Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.9
3.3
Journals
Brain Sciences
Special Issues
Advances in Seizure Prediction and Detection
share announcement

Advances in Seizure Prediction and Detection

A special issue of Brain Sciences (ISSN 2076-3425). This special issue belongs to the section "Computational Neuroscience and Neuroinformatics".

Deadline for manuscript submissions: closed (15 April 2022) | Viewed by 8574

Special Issue Editor

Dr. Mark Myers

E-Mail Website
Guest Editor
Department of Anatomy and Neurobiology, University of Tennessee Health Science Center, Memphis, TN 38163, USA
Interests: computational neurodynamics; brain modeling; epilepsy; cognitive processing; visual neuroscience

Special Issue Information

Dear Colleagues,

According to the United States Centers for Disease Control (CDC), the US population consists of 3.4 million individuals with epilepsy nationwide, including 3 million adults and 470,000 children—these refer to active epilepsy populations. Globally, there are over 50 million individuals whose quality of life is negatively impacted by epilepsy. Active epilepsy is defined as an individual with history of doctor-diagnosed epilepsy or seizure disorder currently taking medication to control it or had one or more seizures in the past year (or both). The average incidence of epilepsy each year in the United States is estimated at 150,000 or 48 for every 100,000 people. This makes epilepsy one of the most common neurological diseases globally.

Seizure prediction based on electroencephalograms (EEG)/intracranial EEG (iEEG) is complicated by two factors. The first is that preictal and interictal EEG/iEEG patterns across patients vary substantially. There may be no single generic algorithm that can be applied to all patients and achieve high sensitivity. The second is that EEG/iEEG is highly complex and varies over time, and no single measure of EEG/iEEG has yet been predictive on its own. Therefore, high sensitivity is possible using a patient-specific classification method based on multiple features extracted from EEG/iEEG. Seizure detection analysis includes the testing of pre-ictal (pre-seizure) and seizure occurrences. The robustness of any seizure prediction algorithm must also inter-ictal events take into consideration in order to test false detection occurrences through instances where there are no impending seizures.

Technological advances have focused on various feature extraction approaches to seizure prediction. Feature extraction approaches include, but are not limited to, univariate linear and nonlinear measures (spectral power, wavelet energy and entropy, correlation dimensionality, Lyapunov exponent, and dynamic similarity index), and bivariate linear measures (mean phase coherence, conditional probability, Shannon entropy, wavelet synchrony, lag synchronization index, dynamic entrainment, and phase locking value). In terms of advancements in classification, support vector machines are currently the most popular approach in supervised machine-learning and have been adopted in a large number of seizure-prediction studies. Other classifiers that have had a reasonably high degree of success are artificial and cellular neural networks with architectures involving feed-forward backpropagation, layer-recurrent feed-forward input time-delay backpropagation, Elman, and distributed time delay. These methods have incrementally improved prediction sensitivity and specificity performance.

The overall aim of this Brain Sciences Special Issue is to disseminate and discuss recent advances in seizure prediction methodologies, with a focus on the following subtopics:

  • Emerging methodologies in seizure prediction—providing new tools that improve sensitivity and specificity performance.
  • Modeling approaches to prediction and detection.
  • IoT advances in seizure prediction.
  • Novel approaches to prediction and treatment of intractable seizures.
  • Remote detection approaches to seizure prediction and detection.

Dr. Mark Myers
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Brain Sciences is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • patient-based prediction
  • seizure prediction
  • seizure detection
  • seizure prediction horizon (SPH)
  • seizure occurrence period (SOP)

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

12 pages, 2999 KiB  
Article
Transfer Learning-Based Model for Diabetic Retinopathy Diagnosis Using Retinal Images
by Muhammad Kashif Jabbar, Jianzhuo Yan, Hongxia Xu, Zaka Ur Rehman and Ayesha Jabbar
Brain Sci. 2022, 12(5), 535; https://0-doi-org.brum.beds.ac.uk/10.3390/brainsci12050535 - 22 Apr 2022
Cited by 30 | Viewed by 2620
Abstract
Diabetic retinopathy (DR) is a visual obstacle caused by diabetic disease, which forms because of long-standing diabetes mellitus, which damages the retinal blood vessels. This disease is considered one of the principal causes of sightlessness and accounts for more than 158 million cases [...] Read more.
Diabetic retinopathy (DR) is a visual obstacle caused by diabetic disease, which forms because of long-standing diabetes mellitus, which damages the retinal blood vessels. This disease is considered one of the principal causes of sightlessness and accounts for more than 158 million cases all over the world. Since early detection and classification could diminish the visual impairment, it is significant to develop an automated DR diagnosis method. Although deep learning models provide automatic feature extraction and classification, training such models from scratch requires a larger annotated dataset. The availability of annotated training datasets is considered a core issue for implementing deep learning in the classification of medical images. The models based on transfer learning are widely adopted by the researchers to overcome annotated data insufficiency problems and computational overhead. In the proposed study, features are extracted from fundus images using the pre-trained network VGGNet and combined with the concept of transfer learning to improve classification performance. To deal with data insufficiency and unbalancing problems, we employed various data augmentation operations differently on each grade of DR. The results of the experiment indicate that the proposed framework (which is evaluated on the benchmark dataset) outperformed advanced methods in terms of accurateness. Our technique, in combination with handcrafted features, could be used to improve classification accuracy. Full article
(This article belongs to the Special Issue Advances in Seizure Prediction and Detection)
►▼ Show Figures

Figure 1

5 pages, 195 KiB  
Communication
Use of Interval Therapy with Benzodiazepines to Prevent Seizure Recurrence in Stressful Situations
by Roy G. Beran
Brain Sci. 2022, 12(5), 512; https://0-doi-org.brum.beds.ac.uk/10.3390/brainsci12050512 - 19 Apr 2022
Viewed by 1499
Abstract
Introduction: Antiseizure medications (ASMs) control 70–75% of seizures. Accepting stress as a trigger for seizures, intervention, at the time of predictable stress, should offer a therapeutic option. Mode of intervention: Intervention requires the maintenance of an accurate seizure diary to identify a recurring [...] Read more.
Introduction: Antiseizure medications (ASMs) control 70–75% of seizures. Accepting stress as a trigger for seizures, intervention, at the time of predictable stress, should offer a therapeutic option. Mode of intervention: Intervention requires the maintenance of an accurate seizure diary to identify a recurring pattern. With a questioning approach to that diary, the clinician may intervene when stressful provocateurs occur. Benzodiazepines, such as clobazam, initiated prior to the predictable stress, and continued until after it has passed, should be short lived, making serious adverse effects unlikely. Benzodiazepines have a dual benefit, being both anxietolytic and raising the seizure threshold in patients with epilepsy. Discussion: Many patients claim stress provokes their seizures and may not be aware the stress was the provocateur, until after a seizure occurred, leading to a retrospective claim of the relationship. To confirm the relationship, permitting preventative measures, before exposure to provocative factors, often unable to be avoided, requires maintenance and review of a detailed diary. Interval temporary use of benzodiazepines, such as clobazam, or alternatively clonazepam, diazepam or nitrazepam, offers a reasonable response to obviate subsequent seizures, and should be continued, for a brief period, after the risk has abated. Subsequent review of the diary, over a period of repeated exposures to the identified stress, will confirm or refute the therapeutic effect. Conclusion: Judicious use of interval therapy, with one of the benzodiazepines, covering the period of stressful provocation, offers adjunctive treatment of possible refractory epilepsy, based upon the review of the strictly maintained epilepsy/seizure diary. Full article
(This article belongs to the Special Issue Advances in Seizure Prediction and Detection)
23 pages, 3708 KiB  
Article
Online Prediction of Lead Seizures from iEEG Data
by Hsiang-Han Chen, Han-Tai Shiao and Vladimir Cherkassky
Brain Sci. 2021, 11(12), 1554; https://0-doi-org.brum.beds.ac.uk/10.3390/brainsci11121554 - 24 Nov 2021
Cited by 10 | Viewed by 1681
Abstract
We describe a novel system for online prediction of lead seizures from long-term intracranial electroencephalogram (iEEG) recordings for canines with naturally occurring epilepsy. This study adopts new specification of lead seizures, reflecting strong clustering of seizures in observed data. This clustering results in [...] Read more.
We describe a novel system for online prediction of lead seizures from long-term intracranial electroencephalogram (iEEG) recordings for canines with naturally occurring epilepsy. This study adopts new specification of lead seizures, reflecting strong clustering of seizures in observed data. This clustering results in fewer lead seizures (~7 lead seizures per dog), and hence new challenges for online seizure prediction, that are addressed in the proposed system. In particular, the machine learning part of the system is implemented using the group learning method suitable for modeling sparse and noisy seizure data. In addition, several modifications for the proposed system are introduced to cope with the non-stationarity of a noisy iEEG signal. They include: (1) periodic retraining of the SVM classifier using most recent training data; (2) removing samples with noisy labels from training data; and (3) introducing a new adaptive post-processing technique for combining many predictions made for 20 s windows into a single prediction for a 4 h segment. Application of the proposed system requires only two lead seizures for training the initial model, and results in high prediction performance for all four dogs (with mean 0.84 sensitivity, 0.27 time-in-warning, and 0.78 false-positive rate per day). The proposed system achieves accurate prediction of lead seizures during long-term test periods, 3–16 lead seizures during a 169–364 day test period, whereas earlier studies did not differentiate between lead vs. non-lead seizures and used much shorter test periods (~few days long). Full article
(This article belongs to the Special Issue Advances in Seizure Prediction and Detection)
►▼ Show Figures

Figure 1

15 pages, 2127 KiB  
Article
Prediction of Epilepsy Based on Tensor Decomposition and Functional Brain Network
by Han Li, Qizhong Zhang, Ziying Lin and Farong Gao
Brain Sci. 2021, 11(8), 1066; https://0-doi-org.brum.beds.ac.uk/10.3390/brainsci11081066 - 13 Aug 2021
Cited by 7 | Viewed by 2077
Abstract
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 [...] Read more.
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. Full article
(This article belongs to the Special Issue Advances in Seizure Prediction and Detection)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop