scholarly journals Features importance in seizure classification using scalp EEG reduced to single timeseries

2021 ◽  
Author(s):  
Sebastien Naze ◽  
Jianbin Tang ◽  
James Kozloski ◽  
Stefan Harrer
Keyword(s):  
Support Vector ◽  
Seizure Type ◽  
Low Frequencies ◽  
Scalp Eeg ◽  
Eeg Spectrum ◽  
Wearable Systems ◽  
Vector Machines ◽  
Eeg Recordings ◽  
Single Trace ◽  
Scalp Electroencephalogram

Seizure detection and seizure-type classification are best performed using intra-cranial or full-scalp electroencephalogram (EEG). In embedded wearable systems however, recordings from only a few electrodes are available, reducing the spatial resolution of the signals to a handful of timeseries at most. Taking this constraint into account, we tested the performance of multiple classifiers using a subset of the EEG recordings by selecting a single trace from the montage or performing a dimensionality reduction over each hemispherical space. Our results support that Random Forest (RF) classifiers lead most efficient and stable classification performances over Support Vector Machines (SVM). Interestingly, tracking the feature importances using permutation tests reveals that classical EEG spectrum power bands display different rankings across the classifiers: low frequencies (delta, theta) are most important for SVMs while higher frequencies (alpha, gamma) are more relevant for RF and Decision Trees. We reach up to 94.3% +/- 5.3% accuracy in classifying absence from tonic-clonic seizures using state-of-art sampling methods for unbalanced datasets and leave-patients-out 3-fold cross-validation policy.

scholarly journals P.129 Bi-insular Responsive Neurostimulation Artifact on Scalp Electroencephalogram

2021 ◽  
Vol 48 (s3) ◽  
pp. S56-S56
Author(s):  
EM Paredes-Aragón ◽  
M Chávez-Castillo ◽  
GL Barkley ◽  
JG Burneo ◽  
A Suller-Martí
Keyword(s):  
Scientific Literature ◽  
Seizure Activity ◽  
Epileptiform Activity ◽  
Scalp Eeg ◽  
Proven Efficacy ◽  
Eeg Recordings ◽  
Scalp Electroencephalogram ◽  
Intracranial Electroencephalography

Background: Background: Responsive Neurostimulation (RNS) has proven efficacy in treating medically resistant epilepsy as an intracranial system detecting, recording and treating seizures automatically. No information exists pertaining to artifact characteristics of RNS findings in scalp EEG. Methods: A 30 year-old female was diagnosed using intracranial electroencephalography(iEEG), with bi-insular epilepsy, of unknown cause. She presented large number of focal unaware non-motor seizures and seizures with progression to bilateral tonic-clonic. She was implanted with bi-insular RNS. Results: During scalp EEG recordings, a prominent artifact was seen corresponding to an automatized discharge suspectedly evoked by the RNS trying to minimize the frequent epileptiform activity in her case. Figure 1 and 2 depict these findings. Conclusions: Artifact seen by the RNS in scalp EEG has not been previously described in scientific literature. These findings must be identified to better characterize the role of the RNS in EEG and treatment of seizure activity visible on scalp recordings.

A Realistic Seizure Prediction Study Based on Multiclass SVM

2017 ◽  
Vol 27 (03) ◽  
pp. 1750006 ◽  
Author(s):  
Bruno Direito ◽  
César A. Teixeira ◽  
Francisco Sales ◽  
Miguel Castelo-Branco ◽  
António Dourado
Keyword(s):  
Statistical Significance ◽  
False Positive Rate ◽  
Patient Specific ◽  
Support Vector ◽  
Seizure Prediction ◽  
Feature Sets ◽  
Scalp Eeg ◽  
Positive Rate ◽  
Eeg Recordings ◽  
Multiclass Svm

A patient-specific algorithm, for epileptic seizure prediction, based on multiclass support-vector machines (SVM) and using multi-channel high-dimensional feature sets, is presented. The feature sets, combined with multiclass classification and post-processing schemes aim at the generation of alarms and reduced influence of false positives. This study considers 216 patients from the European Epilepsy Database, and includes 185 patients with scalp EEG recordings and 31 with intracranial data. The strategy was tested over a total of 16,729.80[Formula: see text]h of inter-ictal data, including 1206 seizures. We found an overall sensitivity of 38.47% and a false positive rate per hour of 0.20. The performance of the method achieved statistical significance in 24 patients (11% of the patients). Despite the encouraging results previously reported in specific datasets, the prospective demonstration on long-term EEG recording has been limited. Our study presents a prospective analysis of a large heterogeneous, multicentric dataset. The statistical framework based on conservative assumptions, reflects a realistic approach compared to constrained datasets, and/or in-sample evaluations. The improvement of these results, with the definition of an appropriate set of features able to improve the distinction between the pre-ictal and nonpre-ictal states, hence minimizing the effect of confounding variables, remains a key aspect.

scholarly journals Clinical and socio-demographic factors associated with electroencephalographic abnormalities in children with epilepsy

2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Christian Chukwukere Ogoke ◽  
Wilson Chukwuneke Igwe ◽  
Esther Ngozi Umeadi
Keyword(s):  
Demographic Factors ◽  
Categorical Variables ◽  
Seizure Type ◽  
Tertiary Referral Center ◽  
Scalp Eeg ◽  
Anti Epileptic Drug ◽  
Eeg Abnormalities ◽  
Eeg Recordings ◽  
Socio Demographic Factors ◽  
The Cost

Electroencephalography (EEG) makes critical contribution to the management of epilepsies. Few studies have examined the clinical and socio-demographic factors that are likely to predict finding an abnormal or epileptiform EEG in children with epilepsy (CWE). Knowledge of clinical variables and socio demographic factors that determine EEG abnormalities may inform careful selection of children for EEG and improve the cost-effectiveness of this investigation. Therefore, this study was carried out to assess the relationship between the occurrence of EEG abnormalities and certain factors such as age, gender, clinical neurologic state, seizure type, anti-epileptic drug therapy, activation procedure such as sleep and etiology of epilepsy in children who had EEG in Owerri, Nigeria. The clinical and EEG records of children who had EEG at a tertiary referral center over a period of two years were retrospectively reviewed. Relevant data including demographics, clinical neurologic state, seizure type, EEG findings were extracted. Statistical analysis was used to determine association between categorical variables. The variables noted to be significantly associated with abnormal EEG recordings were the presence of abnormal neurologic findings (p=0.020) and etiology of epilepsy (p=0.045). There were no significant association between abnormal EEG findings and age (p=0.680), gender (p=0.802) and seizure types (p=0.157). The clinical neurological state and etiology of epilepsy in children were significantly associated with the occurrence of abnormalities and yield of interictal scalp EEG. Children with epilepsy who are neurologically abnormal or have multiple etiological factors could be prioritized in EEG appointments in resource-poor settings. Further research in children with epilepsy is needed to confirm these findings.

A NEW PARAMETRIC FEATURE DESCRIPTOR FOR THE CLASSIFICATION OF EPILEPTIC AND CONTROL EEG RECORDS IN PEDIATRIC POPULATION

2012 ◽  
Vol 22 (02) ◽  
pp. 1250001 ◽  
Author(s):  
MERCEDES CABRERIZO ◽  
MELVIN AYALA ◽  
MOHAMMED GORYAWALA ◽  
PRASANNA JAYAKAR ◽  
MALEK ADJOUADI
Keyword(s):  
Pediatric Population ◽  
Support Vector ◽  
Feature Descriptor ◽  
Scalp Eeg ◽  
Vector Machines ◽  
Epileptic Patients ◽  
Sensitivity Specificity ◽  
And Control

This study evaluates the sensitivity, specificity and accuracy in associating scalp EEG to either control or epileptic patients by means of artificial neural networks (ANNs) and support vector machines (SVMs). A confluence of frequency and temporal parameters are extracted from the EEG to serve as input features to well-configured ANN and SVM networks. Through these classification results, we thus can infer the occurrence of high-risk (epileptic) as well as low risk (control) patients for potential follow up procedures.

scholarly journals Automatic Recognition of Personality Profiles Using EEG Functional Connectivity during Emotional Processing

2020 ◽  
Vol 10 (5) ◽  
pp. 278 ◽  
Author(s):  
Manousos A. Klados ◽  
Panagiota Konstantinidi ◽  
Rosalia Dacosta-Aguayo ◽  
Vasiliki-Despoina Kostaridou ◽  
Alessandro Vinciarelli ◽  
...  
Keyword(s):  
Emotional Processing ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Personality Profiles ◽  
Learning Techniques ◽  
Eeg Recordings ◽  
Eeg Functional Connectivity ◽  
Scalp Electroencephalogram ◽  
High Level ◽  
User Friendly

Personality is the characteristic set of an individual’s behavioral and emotional patterns that evolve from biological and environmental factors. The recognition of personality profiles is crucial in making human–computer interaction (HCI) applications realistic, more focused, and user friendly. The ability to recognize personality using neuroscientific data underpins the neurobiological basis of personality. This paper aims to automatically recognize personality, combining scalp electroencephalogram (EEG) and machine learning techniques. As the resting state EEG has not so far been proven efficient for predicting personality, we used EEG recordings elicited during emotion processing. This study was based on data from the AMIGOS dataset reflecting the response of 37 healthy participants. Brain networks and graph theoretical parameters were extracted from cleaned EEG signals, while each trait score was dichotomized into low- and high-level using the k-means algorithm. A feature selection algorithm was used afterwards to reduce the feature-set size to the best 10 features to describe each trait separately. Support vector machines (SVM) were finally employed to classify each instance. Our method achieved a classification accuracy of 83.8% for extraversion, 86.5% for agreeableness, 83.8% for conscientiousness, 83.8% for neuroticism, and 73% for openness.

scholarly journals Seizure Prediction With Spectral Power of EEG Using Cost-Sensitive Support Vector Machines

2010 ◽  
Vol 4 (2) ◽  
Author(s):  
Yun Park ◽  
Theoden Netoff ◽  
Keshab Parhi
Keyword(s):  
Support Vector Machines ◽  
Spectral Power ◽  
Prediction Algorithm ◽  
Patient Specific ◽  
Support Vector ◽  
Seizure Prediction ◽  
Time Space ◽  
Vector Machines ◽  
Out Of Sample ◽  
Eeg Recordings

A patient-specific seizure prediction algorithm is proposed using a classifier to differentiate pre-ictal from inter-ictal EEG signals. The spectral power of EEG processed in four different fashions is used as features: raw, time-differential, space-differential, and time/space-differential EEG. The features are classified using cost-sensitive support vector machines by the double cross-validation methodology. The proposed algorithm has been applied to EEG recordings of 18 patients in the Freiburg EEG database, totaling 80 seizures and 437 h long inter-ictal recordings. Classification with the feature obtained from time/space-differential ECoG demonstrates the performance of 86.25% sensitivity and 0.1281 false positives per hour in out-of-sample testing.

A Comparison of Scaling Methods to Obtain Calibrated Probabilities of Activity for Ligand-Target Predictions

2020 ◽  
Author(s):  
Lewis Mervin ◽  
Avid M. Afzal ◽  
Ola Engkvist ◽  
Andreas Bender
Keyword(s):  
Target Prediction ◽  
Support Vector ◽  
Machine Learning Method ◽  
Learning Method ◽  
Protein Target ◽  
Bioactivity Prediction ◽  
Vector Machines ◽  
Scaling Methods ◽  
Data Points ◽  
Compound Target

In the context of bioactivity prediction, the question of how to calibrate a score produced by a machine learning method into reliable probability of binding to a protein target is not yet satisfactorily addressed. In this study, we compared the performance of three such methods, namely Platt Scaling, Isotonic Regression and Venn-ABERS in calibrating prediction scores for ligand-target prediction comprising the Naïve Bayes, Support Vector Machines and Random Forest algorithms with bioactivity data available at AstraZeneca (40 million data points (compound-target pairs) across 2112 targets). Performance was assessed using Stratified Shuffle Split (SSS) and Leave 20% of Scaffolds Out (L20SO) validation.

Comparison of SVM, RF and SGD Methods for Determination of Programmer's Performance Classification Model in Social Media Activities

2020 ◽  
Vol 4 (2) ◽  
pp. 329-335
Author(s):  
Rusydi Umar ◽  
Imam Riadi ◽  
Purwono
Keyword(s):  
Social Media ◽  
Gradient Descent ◽  
Classification Model ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Svm Algorithm ◽  
Vector Machines ◽  
Performance Patterns ◽  
A Company

The failure of most startups in Indonesia is caused by team performance that is not solid and competent. Programmers are an integral profession in a startup team. The development of social media can be used as a strategic tool for recruiting the best programmer candidates in a company. This strategic tool is in the form of an automatic classification system of social media posting from prospective programmers. The classification results are expected to be able to predict the performance patterns of each candidate with a predicate of good or bad performance. The classification method with the best accuracy needs to be chosen in order to get an effective strategic tool so that a comparison of several methods is needed. This study compares classification methods including the Support Vector Machines (SVM) algorithm, Random Forest (RF) and Stochastic Gradient Descent (SGD). The classification results show the percentage of accuracy with k = 10 cross validation for the SVM algorithm reaches 81.3%, RF at 74.4%, and SGD at 80.1% so that the SVM method is chosen as a model of programmer performance classification on social media activities.

Sign in / Sign up

Export Citation Format

Share Document