Article
Computer Science, Artificial Intelligence
R. Elakkiya
Summary: Epilepsy is a common chronic neurological disorder, and using EEG signals for processing can improve the accuracy of seizure detection in neonates. The proposed CNN model showed high accuracy in predicting epileptic seizures in neonates, outperforming existing models.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Artur Gramacki, Jaroslaw Gramacki
Summary: Electroencephalogram (EEG) is a main diagnostic test for epilepsy, but manual detection is time-consuming and challenging. This research fills the gap in the field of automated seizure detection by providing a complete framework using DL approaches and sharing the corresponding codes and results.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Jian Liu, Yipeng Du, Xiang Wang, Wuguang Yue, Jim Feng
Summary: In this paper, the possibility of using Automated Machine Learning (AutoML) for epilepsy EEG detection is explored. The neural architecture search (NAS) algorithm is applied to design a model for epilepsy EEG analysis, and feature interpretability methods are used to ensure the reliability of the searched model. Experimental results show that the NAS-based model outperforms the baseline model, improving classification accuracy, F1-score, and Cohen's kappa coefficient. Furthermore, the NAS-based model is capable of extracting EEG features related to seizures for classification.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Review
Health Care Sciences & Services
J. Prasanna, M. S. P. Subathra, Mazin Abed Mohammed, Robertas Damasevicius, Nanjappan Jothiraj Sairamya, S. Thomas George
Summary: This review paper focuses on automatic seizure detection in pediatric patients using EEG signals and classifiers. It summarizes the application of personalized medicine approaches in the diagnosis of epilepsy, analyzes challenges and performance metrics using data from the CHB-MIT database.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Engineering, Multidisciplinary
Jose Escorcia-Gutierrez, Kelvin Beleno, Javier Jimenez-Cabas, Mohamed Elhoseny, Mohammad Dahman Alshehri, Mahmoud M. Selim
Summary: Recent advancements in machine learning and deep learning models have found them helpful in designing effective complex measurement systems. At the same time, examining the brain's activities using Electroencephalography (EEG) is essential in determining the mental state or thought of a person. This study proposes an Automated Deep Learning-Enabled Brain Signal Classification for Epileptic Seizure Detection (ADLBSC-ESD) technique that aims to classify brain signals to determine the existence of seizures. The proposed technique utilizes the Improved Teaching and Learning-Enabled Optimization (ITLBO) technique for feature selection from EEG signals and the Deep Belief Network (DBN) model for effective classification, with hyperparameters optimized using the Swallow Swarm Optimization Algorithm (SSA). Simulation results show the improved performance of the ADLBSC-ESD technique compared to current state-of-the-art techniques.
Article
Chemistry, Analytical
Gul Hameed Khan, Nadeem Ahmad Khan, Muhammad Awais Bin Altaf, Qammer Abbasi
Summary: This paper proposes a trainable hybrid approach for epileptic seizure detection using a shallow autoencoder (AE) and a conventional classifier. The encoded AE representation is used as a feature vector for classifying EEG signal segments as epileptic or non-epileptic. The algorithm has low computational complexity and can be used in body sensor networks and wearable devices. Experimental results show that the proposed method achieves high accuracy and sensitivity in detecting abnormal seizure activity.
Article
Engineering, Biomedical
Xuyang Zhao, Noboru Yoshida, Tetsuya Ueda, Hidenori Sugano, Toshihisa Tanaka
Summary: This study applies commonly used models such as LeNet, VGG, ResNet, and ViT to the EEG image classification task, and solves the problems of data imbalance and model interpretation through data augmentation and model explanation methods. The models achieve good performance in seizure detection and provide visual and quantitative information for clinical experts in diagnosis.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Clinical Neurology
Una Pale, Tomas Teijeiro, David Atienza
Summary: Long-term monitoring of patients with epilepsy is a challenging problem in engineering. This study proposes a novel semi-supervised learning approach based on multi-centroid HD computing, which shows significantly improved performance in epilepsy detection, especially in cases of data imbalance.
FRONTIERS IN NEUROLOGY
(2022)
Article
Chemistry, Multidisciplinary
Marcin Kolodziej, Andrzej Majkowski, Andrzej Rysz
Summary: This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. It presents standard approaches for analyzing iEEG signals and discusses modern deep learning algorithms. The study shows that CNN and LSTM networks yield significantly better results, and the gradient-weighted class activation mapping algorithm can identify important iEEG signal fragments for seizure detection.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Analytical
Mariam K. Alharthi, Kawthar M. Moria, Daniyal M. Alghazzawi, Haythum O. Tayeb
Summary: The research aims to integrate local EEG signals into the CHB-MIT dataset using a new compatibility framework, achieving high accuracy, precision, and sensitivity with the deep-learning model of 1D-CNN, Bi-LSTM, and attention.
Article
Chemistry, Multidisciplinary
Zakareya Lasefr, Khaled Elleithy, Ramasani Rakesh Reddy, Eman Abdelfattah, Miad Faezipour
Summary: This paper studied epileptic seizure detection methods based on EEG signals and proposed an enhanced technique with a mobile application for monitoring the classification of EEG signals. The proposed method achieved high accuracy and outperformed previous studies. It will have significant impacts in the medical field and Human-Computer Interaction fields.
APPLIED SCIENCES-BASEL
(2023)
Article
Clinical Neurology
Dionisije Sopic, Tomas Teijeiro, David Atienza, Amir Aminifar, Philippe Ryvlin
Summary: The study demonstrates that personalized EEG signatures combined with dynamic time warping can be a promising method for detecting seizures with high sensitivity from a limited number of EEG channels, despite low false alarm rates, high interpretability, and low computational complexity. This method is compatible with future use in wearable devices.
Article
Computer Science, Artificial Intelligence
Yankun Xu, Jie Yang, Wenjie Ming, Shuang Wang, Mohamad Sawan
Summary: The authors propose a deep learning framework for shortening the latency of epileptic seizure detection through probabilistic prediction. They convert the seizure detection task from binary classification to probabilistic prediction and introduce a crossing period and soft labeling rule to improve the accuracy. In experiments, they successfully detect seizures with shorter latency compared to previous studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Engineering, Biomedical
Jingwei Zhang, Christos Chatzichristos, Kaat Vandecasteele, Lauren Swinnen, Victoria Broux, Evy Cleeren, Wim Van Paesschen, Maarten De Vos
Summary: This paper presents an automatic annotation correction approach for training seizure detection algorithms using wearable EEG data. The approach improves the sensitivity and reduces false-positive detections compared to visually corrected and original seizure annotations.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Valentin Gabeff, Tomas Teijeiro, Marina Zapater, Leila Cammoun, Sylvain Rheims, Philippe Ryvlin, David Atienza
Summary: This study addressed the lack of interpretability of neural network models in medical decision support by developing a deep learning model from EEG signals for online detection of epileptic seizures and associating model behavior with expert medical knowledge. The focus was on aggregating classification results, identifying frequency patterns, and recognizing signal waveforms. Results showed that the kernel size in the first layer significantly impacts feature interpretability and model sensitivity.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2021)