Is Using Threshold-Crossing Method and Single Type of Features Sufficient to Achieve Realistic Application of Seizure Prediction?

Yang, Zheng; Wang, Gang; Wang, Jue

doi:10.1177/1550059415588658

Cited by 6 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, multiple features may lead to lower time efficiency. For example, Zheng's study showed that the combination of phase synchronization and spectral power features is unnecessary due to increased computation complexity (Zheng et al, 2016 ). That is, multiple features may not always be necessary.…”

Section: Discussionmentioning

confidence: 99%

Epileptic Seizure Prediction Based on Permutation Entropy

Yang

Zhou

Niu

et al. 2018

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Epilepsy is a chronic non-communicable disorder of the brain that affects individuals of all ages. It is caused by a sudden abnormal discharge of brain neurons leading to temporary dysfunction. In this regard, if seizures could be predicted a reasonable period of time before their occurrence, epilepsy patients could take precautions against them and improve their safety and quality of life. However, the potential that permutation entropy(PE) can be applied in human epilepsy prediction from intracranial electroencephalogram (iEEG) recordings remains unclear. Here, we described the novel application of PE to track the dynamical changes of human brain activity from iEEG recordings for the epileptic seizure prediction. The iEEG signals of 19 patients were obtained from the Epilepsy Centre at the University Hospital of Freiburg. After preprocessing, PE was extracted in a sliding time window, and a support vector machine (SVM) was employed to discriminate cerebral state. Then a two-step post-processing method was applied for the purpose of prediction. The results showed that we obtained an average sensitivity (SS) of 94% and false prediction rates (FPR) with 0.111 h−1. The best results with SS of 100% and FPR of 0 h−1 were achieved for some patients. The average prediction horizon was 61.93 min, leaving sufficient treatment time before a seizure. These results indicated that applying PE as a feature to extract information and SVM for classification could predict seizures, and the presented method shows great potential in clinical seizure prediction for human.

show abstract

Section: Discussionmentioning

confidence: 99%

Epileptic Seizure Prediction Based on Permutation Entropy

Yang

Zhou

Niu

et al. 2018

Front. Comput. Neurosci.

View full text Add to dashboard Cite

show abstract

“…The diagnosis of a disease can be eventually translated into a classification problem. In this study, in order to verify whether the PSD and non-PSD patients can be distinguished using the extracted brain network characteristics, they were grouped together as the features and the cost-sensitive support vector machine ( Luts et al, 2010 ) was used as the classifier that has been used in our previous studies ( Zheng et al, 2016 ; Zheng and Xu, 2019 ). The classification accuracy defined as the ratio between the number of correctly identified patients and the total number of patients was used as the performance measurement.…”

Section: Methodsmentioning

confidence: 99%

The characteristics of brain network in patient with post-stroke depression under cognitive task condition

Peng,

Zheng,

Yuan

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

ObjectivesPost-stroke depression (PSD) may be associated with the altered brain network property. This study aimed at exploring the brain network characteristics of PSD under the classic cognitive task, i.e., the oddball task, in order to promote our understanding of the pathogenesis and the diagnosis of PSD.MethodsNineteen stroke survivors with PSD and 18 stroke survivors with no PSD (non-PSD) were recruited. The functional near-infrared spectroscopy (fNIRS) covering the dorsolateral prefrontal cortex was recorded during the oddball task state and the resting state. The brain network characteristics were extracted using the graph theory and compared between the PSD and the non-PSD subjects. In addition, the classification performance between the PSD and non-PSD subjects was evaluated using features in the resting and the task state, respectively.ResultsCompared with the resting state, more brain network characteristics in the task state showed significant differences between the PSD and non-PSD groups, resulting in better classification performance. In the task state, the assortativity, clustering coefficient, characteristic path length, and local efficiency of the PSD subjects was larger compared with the non-PSD subjects while the global efficiency of the PSD subjects was smaller than that of the non-PSD subjects.ConclusionThe altered brain network properties associated with PSD in the cognitive task state were more distinct compared with the resting state, and the ability of the brain network to resist attack and transmit information was reduced in PSD patients in the task state.SignificanceThis study demonstrated the feasibility and superiority of investigating brain network properties in the task state for the exploration of the pathogenesis and new diagnosis methods for PSD.

show abstract

“…In the second step (red boxes in figure 4), real-time decomposition was performed, and the firing rates of N MUs were obtained for individual 0.5 s windows with a 0.1 s step, and were substituted into the regression function (4) to estimate the forces. The estimated force was further smoothed with a Kalman filter, which has been demonstrated to eliminate sporadic, isolated, and large-amplitude fluctuations [38].…”

Section: Data Processing 231 Real-time Force Estimationmentioning

confidence: 99%

Real-time isometric finger extension force estimation based on motor unit discharge information

Yang

Hu²

2019

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Objective. The goal of this study was to perform real-time estimation of isometric finger extension force using the discharge information of motor units (MUs). Approach. A real-time electromyogram (EMG) decomposition method based on the fast independent component analysis (FastICA) algorithm was developed to extract MU discharge events from high-density (HD) EMG recordings. The decomposition was first performed offline during an initialization period, and the obtained separation matrix was then applied to new data samples in realtime. Since MU pool discharge probability reflects the neural drive to spinal motoneurons, individual finger forces were estimated based on a firing rate-force model established during the initialization, termed the neural-drive method. The conventional EMG amplitudebased method was used to estimate the forces as a comparison, termed the EMG-amplitude method. Simulated HD-EMG signals were first used to evaluate the accuracy of the real-time decomposition. Experimental EMG recordings of 5 min of isometric finger extension with pseudorandom force levels were used to assess the performance of force estimation over time. Main results. The simulation results showed that the accuracy of real-time decomposition was 86%, compared with an offline accuracy of 94%. However, the real-time decomposition accuracy was stable over time. The experimental results showed that the neural-drive method had a significantly smaller root mean square error (RMSE) of the force estimation compared with the EMG-amplitude method, which was consistent across fingers. Additionally, the RMSE of the neural-drive method was stable until 230 s, while the RMSE of the EMGamplitude method increased progressively over time. Significance. The neural-drive method on real-time finger force estimation was more accurate over time compared with the conventional EMG-amplitude method during prolonged muscle contractions. The outcomes can potentially offer a more accurate and robust neural interface technique for reliable neural-machine interactions based on MU pool discharge information.

show abstract

Is Using Threshold-Crossing Method and Single Type of Features Sufficient to Achieve Realistic Application of Seizure Prediction?

Cited by 6 publications

References 41 publications

Epileptic Seizure Prediction Based on Permutation Entropy

Epileptic Seizure Prediction Based on Permutation Entropy

The characteristics of brain network in patient with post-stroke depression under cognitive task condition

Real-time isometric finger extension force estimation based on motor unit discharge information

Contact Info

Product

Resources

About