A Two-Layer LSTM Deep Learning Model for Epileptic Seizure Prediction

Varnosfaderani, Shiva Maleki; Rahman, Rihat; Sarhan, Nabil J.; Kuhlmann, Levin; Asano, Eishi; Luat, Aimee F.; Alhawari, Mohammad

doi:10.1109/aicas51828.2021.9458539

Cited by 14 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data was collected from three adult human subjects, all females, who had epilepsy surgery before the clinical trial. We compare the prediction performance of our MViT approach with the top winning teams of the Kaggle competition [ 33 ] as well as baseline machine learning methods [ 15 , 16 , 29 , 61 , 62 , 63 , 64 ]. In [ 15 ], Cook and his team successfully implanted the first-in-man seizure advisory system in several patients with drug-resistant epilepsy.…”

Section: Resultsmentioning

confidence: 99%

“…However, the results from [ 61 ] are based on the model trained and tested on individual subjects, and the generalizability of CNNs trained on raw EEG signals needs to be validated in future studies. Varnosfaderani et al [ 64 ] reported a higher AUC score of 0.920 using a two-layer LSTM network. The authors first extracted hand-crafted features including temporal features (e.g., mean, variance, and peak-to-peak values) and spectral features (e.g., spectral power in eight canonical EEG frequency bands) from the EEG signals and used them as inputs to the LSTM network.…”

Section: Resultsmentioning

confidence: 99%

“…This ensemble approach, however, failed to improve the prediction performance, achieving an average AUC score of 0.815 on the public test set. [33] distribution statistics, and spectral power randomized trees GarethJones [33] 2018 Distribution statistics, spectral power, SVM -0.815/0.797 signal RMS, correlation, and spectral edge tree ensemble QingnanTang [33] 2018 Spectral power, spectral entropy Gradient boosting, -0.854/0.791 correlation, and spectral edge power SVM Nullset [33] 2018 Hjorth parameters, spectral power, Random Forest, -0.844/0.746 spectral edge, spectral entropy, adaptive boosting, Shannon entropy , and fractal dimensions and gradient boosting Reuben et al [63] 2019 Preictal probabilities from MLP -0.815/the top 8 teams in [33] Varnosfaderani et al [64] Two recent studies [29,61] achieved improved AUC scores (Table 3) by training CNNs on time-frequency features [29] and raw EEG signals [61], respectively. The promising results of the two studies were obtained using considerably different forms of the inputs, which demonstrates the versatility of CNNs in the seizure prediction task.…”

Section: Mvit Prediction Performance On Invasive Human Eegmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Channel Vision Transformer for Epileptic Seizure Prediction

2022

View full text Add to dashboard Cite

Epilepsy is a neurological disorder that causes recurrent seizures and sometimes loss of awareness. Around 30% of epileptic patients continue to have seizures despite taking anti-seizure medication. The ability to predict the future occurrence of seizures would enable the patients to take precautions against probable injuries and administer timely treatment to abort or control impending seizures. In this study, we introduce a Transformer-based approach called Multi-channel Vision Transformer (MViT) for automated and simultaneous learning of the spatio-temporal-spectral features in multi-channel EEG data. Continuous wavelet transform, a simple yet efficient pre-processing approach, is first used for turning the time-series EEG signals into image-like time-frequency representations named Scalograms. Each scalogram is split into a sequence of fixed-size non-overlapping patches, which are then fed as inputs to the MViT for EEG classification. Extensive experiments on three benchmark EEG datasets demonstrate the superiority of the proposed MViT algorithm over the state-of-the-art seizure prediction methods, achieving an average prediction sensitivity of 99.80% for surface EEG and 90.28–91.15% for invasive EEG data.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Mvit Prediction Performance On Invasive Human Eegmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Channel Vision Transformer for Epileptic Seizure Prediction

2022

View full text Add to dashboard Cite

show abstract

“…Moreover, we also compare the performance of these DL methods to a deep convolutional network structure that is known to generalize well on raw EEG signals [53] and EEGNet [54] by training those models on the available seizure data. In addition, state-of-the-art algorithms [55,56] that were tested on the kaggle dataset are compared with the obtained results. The results of overall, public, and private AUC, as well as FPR, accuracy and sensitivity are summarized in Table 6.…”

Section: Comparison To Other DL Algorithmsmentioning

confidence: 99%

“…Compared with models that process raw input data such as EEGNet, ConvNet, CNN, and LSTM, the model shows the best AUC and follows LSTM in sensitivity (70%). The work [55,56] uses scalogram, spectrogram, time, and frequency domain features to be fed into DL algorithms. The results show promising public AUC, with the highest being 0.92, when using time and frequency domain features with a two-layer LSTM network.…”

Section: Comparison To Other DL Algorithmsmentioning

confidence: 99%

General and patient-specific seizure classification using deep neural networks

Massoud

Abdelzaher

Kuhlmann

et al. 2023

Analog Integr Circ Sig Process

Self Cite

View full text Add to dashboard Cite

Seizure prediction algorithms have been central in the field of data analysis for the improvement of epileptic patients’ lives. The most recent advancements of which include the use of deep neural networks to present an optimized, accurate seizure prediction system. This work puts forth deep learning methods to automate the process of epileptic seizure detection with electroencephalogram (EEG) signals as input; both a patient-specific and general approach are followed. EEG signals are time structure series motivating the use of sequence algorithms such as temporal convolutional neural networks (TCNNs), and long short-term memory networks. We then compare this methodology to other prior pre-implemented structures, including our previous work for seizure prediction using machine learning approaches support vector machine and random under-sampling boost. Moreover, patient-specific and general seizure prediction approaches are used to evaluate the performance of the best algorithms. Area under curve (AUC) is used to select the best performing algorithm to account for the imbalanced dataset. The presented TCNN model showed the best patient-specific results than that of the general approach with, AUC of 0.73, while ML model had the best results for general classification with AUC of 0.75.

show abstract

An End-To-End Seizure Prediction Method Using Convolutional Neural Network and Transformer

Wang,

Zhao

2024

IFMBE Proceedings

View full text Add to dashboard Cite

A Two-Layer LSTM Deep Learning Model for Epileptic Seizure Prediction

Cited by 14 publications

References 16 publications

Multi-Channel Vision Transformer for Epileptic Seizure Prediction

Multi-Channel Vision Transformer for Epileptic Seizure Prediction

General and patient-specific seizure classification using deep neural networks

An End-To-End Seizure Prediction Method Using Convolutional Neural Network and Transformer

Contact Info

Product

Resources

About