A robust approach towards epileptic seizure detection

Amin, Saadullah; Kamboh, Awais Mehmood

doi:10.1109/mlsp.2016.7738825

Cited by 11 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…El Saadi et al [142] obtained 97.3% accuracy using the under-sampling method with the SVM classifier. In another work by Saadullah and Awais [143], they used a combination of SMOTE and RUSTBOST techniques for detecting seizure to imbalance seizure data with 97% accuracy. However, the research done by Yuan Qi et al [86] was very close to the satisfactory result as they assigned the heavy weights to a minority class of the data to maintain the effective balance and solved the biasing issue.…”

Section: Class Imbalance Issue In Seizure Detectionmentioning

confidence: 99%

A review of epileptic seizure detection using machine learning classifiers

et al. 2020

View full text Add to dashboard Cite

Epilepsy is a serious chronic neurological disorder, can be detected by analyzing the brain signals produced by brain neurons. Neurons are connected to each other in a complex way to communicate with human organs and generate signals. The monitoring of these brain signals is commonly done using Electroencephalogram (EEG) and Electrocorticography (ECoG) media. These signals are complex, noisy, non-linear, non-stationary and produce a high volume of data. Hence, the detection of seizures and discovery of the brain-related knowledge is a challenging task. Machine learning classifiers are able to classify EEG data and detect seizures along with revealing relevant sensible patterns without compromising performance. As such, various researchers have developed number of approaches to seizure detection using machine learning classifiers and statistical features. The main challenges are selecting appropriate classifiers and features. The aim of this paper is to present an overview of the wide varieties of these techniques over the last few years based on the taxonomy of statistical features and machine learning classifiers—‘black-box’ and ‘non-black-box’. The presented state-of-the-art methods and ideas will give a detailed understanding about seizure detection and classification, and research directions in the future.

show abstract

Section: Class Imbalance Issue In Seizure Detectionmentioning

confidence: 99%

A review of epileptic seizure detection using machine learning classifiers

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Japkowicz and Stephen [114], in a review, believed that the SVMs were less prone to the imbalanced classification problem than other classification learning algorithms since the boundaries were calculated in regards to only a few support vectors, and the class size might not affect the class boundary too much. Nonetheless, researches [58], [115], [116] confirmed that SVMs could be ineffective in determining the class boundaries when the class distribution was highly skewed. These results supported our recent findings that Cubic SVM and k-NN performed consistently better in terms of accuracy but have been biased toward the majority class (i.e., good outcomes).…”

Section: ) Rusboosted Trees Prediction Modelmentioning

confidence: 99%

Improving Outcome Prediction for Traumatic Brain Injury From Imbalanced Datasets Using RUSBoosted Trees on Electroencephalography Spectral Power

Noor¹,

Ibrahim²,

Lah³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Reliable prediction of traumatic brain injury (TBI) outcomes based on machine learning (ML) that is derived from quantitative electroencephalography (EEG) features has renewed interest in recent years. Nevertheless, the approach has suffered from imbalanced datasets. Hence, to get a reliable predictive model for predicting outcomes, specifically in a high proportion of moderate TBI with good outcomes, could be challenging. This work proposes an improved outcome predictive model that combines the absolute power spectral density (PSD) as input features for training random under-sampling boosting decision trees (RUSBoosted Trees) as a classifier. Resting-state, eyes-closed EEG data were obtained from 27 moderate TBI patients with follow-up visits. Patient outcome at 4-10 weeks to 12-month was dichotomized based on the Glasgow Outcome Scale as poor (GOS score ≤ 4) and good outcomes (GOS score = 5). The predictive values of absolute PSD from five frequency bands: δ (0.5-4Hz), θ (4-7Hz), α (7-13Hz), β (13-30Hz) and γ (30-100Hz) were evaluated to identify the most informative predictors for reliable prediction outcomes. RUSBoosted Trees performed best at discriminating patients into two outcomes categories (G-Mean = 92.95%, TP rate =100%, TN rate = 86.4%) of absolute PSD in δ and γ bands, which was excellent compared to the other state-of-the-art methods. The highest area under the curve (AUC) of absolute PSD in δ (AUC δ = 0.97) and γ (AUC γ = 0.95) revealed their predictive values as robust prognostic markers for prediction outcomes. The RUSBoosted Trees presents a promising result in prognosis prediction of highly imbalanced data, making it an accessible prediction tool for clinical decision-making, unlike the black-box approaches.

show abstract

“…In this study, the EEG data used is from a publicly available dataset, referred to as CHB-MIT dataset [32]. This dataset has been very widely used, e.g., [33] and [34]. This EEG dataset is recorded from 24 patients at Children Hospital Boston (CHB).…”

Section: A Datasetmentioning

confidence: 99%

“…Out of the total 50,000, let's say 48,000, i.e., 96%, belong to the non-seizure class, i.e., normal activity, and the remaining 2000, i.e., 4%, to the seizure class. If we train a traditional classifier on this composition of data, there is overwhelming likelihood that our classifier may not deliver satisfactory performance due to inadequate training of the marginalized class [34].…”

Section: Classifiermentioning

confidence: 99%

See 1 more Smart Citation

Epileptic Seizure Detection With a Reduced Montage: A Way Forward for Ambulatory EEG Devices

et al. 2020

Self Cite

View full text Add to dashboard Cite

Electroencephalogram (EEG) is one of the fundamental tools for analyzing the behavior of brain and particularly helpful for treatment of epilepsy and detection of associated seizures. For longterm recording of EEG signals, current research is heading towards simple, unobtrusive and ambulatory devices with a small number of channels. The primary contribution of this paper is to assess the performance difference between the seizure detection results using features from all channels versus only the channels in/around the temporal region. For this purpose, we develop a supervised seizure detection algorithm that uses time domain features extracted sequentially for every 1-second epoch. By using this algorithm, we obtained sensitivity values of 0.95 and 0.92, specificity values of 0.99 and 0.99 and false positive per hour values as 0.16 and 0.21 for all 23 channels and 10 temporal region channels, respectively. These results show that restricting the EEG analysis to temporal region results only in a graceful and gradual degradation of classifier performance. We conclude that EEG ambulatory devices with a montage local to the temporal region could demonstrate satisfactory performance. This presents a promising way forward for the use of ambulatory devices with compact wearable design.

show abstract

A robust approach towards epileptic seizure detection

Cited by 11 publications

References 5 publications

A review of epileptic seizure detection using machine learning classifiers

A review of epileptic seizure detection using machine learning classifiers

Improving Outcome Prediction for Traumatic Brain Injury From Imbalanced Datasets Using RUSBoosted Trees on Electroencephalography Spectral Power

Epileptic Seizure Detection With a Reduced Montage: A Way Forward for Ambulatory EEG Devices

Contact Info

Product

Resources

About