Task-free spectral EEG dynamics track and predict patient recovery from severe acquired brain injury

Brink, Ruud L. van den; Nieuwenhuis, Sander; Boxtel, G.J.M. van; Luijtelaar, E.L.J.M. van; Eilander, H.J.; Wijnen, V.J.M.

doi:10.1016/j.nicl.2017.10.003

Cited by 23 publications

(28 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the performance of the proposed method is only assessed with four similar methods. The first comparison method is the work by Brink et al [ 30 ] that utilized Naive Bayes to classify TBI from task-free EEG. The second method for comparison classifies the EEG signal by employing the AdaBoost classifier and is developed by McNerney et al [ 29 ].…”

Section: Resultsmentioning

confidence: 99%

“…Asserting that the extracted features from the frequency bands can provide valuable data to the classifier, the four comparison methods [ 29 , 30 , 91 , 92 ] used the frequency band-based features. In contrast, the proposed approach in this research does not require any extraction of the features.…”

Section: Resultsmentioning

confidence: 99%

“…Subsequently, the signal is downsampled from 1000 Hz to 100 Hz (i.e., using a downsampling integer factor D of 10). Downsampling is commonly used in the EEG processing task as it can reduce the data time points and save up computational power [ 30 , 33 , 78 ]. Also, downsampling can free up memories due to lesser time points, making this method portable and less costly to implement.…”

Section: Methodsmentioning

confidence: 99%

“…Also, Brink et al [ 30 ] presented a task-free based EEG approach that makes used of the Naive Bayes classifier to detect severe TBI. A notch filter was applied to the raw EEG to remove the electrical line noises.…”

Section: Introductionmentioning

confidence: 99%

“…The cleaned EEG of each subject was segmented into two-seconds segments. The relation between the log-transformed orthogonalized amplitude from three frequency bands, which are the theta, delta, and gamma bands, is determined [ 30 ]. Their approach can detect severe TBI and has shown good detection accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Classification of Non-Severe Traumatic Brain Injury from Resting-State EEG Signal Using LSTM Network with ECOC-SVM

Lai

Ibrahim

Hamid

et al. 2020

Sensors

View full text Add to dashboard Cite

Traumatic brain injury (TBI) is one of the common injuries when the human head receives an impact due to an accident or fall and is one of the most frequently submitted insurance claims. However, it is often always misused when individuals attempt an insurance fraud claim by providing false medical conditions. Therefore, there is a need for an instant brain condition classification system. This study presents a novel classification architecture that can classify non-severe TBI patients and healthy subjects employing resting-state electroencephalogram (EEG) as the input, solving the immobility issue of the computed tomography (CT) scan and magnetic resonance imaging (MRI). The proposed architecture makes use of long short term memory (LSTM) and error-correcting output coding support vector machine (ECOC-SVM) to perform multiclass classification. The pre-processed EEG time series are supplied to the network by each time step, where important information from the previous time step will be remembered by the LSTM cell. Activations from the LSTM cell is used to train an ECOC-SVM. The temporal advantages of the EEG were amplified and able to achieve a classification accuracy of 100%. The proposed method was compared to existing works in the literature, and it is shown that the proposed method is superior in terms of classification accuracy, sensitivity, specificity, and precision.

show abstract

Section: Resultsmentioning

confidence: 99%