Diagnosis of Epilepsy with Functional Connectivity in EEG after a Suspected First Seizure

Abstract

Epilepsy is regarded as a structural and functional network disorder, affecting around 50 million people worldwide. A correct disease diagnosis can lead to quicker medical action, preventing adverse effects. This paper reports the design of a classifier for epilepsy diagnosis in patients after a first ictal episode, using electroencephalogram (EEG) recordings. The dataset consists of resting-state EEG from 629 patients, of which 504 were retained for the study. The patient’s cohort exists out of 291 patients with epilepsy and 213 patients with other pathologies. The data were split into two sets: 80% training set and 20% test set. The extracted features from EEG included functional connectivity measures, graph measures, band powers and brain asymmetry ratios. Feature reduction was performed, and the models were trained using Machine Learning (ML) techniques. The models’ evaluation was performed with the area under the receiver operating characteristic curve (AUC). When focusing specifically on focal lesional epileptic patients, better results were obtained. This classification task was optimized using a 5-fold cross-validation, where SVM using PCA for feature reduction achieved an AUC of 0.730 ± 0.030. In the test set, the same model achieved 0.649 of AUC. The verified decrease is justified by the considerable diversity of pathologies in the cohort. An analysis of the selected features across tested models shows that functional connectivity and its graph measures have the most considerable predictive power, along with full-spectrum frequency-based features. To conclude, the proposed algorithms, with some refinement, can be of added value for doctors diagnosing epilepsy from EEG recordings after a suspected first seizure.

From basic sciences and engineering to epileptology: A translational approach

“…Recent investigations explored the use of quantitative scalp EEG analysis to assist the diagnosis of epilepsy, mainly based on the use of ML. [54][55][56][57][58][59] For example, SpikeNet, a deep neural network, was trained on a total of 9571 scalp EEG records (with and without spikes) to perform spike detection and showed performances compared to those achieved by fellowship-trained neurophysiology experts. 54 On the other side, DeepSpike was developed for the detection of epileptiform discharges based on multiple instance object detection and required a relatively low number of labeled training data.…”

“…59 In line with these investigations, Nadalin et al (2021) trained a CNN for spike ripple detection based on recordings from a total of 34 subjects. 60 Matos et al (2022) proposed a classifier for supporting the diagnosis of epilepsy, based on functional connectivity features of EEG in patients who had a first seizure. 57 in addition to quantitative EEG features such as univariate temporal measures, connectivity, and graph metrics.…”

“…60 Matos et al (2022) proposed a classifier for supporting the diagnosis of epilepsy, based on functional connectivity features of EEG in patients who had a first seizure. 57 in addition to quantitative EEG features such as univariate temporal measures, connectivity, and graph metrics. The algorithm was tested using a leave-one-subject-out cross-validation.…”

“…Recent investigations explored the use of quantitative scalp EEG analysis to assist the diagnosis of epilepsy, mainly based on the use of ML 54–59 . For example, SpikeNet, a deep neural network, was trained on a total of 9571 scalp EEG records (with and without spikes) to perform spike detection and showed performances compared to those achieved by fellowship‐trained neurophysiology experts 54 .…”

Direct Estimation of Equivalent Bioelectric Sources Based on Huygens’ Principle

“…The potential to be able to characterize the electric activity of different organs using a non-invasive method for the computation of their surface potentials is a major breakthrough, especially in real-time applications (i.e., diagnosis of a cardiac arrest). Such non-invasive methods are commonly known as the inverse problem of electroencephalography [ 3 , 13 , 14 ] and electrocardiography [ 15 , 16 , 17 ], respectively, which have been studied to a great extent within the scientific community. Inverse problems aim at the specification of those equivalent sources responsible for the genesis of several known (measured) potentials on a surface that encloses them.…”