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

Abstract

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.

Time-Frequency Representations of Brain Oscillations: Which One Is Better?

“…Machine learning techniques for the exploration of brain signals have witnessed increased adoption in recent years ( Moca et al, 2009 ; Vu et al, 2018 ; Glaser et al, 2019 ; Roy et al, 2019 ; Li et al, 2020 ; Lo Giudice et al, 2022 ). However, it is important to note that such tools have their own pitfalls and may present traps that can mislead even the experimented user.…”

Entropy Measures of Electroencephalograms towards the Diagnosis of Psychogenic Non-Epileptic Seizures

“…Gasparini et al [ 13 ] and Lo Giudice et al [ 14 ] both statistically analysed the entropy of the EEG signal. The authors of [ 13 ] found no differences between the Shannon or permutation entropies of PNES patients and healthy controls, and [ 14 ] found no difference in interictal permutation entropy between PNES and epilepsy subjects. Therefore, statistical analysis alone may not be sufficient to differentiate between these groups.…”

“…Gasparini et al [ 13 ] and Lo Giudice et al [ 14 ] both used the entropy of the EEG as a control for comparison to the entropies of hidden layers in deep learning models. Gasparini et al [ 13 ] extracted the Shannon and permutation entropies from the EEGs of six PNES subjects and ten healthy controls and found no statistical difference between the two classes for either measure.…”

“…Gasparini et al [ 13 ] extracted the Shannon and permutation entropies from the EEGs of six PNES subjects and ten healthy controls and found no statistical difference between the two classes for either measure. Lo Giudice et al [ 14 ] used interictal EEG from 18 epilepsy and 18 PNES subjects and also found no statistical difference between the two classes for the permutation entropy of the signal.…”

Convolutional Neural Network Classification of Rest EEG Signals among People with Epilepsy, Psychogenic Non Epileptic Seizures and Control Subjects

“…They have abilities to learn complex patterns, including latent features that are not discernible by visual inspection or standard approaches. Indeed, in a previous paper, we [ 13 ] compared the processing capabilities of standard algorithms with deep algorithms. We analyzed 18 patients with ES and 18 patients with PNES.…”