End-to-end CNN detects neonatal seizures from raw EEG.
problem Detecting neonatal seizures from raw EEG data.
method Fully convolutional deep neural network for feature extraction and classification.
result Deep architecture achieves comparable accuracy to SVM-based detectors.
Deep CNN architectures improve neonatal seizure detection accuracy.
problem Improving EEG-based neonatal seizure detection accuracy.
method Design and test of deep convolutional networks of varying depths compared to a shallow SVM-based detector.
result A deep 11-layer CNN architecture significantly outperforms shallow architectures, improving AUC90 from 82.6% to 86.8%.
Mobile app for neonatal EEG interpretation helps non-experts diagnose brain health.
problem Limited EEG interpretation skills among neonatal healthcare professionals.
method Low-cost, low-power EEG acquisition system with AI-assisted sonification.
result Improves diagnostic capabilities of non-expert clinicians.
New method identifies key channels for extreme brain events.
problem Identifying channels responsible for extreme brain events like seizures.
method Extends canonical correlation to tail dependence, developing TPDM for clustering.
result Tail connectivity provides additional discriminatory power for seizure risk.
Deep learning detects sleep state fluctuations in neonates from single EEG channel.
problem Monitoring sleep state fluctuations in neonatal intensive care units.
method Deep learning-based algorithm trained on 53 EEG recordings, validated on 30 polysomnography recordings.
result High accuracy (90%) in detecting quiet sleep states from single EEG channel, generalizing well to external dataset.
Paper benchmarks machine learning for multi-class seizure type classification.
problem Accurate classification of seizure types in epileptic patients.
method Used machine learning algorithms on the TUH EEG seizure corpus.
result Achieved weighted F1 scores of up to 0.901 for seizure-wise cross validation. Paper proposes a deep learning method for automatic seizure detection.
problem Manual seizure identification is time-consuming, labor-intensive, and error-prone.
method Leverages attention mechanism and BiLSTM to capture spatial and temporal features.
result Average sensitivity, specificity, and precision of 87.00%, 88.60%, and 88.63% respectively.
Novel IndRNN model improves seizure/non-seizure classification accuracy.
problem Manual EEG analysis by neurologists is laborious and prone to errors.
method Leverages independently recurrent neural networks (IndRNN) to capture seizure features across various time scales.
result The proposed approach outperforms state-of-the-art methods in cross-validation experiments.
Model predicts epileptic seizures with high accuracy using EEG signals.
problem Predicting epileptic seizures with high accuracy for diagnosis and treatment.
method Pearson's product-moment correlation coefficient with a linear classifier on generalized Gaussian modeling.
result 100% effectiveness for sensitivity and specificity greater than 83%.
Efficient binarized algorithm detects seizures from iEEG with one-shot learning.
problem Detecting seizures from iEEG data efficiently and accurately.
method Combines local binary patterns with hyperdimensional computing for end-to-end binary operations.
result Algorithm learns from one or two seizures and generalizes on 27 further seizures.
Deep learning improves automated detection of epileptic seizures.
problem Automated detection of epileptic seizures using traditional methods is limited.
method Deep learning techniques for feature extraction and classification.
result Deep learning enhances accuracy in diagnosing epileptic seizures.
Deep learning helps predict epileptic seizures from EEG data.
problem Challenging prediction of epileptic seizures in medical domain.
method Applied deep learning and machine learning models to EEG data.
result Improved prediction of epileptic seizures.
SeizureNet classifies EEG seizures with high accuracy.
problem Challenges in classifying epileptic seizures due to signal quality and patient variability.
method Deep learning framework using multi-spectral feature embeddings and knowledge distillation.
result SeizureNet achieves high F1 scores for seizure and patient-wise classification.
Neural memory networks improve seizure type classification.
problem Automating the classification of seizure type for clinical and research purposes.
method Introduced a novel approach using neural memory networks (NMNs) enhanced with external memory modules and trainable neural plasticity.
result Achieved a state-of-the-art weighted F1 score of 0.945 for seizure type classification.
Epileptic seizure activity shows complicated dynamics in both space and time. To understand the evolution and propagation of seizures spatially extended sets of data need to be analysed. We have previously described an efficient filtering scheme using variational Laplace that can be used in the Dynamic Causal Modelling…
Convolutional networks predict seizure onset in the preictal phase.
problem Predicting the onset of focal seizures using EEG data.
method Wavelet transformation and convolutional filters to learn features; optimization for prediction horizon.
result A ten-minute prediction horizon for seizure onset.
Model predicts epileptic seizures by detecting preictal state using wavelet transform and PCA.
problem Predicting epileptic seizures before onset.
method Common spatial pattern filtering, wavelet transform for preprocessing, PCA for feature extraction, SVM for classification.
result Average sensitivity of 93.1% for 84 seizures in 23 subjects.
Synthetic learning improves neonatal brain MRI segmentation robustness.
problem Challenges in neonatal brain MRI segmentation due to image contrast and anatomical variations.
method Synthetic learning model trained on few T2-weighted volumes, then enhanced with motion artifacts and over-segmentation.
result Synthetic learning robust to image contrast and improves segmentation of both T1- and T2-weighted images.
Large open EEG seizure corpus created for clinical research.
problem Creating an accurate representation of clinical seizure EEG data.
method Developed a large open EEG seizure corpus, described techniques, and evaluated their effectiveness.
result Presented descriptive statistics on the resulting large open EEG seizure corpus.
Driven by the multi-level structure of human intracranial electroencephalogram (iEEG) recordings of epileptic seizures, we introduce a new variant of a hierarchical Dirichlet Process---the multi-level clustering hierarchical Dirichlet Process (MLC-HDP)---that simultaneously clusters datasets on multiple levels. Our sei…
Model detects epileptic seizures in EEG with high sensitivity.
problem Detecting epileptic seizures in EEG signals.
method Time-series scale mixture model with hidden Markov structure.
result Model outperformed baselines in seizure detection.
Deep learning improves seizure detection in EEGs.
problem Challenges in automated seizure detection in EEGs due to low signal-to-noise ratio and confusion with artifacts.
method Evaluation of hybrid deep structures including Convolutional Neural Networks and Long Short-Term Memory Networks on the TUH EEG Seizure Corpus.
result 30% sensitivity at 7 false alarms per 24 hours using a novel recurrent convolutional architecture.
Path signatures help predict seizures from brain activity.
problem Predicting future seizures from EEG data is challenging.
method Path signature analysis for mapping EEG time series to seizure prediction.
result Path signature method achieves similar results to modern machine learning.
Deep learning models predict epileptic seizures with high accuracy.
problem Predicting epileptic seizures for better patient care.
method Developed Temporal Multi-Channel Transformer (TMC-T) and Vision Transformer (TMC-ViT) models for EEG signals.
result TMC-ViT model outperformed CNN in seizure prediction.
CNN predicts epileptic seizures from iEEG signals.
problem Accurately forecasting epileptic seizures to reduce patient uncertainty.
method Used a CNN for seizure prediction without hand-crafted features.
result CNN models outperformed previous methods on public datasets.
Deep learning model improves EEG seizure classification accuracy.
problem Manual EEG analysis by neurologists is labor-intensive and prone to errors.
method Integrates IndRNN with dense structure and attention mechanism for temporal and spatial feature extraction.
result Average sensitivity, specificity, and precision of 88.80%, 88.60%, and 88.69% on noisy CHB-MIT data set.
Wavelet-based CFC improves EEG seizure classification.
problem Improving accuracy in distinguishing ictal seizures from normal brain activity.
method Wavelet-based cross frequency coupling (CFC) for feature extraction, followed by t-test and QDA for classification.
result Wavelet-based CFC enhances classification accuracy of epileptic EEG signals.
Convolutional neural network detects early seizures with low power microcontroller.
problem Early detection of seizures for patients with severe epilepsy.
method Energy-efficient convolutional neural network designed for implantable microcontrollers.
result Outperforms other detectors with high sensitivity and low false detection rate.
Semi-supervised GAN for seizure prediction using EEG and unlabeled data.
problem Improving seizure prediction accuracy with limited labeled data.
method Generative Adversarial Network (GAN) trained on unlabeled EEG data with data fusion.
result Seizure prediction accuracy of 77.68% and 75.47% on two datasets.
Bidirectional LSTM predicts seizures with 84% accuracy.
problem Predicting seizures for epilepsy patients to prevent drug side effects.
method Trained EEG data from canines on a double Bidirectional LSTM layer.
result AUC of 0.84 on test dataset, significantly better than SVM and GRU networks.
TGCN detects seizures from EEGs with fewer parameters.
problem Automated seizure detection from EEGs is challenging and time-consuming.
method Temporal Graph Convolutional Network (TGCN) that leverages structural information.
result TGCN matches state-of-the-art performance in seizure detection.
Deep neural network improves EEG-based epilepsy diagnosis.
problem Automated identification of seizure onset zones in epilepsy patients.
method Residual deep convolutional neural network trained on raw EEG data.
result State-of-the-art performance on epilepsy classification benchmarks.
Efficiently fine-tunes patient-independent seizure detection models with tensor kernel machine.
problem Improving seizure detection accuracy for wearable devices.
method Transfer learning with tensor kernel machine using canonical polyadic decomposition.
result Patient fine-tuned model achieves high performance with smaller model size.
Bayesian method improves deep learning for noisy EEG seizure detection.
problem Label noise in scalp EEG data hinders deep learning performance.
method Integrates domain knowledge into a Bayesian framework to inform deep learning models of label ambiguities.
result BUNDL enhances robustness of seizure detection systems under noisy label conditions.
New algorithm detects seizures more accurately across subjects.
problem Inter-subject variability in brain signal analysis.
method Clustering covariance matrices on a Riemannian manifold, unsupervised selection of relevant subjects, SVM classifier training.
result Accuracy increased from 86.83% to 89.84% and specificity from 87.38% to 89.64%.
Develops deep neural networks for accurate seizure detection.
problem Seizure detection using EEG signals and brain connectivity.
method Combines EBC, DMNN, MENN, and MFNN methods.
result DMNN achieves highest accuracy (99.43%).
Novel hybrid bilinear model improves epilepsy diagnosis accuracy.
problem Improving accuracy in epilepsy diagnosis and treatment.
method Hybrid bilinear deep learning network using sEEG and audiovisual monitoring.
result Obtained F1-scores of 97.4% and 97.2% on two seizure datasets.
Patients with epilepsy can manifest short, sub-clinical epileptic "bursts" in addition to full-blown clinical seizures. We believe the relationship between these two classes of events---something not previously studied quantitatively---could yield important insights into the nature and intrinsic dynamics of seizures. A…
Convolutional LSTM networks outperform GRU in EEG seizure detection.
problem Seizure detection in EEG signals.
method Comparison of LSTM and GRU units, hybrid CNN-RNN architecture, various initialization and regularization methods.
result Convolutional LSTM networks achieve 30% sensitivity at 6 false alarms per 24 hours.
Optimization models predict cryptocurrency market equilibria under government seizure risk.
problem Determining cryptocurrency market equilibria under government seizure risk.
method Game-theoretic optimization models with utility functions.
result Existence and uniqueness of Nash equilibrium in cryptocurrency markets.
Visual analytics system for comparing medical records using sequence embeddings.
problem Challenges in analyzing medical records due to high dimensionality, irregularity, and sparsity.
method Event and sequence embeddings using autoencoder and self-attention mechanism, with sequence alignment for comparison.
result Demonstrated effectiveness with real-world neonatal ICU dataset.
Method detects critical events in complex systems by learning latent causal structure.
problem Detecting onset of epileptic seizures, customer churn, or pandemics from hidden causal interactions.
method A machine learning method that learns an optimal feature representation from powers of the empirical covariance or precision matrix.
result Proves structural consistency and demonstrates competitive results in seizure and churn prediction.
Develops framework for estimating and improving DTRs with time-varying IV in the presence of unmeasured confounding.
problem Estimating DTRs from observational data with unmeasured confounding.
method Time-varying instrumental variable (IV) framework for estimating and improving DTRs.
result IV-optimal and IV-improved DTRs perform better than DTRs assuming no unmeasured confounding.
Developing a Brain-Computer Interface~(BCI) for seizure prediction can help epileptic patients have a better quality of life. However, there are many difficulties and challenges in developing such a system as a real-life support for patients. Because of the nonstationary nature of EEG signals, normal and seizure patter…
Paper proposes a k-NN classifier for detecting spike-and-wave seizures in EEG.
problem Early detection of epileptic seizures in EEG signals.
method Uses t-location-scale distribution and k-nearest neighbors classifier.
result Demonstrates improved classification accuracy, sensitivity, and specificity on real data.
Machine learning detects epilepsy development from EEG before seizures.
problem Early detection of epilepsy development (epileptogenesis) before seizures.
method Deep CNN combined with prediction aggregation for EEG data analysis.
result Deep learning achieves 99% AUC for EPG detection from EEG recordings.
Graph learning method improves brain state classification.
problem Classifying brain states from iEEG signals.
method Representation learning on graphs for time-varying brain networks.
result 9.13% improvement in AUC for seizure vs. non-seizure classification.
New metrics improve evaluation of EEG event detection algorithms.
problem Lack of standard evaluation metrics for EEG event detection.
method Proposed and demonstrated new metrics: ATWV and TAES.
result Deep learning algorithms need improvement for strict user acceptance.