EEG-based classification of epilepsy and PNES: EEG microstate and functional brain network features

Ahmadi, Negar; Pei, Yulong; Carrette, Evelien; Aldenkamp, Albert P.; Pechenizkiy, Mykola

doi:10.1186/s40708-020-00107-z

Cited by 50 publications

(81 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there have been microstate feature-based studies on many diseases and cognitive tasks, there are few studies on classification using these microstate features. For example, Negar et al, investigated EEG microstate features for classification of epilepsy and PNES, and their findings showed that when the coverage feature of the EEG microstate analysis is calculated in beta-band, the classification showed fairly high accuracy and precision 41 . In addition, Kiran Raj et al, used machine learning techniques to explore if abnormalities in EEG microstates can identify patients with temporal lobe epilepsy 34 .…”

Section: Introductionmentioning

confidence: 99%

EEG microstate features according to performance on a mental arithmetic task

Kim

Duc

Choi

et al. 2021

Sci Rep

View full text Add to dashboard Cite

In this study, we hypothesized that task performance could be evaluated applying EEG microstate to mental arithmetic task. This pilot study also aimed at evaluating the efficacy of microstates as novel features to discriminate task performance. Thirty-six subjects were divided into good and poor performers, depending on how well they performed the task. Microstate features were derived from EEG recordings during resting and task states. In the good performers, there was a decrease in type C and an increase in type D features during the task compared to the resting state. Mean duration and occurrence decreased and increased, respectively. In the poor performers, occurrence of type D feature, mean duration and occurrence showed greater changes. We investigated whether microstate features were suitable for task performance classification and eleven features including four archetypes were selected by recursive feature elimination (RFE). The model that implemented them showed the highest classification performance for differentiating between groups. Our pilot findings showed that the highest mean Area Under Curve (AUC) was 0.831. This study is the first to apply EEG microstate features to specific cognitive tasks in healthy subjects, suggesting that EEG microstate features can reflect task achievement.

show abstract

Section: Introductionmentioning

confidence: 99%

EEG microstate features according to performance on a mental arithmetic task

Kim

Duc

Choi

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In the literature there are several promising results achieved by AI algorithms on neurological conditions [ 9 , 10 , 63 , 64 ]. Only two works have presented classification studies differentiating ES and PNES [ 18 , 65 ], both based on ML. The first study [ 18 ] performed a classification of 20 epilepsy and 20 PNES patients by using the imperialist competitive algorithm for feature extraction, achieving an accuracy higher than 90%.…”

Section: Discussionmentioning

confidence: 99%

“…However, they used the EEGs including periods of seizures: this was likely to result in a significant difference between the two groups. In another study of the same group [ 65 ], the authors studied the interictal EEGs of five subjects with ES and five subjects with PNES by feature extraction for automatic classification and functional brain network analysis. The accuracy was found to be around 80% when the classification was computed based on the microstate features extracted from the beta-bands.…”

Section: Discussionmentioning

confidence: 99%

Permutation Entropy-Based Interpretability of Convolutional Neural Network Models for Interictal EEG Discrimination of Subjects with Epileptic Seizures vs. Psychogenic Non-Epileptic Seizures

Giudice

Varone

Ieracitano

et al. 2022

Entropy

View full text Add to dashboard Cite

The differential diagnosis of epileptic seizures (ES) and psychogenic non-epileptic seizures (PNES) may be difficult, due to the lack of distinctive clinical features. The interictal electroencephalographic (EEG) signal may also be normal in patients with ES. Innovative diagnostic tools that exploit non-linear EEG analysis and deep learning (DL) could provide important support to physicians for clinical diagnosis. In this work, 18 patients with new-onset ES (12 males, 6 females) and 18 patients with video-recorded PNES (2 males, 16 females) with normal interictal EEG at visual inspection were enrolled. None of them was taking psychotropic drugs. A convolutional neural network (CNN) scheme using DL classification was designed to classify the two categories of subjects (ES vs. PNES). The proposed architecture performs an EEG time-frequency transformation and a classification step with a CNN. The CNN was able to classify the EEG recordings of subjects with ES vs. subjects with PNES with 94.4% accuracy. CNN provided high performance in the assigned binary classification when compared to standard learning algorithms (multi-layer perceptron, support vector machine, linear discriminant analysis and quadratic discriminant analysis). In order to interpret how the CNN achieved this performance, information theoretical analysis was carried out. Specifically, the permutation entropy (PE) of the feature maps was evaluated and compared in the two classes. The achieved results, although preliminary, encourage the use of these innovative techniques to support neurologists in early diagnoses.

show abstract

“…Therefore, Pearson product-moment correlation coefficient, which was first developed by Pearson in 1895 [33], was applied to calculate the correlation matrix, where the rows and columns both represent channels. The value of the correlation matrix represents the correlation between channels [34].…”

Section: Functional Brain Network Constructionmentioning

confidence: 99%

Prediction of Epilepsy Based on Tensor Decomposition and Functional Brain Network

et al. 2021

View full text Add to dashboard Cite

Epilepsy is a chronic neurological disorder which can affect 65 million patients worldwide. Recently, network based analyses have been of great help in the investigation of seizures. Now graph theory is commonly applied to analyze functional brain networks, but functional brain networks are dynamic. Methods based on graph theory find it difficult to reflect the dynamic changes of functional brain network. In this paper, an approach to extracting features from brain functional networks is presented. Dynamic functional brain networks can be obtained by stacking multiple functional brain networks on the time axis. Then, a tensor decomposition method is used to extract features, and an ELM classifier is introduced to complete epilepsy prediction. In the prediction of epilepsy, the accuracy and F1 score of the feature extracted by tensor decomposition are higher than the degree and clustering coefficient. The features extracted from the dynamic functional brain network by tensor decomposition show better and more comprehensive performance than degree and clustering coefficient in epilepsy prediction.

show abstract

EEG-based classification of epilepsy and PNES: EEG microstate and functional brain network features

Cited by 50 publications

References 59 publications

EEG microstate features according to performance on a mental arithmetic task

EEG microstate features according to performance on a mental arithmetic task

Permutation Entropy-Based Interpretability of Convolutional Neural Network Models for Interictal EEG Discrimination of Subjects with Epileptic Seizures vs. Psychogenic Non-Epileptic Seizures

Prediction of Epilepsy Based on Tensor Decomposition and Functional Brain Network

Contact Info

Product

Resources

About