods. The proposed SCA-IEDP model has achieved superior performance in comparison with the traditional SCA and other competing methods. It achieved 79.9% and 63.4% accuracy values in subject-dependent and subject-independent classification approaches, respectively. This shows that considering the IED probabilities in designing an IED detection system can boost its performance.

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.

Night Watch on the Titanic: Detecting Early Signs of Epileptogenesis in Alzheimer Disease

Aberrant cortical network excitability is an inextricable feature of Alzheimer disease (AD) that can negatively impact memory and accelerate cognitive decline. Surface electroencephalogram spikes and intracranial recordings of nocturnal silent seizures in human AD, coupled with the abnormal neural synchrony that precedes development of behavioral seizures in mouse AD models, build the case for epileptogenesis as an early therapeutic target for AD. Since most individuals with AD do not develop overt seizures, leveraging functional biomarkers of epilepsy risk to stratify a heterogeneous AD patient population for treatment is research priority for successful clinical trial design. Who will benefit from antiseizure interventions, which one, and when should it begin?

Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning

OBJECTIVE

Develop a high-performing algorithm to detect mesial temporal lobe (mTL) epileptiform discharges on intracranial electrode recordings.

METHODS

An epileptologist annotated 13,959 epileptiform discharges from a dataset of intracranial EEG recordings from 46 epilepsy patients. Using this dataset, we trained a convolutional neural network (CNN) to recognize mTL epileptiform discharges from a single intracranial bipolar channel. The CNN outputs from multiple bipolar channel inputs were averaged to generate the final detector output. Algorithm performance was estimated using a nested 5-fold cross-validation.

RESULTS

On the receiver-operating characteristic curve, our algorithm achieved an area under the curve (AUC) of 0.996 and a partial AUC (for specificity > 0.9) of 0.981. AUC on a precision-recall curve was 0.807. A sensitivity of 84% was attained at a false positive rate of 1 per minute. 35.9% of the false positive detections corresponded to epileptiform discharges that were missed during expert annotation.

CONCLUSIONS

Using deep learning, we developed a high-performing, patient non-specific algorithm for detection of mTL epileptiform discharges on intracranial electrodes.

SIGNIFICANCE

Our algorithm has many potential applications for understanding the impact of mTL epileptiform discharges in epilepsy and on cognition, and for developing therapies to specifically reduce mTL epileptiform activity.

Multivariate Multiscale Dispersion Entropy of Biomedical Times Series

Due to the non-linearity of numerous physiological recordings, non-linear analysis of multi-channel signals has been extensively used in biomedical engineering and neuroscience. Multivariate multiscale sample entropy (MSE–mvMSE) is a popular non-linear metric to quantify the irregularity of multi-channel time series. However, mvMSE has two main drawbacks: (1) the entropy values obtained by the original algorithm of mvMSE are either undefined or unreliable for short signals (300 sample points); and (2) the computation of mvMSE for signals with a large number of channels requires the storage of a huge number of elements. To deal with these problems and improve the stability of mvMSE, we introduce multivariate multiscale dispersion entropy (MDE–mvMDE), as an extension of our recently developed MDE, to quantify the complexity of multivariate time series. We assess mvMDE, in comparison with the state-of-the-art and most widespread multivariate approaches, namely, mvMSE and multivariate multiscale fuzzy entropy (mvMFE), on multi-channel noise signals, bivariate autoregressive processes, and three biomedical datasets. The results show that mvMDE takes into account dependencies in patterns across both the time and spatial domains. The mvMDE, mvMSE, and mvMFE methods are consistent in that they lead to similar conclusions about the underlying physiological conditions. However, the proposed mvMDE discriminates various physiological states of the biomedical recordings better than mvMSE and mvMFE. In addition, for both the short and long time series, the mvMDE-based results are noticeably more stable than the mvMSE- and mvMFE-based ones. For short multivariate time series, mvMDE, unlike mvMSE, does not result in undefined values. Furthermore, mvMDE is faster than mvMFE and mvMSE and also needs to store a considerably smaller number of elements. Due to its ability to detect different kinds of dynamics of multivariate signals, mvMDE has great potential to analyse various signals.

New Approaches to Studying Silent Mesial Temporal Lobe Seizures in Alzheimer's Disease

Silent seizures were discovered in mouse models of Alzheimer's disease over 10 years ago, yet it remains unclear whether these seizures are a salient feature of Alzheimer's disease in humans. Seizures that arise early in the course of Alzheimer's disease most likely originate from the mesial temporal lobe, one of the first structures affected by Alzheimer's disease pathology and one of the most epileptogenic regions of the brain. Several factors greatly limit our ability to identify mesial temporal lobe seizures in patients with Alzheimer's disease, however. First, mesial temporal lobe seizures can be difficult to recognize clinically, as their accompanying symptoms are often subtle or even non-existent. Second, electrical activity arising from the mesial temporal lobe is largely invisible on the scalp electroencephalogram (EEG), the mainstay of diagnosis for epilepsy in this population. In this review, we will describe two new approaches being used to study silent mesial temporal lobe seizures in Alzheimer's disease. We will first describe the methodology and application of foramen ovale electrodes, which captured the first recordings of silent mesial temporal lobe seizures in humans with Alzheimer's disease. We will then describe machine learning approaches being developed to non-invasively identify silent mesial temporal lobe seizures on scalp EEG. Both of these tools have the potential to elucidate the role of silent seizures in humans with Alzheimer's disease, which could have important implications for early diagnosis, prognostication, and development of targeted therapies for this population.

Automated Source Estimation of Scalp EEG Epileptic Activity Using eLORETA Kurtosis Analysis

OBJECTIVES

eLORETA (exact low-resolution brain electromagnetic tomography) is a technique created by Pascual-Marqui et al. [Int J Psychophysiol. 1994 Oct; 18(1): 49-65] for the 3-dimensional representation of current source density in the brain by electroencephalography (EEG) data. Kurtosis analysis allows for the identification of spiky activity in the brain. In this study, we focused on the evaluation of the reliability of eLORETA kurtosis analysis. For this purpose, the results of eLORETA kurtosis source localization of paroxysmal activity in EEG were compared with those of eLORETA current source density (CSD) analysis of EEG data in 3 epilepsy patients with partial seizures.

METHODS

EEG was measured using a digital EEG system with 19 channels. We set the bandpass filter at traditional frequency band settings (1-4, 4-8, 8-15, 15-30, and 30-60 Hz) and 5-10 and 20-70 Hz and performed eLORETA kurtosis to compare the source localization of paroxysmal activity with that of visual interpretation of EEG data and CSD analysis of eLORETA in focal epilepsy patients.

RESULTS

The eLORETA kurtosis analysis of EEG data preprocessed by bandpass filtering from 20 to 70 Hz and traditional frequency band settings did not show any discrete paroxysmal source activity compatible with the results of CSD analysis of eLORETA. In all 3 cases, eLORETA kurtosis analysis filtered at 5-10 Hz showed paroxysmal activities in the theta band, which were all consistent with the visual inspection results and the CSD analysis results.

DISCUSSION

Our findings suggested that eLORETA kurtosis analysis of EEG data might be useful for the identification of spiky paroxysmal activity sources in epilepsy patients. Since EEG is widely used in the clinical practice of epilepsy, eLORETA kurtosis analysis is a promising method that can be applied to epileptic activity mapping.

Enhanced Data Covariance Estimation Using Weighted Combination of Multiple Gaussian Kernels for Improved M/EEG Source Localization

In the recent past, estimating brain activity with magneto/electroencephalography (M/EEG) has been increasingly employed as a noninvasive technique for understanding the brain functions and neural dynamics. However, one of the main open problems when dealing with M/EEG data is its non-Gaussian and nonstationary structure. In this paper, we introduce a methodology for enhancing the data covariance estimation using a weighted combination of multiple Gaussian kernels, termed WM-MK, that relies on the Kullback-Leibler divergence for associating each kernel weight to its relevance. From the obtained results of validation on nonstationary and non-Gaussian brain activity (simulated and real-world EEG data), WM-MK proves that the accuracy of the source estimation raises by more effectively exploiting the measured nonlinear structures with high time and space complexity.

Automatic Seizure Detection Based on Morphological Features Using One-Dimensional Local Binary Pattern on Long-Term EEG

Epileptic neurological disorder of the brain is widely diagnosed using the electroencephalography (EEG) technique. EEG signals are nonstationary in nature and show abnormal neural activity during the ictal period. Seizures can be identified by analyzing and obtaining features of EEG signal that can detect these abnormal activities. The present work proposes a novel morphological feature extraction technique based on the local binary pattern (LBP) operator. LBP provides a unique decimal value to a sample point by weighing the binary outcomes after thresholding the neighboring samples with the present sample point. These LBP values assist in capturing the rising and falling edges of the EEG signal, thus providing a morphologically featured discriminating pattern for epilepsy detection. In the present work, the variability in the LBP values is measured by calculating the sum of absolute difference of the consecutive LBP values. Interquartile range is calculated over the preprocessed EEG signal to provide dispersion measure in the signal. For classification purpose, K-nearest neighbor classifier is used, and the performance is evaluated on 896.9 hours of data from CHB-MIT continuous EEG database. Mean accuracy of 99.7% and mean specificity of 99.8% is obtained with average false detection rate of 0.47/h and sensitivity of 99.2% for 136 seizures.

Deep Neural Architectures for Mapping Scalp to Intracranial EEG

Data is often plagued by noise which encumbers machine learning of clinically useful biomarkers and electroencephalogram (EEG) data is no exemption. Intracranial EEG (iEEG) data enhances the training of deep learning models of the human brain, yet is often prohibitive due to the invasive recording process. A more convenient alternative is to record brain activity using scalp electrodes. However, the inherent noise associated with scalp EEG data often impedes the learning process of neural models, achieving substandard performance. Here, an ensemble deep learning architecture for nonlinearly mapping scalp to iEEG data is proposed. The proposed architecture exploits the information from a limited number of joint scalp-intracranial recording to establish a novel methodology for detecting the epileptic discharges from the sEEG of a general population of subjects. Statistical tests and qualitative analysis have revealed that the generated pseudo-intracranial data are highly correlated with the true intracranial data. This facilitated the detection of IEDs from the scalp recordings where such waveforms are not often visible. As a real-world clinical application, these pseudo-iEEGs are then used by a convolutional neural network for the automated classification of intracranial epileptic discharges (IEDs) and non-IED of trials in the context of epilepsy analysis. Although the aim of this work was to circumvent the unavailability of iEEG and the limitations of sEEG, we have achieved a classification accuracy of 68% an increase of 6% over the previously proposed linear regression mapping.