scholarly journals EEG Synchronization Analysis for Seizure Prediction: A Study on Data of Noninvasive Recordings

Processes ◽  
2020 ◽  
Vol 8 (7) ◽  
pp. 846 ◽  
Author(s):  
Paolo Detti ◽  
Giampaolo Vatti ◽  
Garazi Zabalo Manrique de Lara
Keyword(s):  
Prediction Method ◽  
Control Device ◽  
Patient Specific ◽  
Seizure Prediction ◽  
Classification Approach ◽  
Machine Learning Methods ◽  
Eeg Data ◽  
Epileptic Patients ◽  
The University ◽  
The Brain

Objective: Epilepsy is a neurological disorder arising from anomalies of the electrical activity in the brain, affecting ~65 million individuals worldwide. Prediction methods, typically based on machine learning methods, require a large amount of data for training, in order to correctly classify seizures with small false alarm rates. Methods: In this work, we present a new database containing EEG scalp signals of 14 epileptic patients acquired at the Unit of Neurology and Neurophysiology of the University of Siena, Italy. Furthermore, a patient-specific seizure prediction method, based on the detection of synchronization patterns in the EEG, is proposed and tested on the data of the database. The use of noninvasive EEG data aims to explore the possibility of developing a noninvasive monitoring/control device for the prediction of seizures. The prediction method employs synchronization measures computed over all channel pairs and a computationally inexpensive threshold-based classification approach. Results and conclusions: The experimental analysis, performed by inspection and by the proposed threshold-based classifier on all the patients of the database, shows that the features extracted by the synchronization measures are able to detect preictal and ictal states and allow the prediction of the seizures few minutes before the seizure onsets.

scholarly journals A Review of Epileptic Seizure Prediction: Physiological Mechanism and Data Based Attempts

2021 ◽  
pp. 1-13
Author(s):  
Agboola HA ◽  
◽  
Susu AA ◽  
Keyword(s):  
Epileptic Seizure ◽  
Physiological Mechanism ◽  
Prediction Algorithm ◽  
Seizure Prediction ◽  
Brain Disorder ◽  
Treatment Protocols ◽  
Epileptic Patients ◽  
Epileptic Seizure Prediction ◽  
The Brain ◽  
Modelling Methods

Epilepsy is a chronic brain disorder and epileptic patients encounter recurrent seizures caused by abnormally synchronous electrical activity in parts of the brain. Over 50 million people spread across the world have epilepsy amongst whom approximately 30% suffer from refractory epilepsy which cannot be controlled by existing treatment protocols. For all epileptic sufferers, the thought that their next seizure could come at any time is agonizing and traumatic. However, if seizures could be predicted reliably, associated dangers and inconveniences will be greatly mitigated. Although the epileptic seizure prediction challenge has been tackled headlong by researchers through different modelling methods the problem of prediction has not yet been satisfactorily solved. In this paper, a systematic literature review of prominent epileptic seizure prediction attempts was carried out. We focus majorly on the two predominant classes of modelling attempts used: physiological mechanism and data based. The review underscores the richness and utility of the diverse modeling strategies as well as the gainful contribution of researchers in the field of epilepsy. It shows that meaningful progress has been made towards discovering the exact mechanism of seizure generation and realization of reliable and consistent seizure prediction algorithm

scholarly journals Evaluation of machine learning methods for seizure prediction in epilepsy

2019 ◽  
Vol 5 (1) ◽  
pp. 109-112
Author(s):  
Matthias Eberlein ◽  
Jens Müller ◽  
Hongliu Yang ◽  
Simon Walz ◽  
Janina Schreiber ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Statistical Evaluation ◽  
Performance Comparison ◽  
Seizure Prediction ◽  
Reliable System ◽  
Presurgical Evaluation ◽  
Intracranial Eeg ◽  
Machine Learning Methods ◽  
Eeg Data

AbstractEpilepsy affects about 50 million people worldwide of which one third is refractory to medication. An automated and reliable system that warns of impending seizures would greatly improve patient’s quality of life by overcoming the uncertainty and helplessness due to the unpredicted events. Here we present new seizure prediction results including a performance comparison of different methods. The analysis is based on a new set of intracranial EEG data that has been recorded in our working group during presurgical evaluation. We applied two different methods for seizure prediction and evaluated their performance pseudoprospectively. The comparison of this evaluation with common statistical evaluation reveals possible reasons for overly optimistic estimations of the performance of seizure forecasting systems.

Numerical Analysis of the VAD Outflow Cannula Positioning on the Blood Flow in the Patient–Specific Brain Supplying Arteries

2020 ◽  
Vol 22 (2) ◽  
pp. 619-636 ◽  
Author(s):  
Zbigniew Tyfa ◽  
Damian Obidowski ◽  
Krzysztof Jóźwik
Keyword(s):  
Blood Flow ◽  
Computer Aided Design ◽  
Volume Flow Rate ◽  
Flow Distribution ◽  
Primary Objective ◽  
Patient Specific ◽  
Blood Flow Distribution ◽  
Reconstruction Process ◽  
Outflow Cannula ◽  
The Brain

AbstractThe primary objective of this research can be divided into two separate aspects. The first one was to verify whether own software can be treated as a viable source of data for the Computer Aided Design (CAD) modelling and Computational Fluid Dynamics CFD analysis. The second aspect was to analyze the influence of the Ventricle Assist Device (VAD) outflow cannula positioning on the blood flow distribution in the brain-supplying arteries. Patient-specific model was reconstructed basing on the DICOM image sets obtained with the angiographic Computed Tomography. The reconstruction process was performed in the custom-created software, whereas the outflow cannulas were added in the SolidWorks software. Volumetric meshes were generated in the Ansys Mesher module. The transient boundary conditions enabled simulating several full cardiac cycles. Performed investigations focused mainly on volume flow rate, shear stress and velocity distribution. It was proven that custom-created software enhances the processes of the anatomical objects reconstruction. Developed geometrical files are compatible with CAD and CFD software – they can be easily manipulated and modified. Concerning the numerical simulations, several cases with varied positioning of the VAD outflow cannula were analyzed. Obtained results revealed that the location of the VAD outflow cannula has a slight impact on the blood flow distribution among the brain supplying arteries.

scholarly journals Transfer of rhodamine-123 into the brain and cerebrospinal fluid of fetal, neonatal and adult rats

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Liam M. Koehn ◽  
Katarzyna M. Dziegielewska ◽  
Mark D. Habgood ◽  
Yifan Huang ◽  
Norman R. Saunders
Keyword(s):  
Cerebrospinal Fluid ◽  
Fetal Brain ◽  
Maternal Blood ◽  
Adult Brain ◽  
Rhodamine 123 ◽  
Patient Specific ◽  
Adult Rats ◽  
Blood Brain ◽  
The Brain ◽  
Brain Barriers

Abstract Background Adenosine triphosphate binding cassette transporters such as P-glycoprotein (PGP) play an important role in drug pharmacokinetics by actively effluxing their substrates at barrier interfaces, including the blood-brain, blood-cerebrospinal fluid (CSF) and placental barriers. For a molecule to access the brain during fetal stages it must bypass efflux transporters at both the placental barrier and brain barriers themselves. Following birth, placental protection is no longer present and brain barriers remain the major line of defense. Understanding developmental differences that exist in the transfer of PGP substrates into the brain is important for ensuring that medication regimes are safe and appropriate for all patients. Methods In the present study PGP substrate rhodamine-123 (R123) was injected intraperitoneally into E19 dams, postnatal (P4, P14) and adult rats. Naturally fluorescent properties of R123 were utilized to measure its concentration in blood-plasma, CSF and brain by spectrofluorimetry (Clariostar). Statistical differences in R123 transfer (concentration ratios between tissue and plasma ratios) were determined using Kruskal-Wallis tests with Dunn’s corrections. Results Following maternal injection the transfer of R123 across the E19 placenta from maternal blood to fetal blood was around 20 %. Of the R123 that reached fetal circulation 43 % transferred into brain and 38 % into CSF. The transfer of R123 from blood to brain and CSF was lower in postnatal pups and decreased with age (brain: 43 % at P4, 22 % at P14 and 9 % in adults; CSF: 8 % at P4, 8 % at P14 and 1 % in adults). Transfer from maternal blood across placental and brain barriers into fetal brain was approximately 9 %, similar to the transfer across adult blood-brain barriers (also 9 %). Following birth when placental protection was no longer present, transfer of R123 from blood into the newborn brain was significantly higher than into adult brain (3 fold, p < 0.05). Conclusions Administration of a PGP substrate to infant rats resulted in a higher transfer into the brain than equivalent doses at later stages of life or equivalent maternal doses during gestation. Toxicological testing of PGP substrate drugs should consider the possibility of these patient specific differences in safety analysis.

scholarly journals Patient-Specific Detection of Cerebral Blood Flow Alterations as Assessed by Arterial Spin Labeling in Drug-Resistant Epileptic Patients

PLoS ONE ◽  
2015 ◽  
Vol 10 (5) ◽  
pp. e0123975 ◽  
Author(s):  
Ilaria Boscolo Galazzo ◽  
Silvia Francesca Storti ◽  
Alessandra Del Felice ◽  
Francesca Benedetta Pizzini ◽  
Chiara Arcaro ◽  
...  
Keyword(s):  
Blood Flow ◽  
Cerebral Blood Flow ◽  
Arterial Spin Labeling ◽  
Spin Labeling ◽  
Patient Specific ◽  
Drug Resistant ◽  
Specific Detection ◽  
Epileptic Patients

A fuzzy sensitivity analysis approach to estimate brain effective connectivity and its application to epileptic seizure detection

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Nader Moharamzadeh ◽  
Ali Motie Nasrabadi
Keyword(s):  
Time Series ◽  
Sensitivity Analysis ◽  
Effective Connectivity ◽  
Multivariate Time Series ◽  
Inference System ◽  
Eeg Data ◽  
Adaptive Neurofuzzy Inference System ◽  
Intracranial Electroencephalography ◽  
Fuzzy Network ◽  
The Brain

Abstract The brain is considered to be the most complicated organ in human body. Inferring and quantification of effective (causal) connectivity among regions of the brain is an important step in characterization of its complicated functions. The proposed method is comprised of modeling multivariate time series with Adaptive Neurofuzzy Inference System (ANFIS) and carrying out a sensitivity analysis using Fuzzy network parameters as a new approach to introduce a connectivity measure for detecting causal interactions between interactive input time series. The results of simulations indicate that this method is successful in detecting causal connectivity. After validating the performance of the proposed method on synthetic linear and nonlinear interconnected time series, it is applied to epileptic intracranial Electroencephalography (EEG) signals. The result of applying the proposed method on Freiburg epileptic intracranial EEG data recorded during seizure shows that the proposed method is capable of discriminating between the seizure and non-seizure states of the brain.

scholarly journals Cerebellar Atrophy in Epileptic Patients

1988 ◽  
Vol 15 (3) ◽  
pp. 299-303 ◽  
Author(s):  
M.I. Botez ◽  
Ezzedine Attig ◽  
Jean Lorrain Vézina
Keyword(s):  
Statistical Analysis ◽  
High Resolution ◽  
Posterior Fossa ◽  
De Novo ◽  
Cerebellar Atrophy ◽  
Ct Scans ◽  
Control Subjects ◽  
Generalized Seizures ◽  
Epileptic Patients ◽  
The Brain

ABSTRACT:High-resolution CT scans of the brain and posterior fossa were performed on 106 phenytoin (PHT)- treated epileptics, 28 de novo epileptics and 43 control subjects. A higher incidence of cerebellar and brainstem (CBS) atrophy was observed in chronic PHT- or PHT+ phenobarbital-treated epileptics compared to the two other groups. Some control subjects and de novo epileptics presented mild CBS atrophy, whereas moderate to severe atrophy was noted exclusively in chronically-treated patients. In attempting to delineate the etiology of CBS atrophy, epileptic patients were divided in three groups: 55 subjects with normal CT scans, 30 with both cerebral and CBS atrophy, and 49 with pure CBS atrophy. Their ages, length of illness, number of generalized seizures, number of other seizures, and amount of PHT received during their lifetime were assessed. Statistical analysis revealed that posterior fossa atrophy in epileptics was significantly correlated with both the length of the illness and the amount of PHT ingested during the patient's lifetime. The number of seizures appears to not be related to CBS atrophy.

scholarly journals Epileptic Seizure Prediction over EEG Data using Hybrid CNN-SVM Model with Edge Computing Services

2018 ◽  
Vol 210 ◽  
pp. 03016 ◽  
Author(s):  
Punjal Agarwal ◽  
Hwang-Cheng Wang ◽  
Kathiravan Srinivasan
Keyword(s):  
Epileptic Seizure ◽  
Life Support ◽  
Real Life ◽  
Prediction Method ◽  
Edge Computing ◽  
Support Vector ◽  
Seizure Prediction ◽  
Computing Services ◽  
Svm Model ◽  
Epileptic Seizure Prediction

Epilepsy is one of the most common neurological disorders, which is characterized by unpredictable brain seizure. About 30% of the patients are not even aware that they have epilepsy and many have to undergo surgeries to relieve the pain. Therefore, developing a robust brain-computer interface for seizure prediction can help epileptic patients significantly. In this paper, we propose a hybrid CNN-SVM model for better epileptic seizure prediction. A convolutional neural network (CNN) consists of a multilayer structure, which can be adapted and modified according to the requirement of different applications. A support vector machine is a discriminative classifier which can be described by a separating optimal hyperplane used for categorizing new samples. The combination of CNN and SVM is found to provide an effective way for epileptic prediction. Furthermore, the resulting model is made autonomous using edge computing services and is shown to be a viable seizure prediction method. The results can be beneficial in real-life support of epilepsy patients.

scholarly journals A Novel Permutation Entropy-Based EEG Channel Selection for Improving Epileptic Seizure Prediction

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7972
Author(s):  
Jee S. Ra ◽  
Tianning Li ◽  
Yan Li
Keyword(s):  
Sensitivity And Specificity ◽  
Epileptic Seizure ◽  
Epileptic Seizures ◽  
Optimization Method ◽  
Channel Selection ◽  
Permutation Entropy ◽  
Patient Specific ◽  
Support Vector ◽  
Seizure Prediction ◽  
Epileptic Seizure Prediction

The key research aspects of detecting and predicting epileptic seizures using electroencephalography (EEG) signals are feature extraction and classification. This paper aims to develop a highly effective and accurate algorithm for seizure prediction. Efficient channel selection could be one of the solutions as it can decrease the computational loading significantly. In this research, we present a patient-specific optimization method for EEG channel selection based on permutation entropy (PE) values, employing K nearest neighbors (KNNs) combined with a genetic algorithm (GA) for epileptic seizure prediction. The classifier is the well-known support vector machine (SVM), and the CHB-MIT Scalp EEG Database is used in this research. The classification results from 22 patients using the channels selected to the patient show a high prediction rate (average 92.42%) compared to the SVM testing results with all channels (71.13%). On average, the accuracy, sensitivity, and specificity with selected channels are improved by 10.58%, 23.57%, and 5.56%, respectively. In addition, four patient cases validate over 90% accuracy, sensitivity, and specificity rates with just a few selected channels. The corresponding standard deviations are also smaller than those used by all channels, demonstrating that tailored channels are a robust way to optimize the seizure prediction.

Sign in / Sign up

Export Citation Format

Share Document