Article
Biology
Karoliina T. Tapani, Paivi Nevalainen, Sampsa Vanhatalo, Nathan J. Stevenson
Summary: Neonatal seizure detection algorithms (SDA) are approaching human equivalence and provide a clinically relevant interpretation of the EEG.
COMPUTERS IN BIOLOGY AND MEDICINE
(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)
Article
Behavioral Sciences
Sheng Wong, Anj Simmons, Jessica Rivera-Villicana, Scott Barnett, Shobi Sivathamboo, Piero Perucca, Patrick Kwan, Levin Kuhlmann, Rajesh Vasa, Terence J. O'Brien
Summary: Diagnosing and managing seizures is challenging for clinicians, and the adoption of automated seizure detection using machine learning technology is limited. Our survey of medical professionals reveals that the main barriers for usage of seizure detection tools in clinical practice are availability, lack of training, and the blackbox nature of ML algorithms.
EPILEPSY & BEHAVIOR
(2023)
Article
Engineering, Electrical & Electronic
Julien Lesouple, Cedric Baudoin, Marc Spigai, Jean-Yves Tourneret
Summary: This paper introduces a semi-supervised anomaly detector based on support vector machines that combines the advantages of existing supervised and unsupervised support vector machine algorithms. The algorithm allows for control over the maximum proportion of vectors detected as anomalies and errors in supervised data through two hyperparameters. Simulations on various benchmark datasets demonstrate the effectiveness of the proposed semi-supervised anomaly detection method.
Article
Computer Science, Artificial Intelligence
Quanhong Wang, Weizhuang Kong, Jitao Zhong, Zhengyang Shan, Juan Wang, Xiaowei Li, Hong Peng, Bin Hu
Summary: In this paper, a novel classification algorithm called SVM-KSRC is proposed for automatic epilepsy detection based on electroencephalography (EEG). The algorithm combines support vector machine (SVM) and kernel sparse representation classification (KSRC) to classify EEG signals. Experimental results show that SVM-KSRC outperforms existing machine learning methods in epilepsy detection.
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
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, Artificial Intelligence
Chen Ding, Tian-Yi Bao, He-Liang Huang
Summary: The study proposes a quantum-inspired classical algorithm for LS-SVM, utilizing an improved sampling technique for classification. The theoretical analysis indicates that the algorithm can achieve classification with logarithmic runtime for low-rank, low-condition number, and high-dimensional data matrices.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Biology
Rishabh Bajpai, Rajamanickam Yuvaraj, A. Amalin Prince
Summary: The study introduces an automated system for detecting brain EEG pathology by converting EEG signals into image domain using time-frequency spectrum, utilizing Convolutional Neural Networks and Support Vector Machines for feature extraction and classification. It achieved high accuracy and specificity, providing clinicians with a diagnostic tool for early detection of EEG pathology.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Computer Science, Artificial Intelligence
Liming Liu, Maoxiang Chu, Rongfen Gong, Li Zhang
Summary: The improved nonparallel support vector machine (INPSVM) proposed in this article inherits the advantages of nonparallel support vector machine (NPSVM) while also offering incomparable benefits over twin support vector machine (TSVM). INPSVM effectively eliminates noise effects and achieves higher classification accuracy for both linear and nonlinear datasets compared to other algorithms. Experimental results demonstrate the superior efficiency, accuracy, and robustness of INPSVM.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
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
Automation & Control Systems
Jingxuan Pang, Xiaokun Pu, Chunguang Li
Summary: Anomaly detection plays a crucial role in industry for maintaining system safety and ensuring product quality. This article introduces a hybrid algorithm, VQ-OCSVM, which combines vector quantization and OCSVM to address the challenges faced by OCSVM in kernel parameter selection and handling complex data distributions. The proposed method effectively bypasses the kernel parameter selection problem and integrates generative and discriminative learning for better generalization capacity. Experimental results demonstrate the effectiveness and advantages of the proposed method.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Gaetano Zazzaro, Luigi Pavone
Summary: This study evaluated the performance of a seizure detection method using EEG signals, and found that the method performed very well in detecting seizures in one patient and achieved good performance in six other patients from the same dataset.
Article
Computer Science, Information Systems
Chima S. Eke, Emmanuel Jammeh, Xinzhong Li, Camille Carroll, Stephen Pearson, Emmanuel Ifeachor
Summary: The successful development of amyloid-based biomarkers and tests for Alzheimer's disease is an important milestone in AD diagnosis. However, limitations exist in providing limited information about the disease process and inability to detect individuals before significant amyloid-beta accumulation. This study aims to identify potential blood-based non-amyloid biomarkers for early AD detection, utilizing machine learning techniques to identify 5 novel panels of non-amyloid proteins that may serve as key biomarkers of early disease with high sensitivity and specificity.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Matteo Avolio, Antonio Fuduli
Summary: This paper introduces a novel approach for binary multiple instance learning classification, combining the strengths of SVM and PSVM, aiming to discriminate between positive and negative instances by generating a hyperplane placed in the middle between two parallel hyperplanes.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Clinical Neurology
Soraia Ventura, Sean R. Mathieson, John M. O'Toole, Vicki Livingstone, Mary-Anne Ryan, Geraldine B. Boylan
Summary: The study aimed to characterize sleep features in 4-5 month old infants, providing normative values for sleep macrostructure and sleep spindles. Sex differences were observed in spindle spectral power and brain symmetry index, with males showing lower power and higher symmetry index compared to females. These findings contribute to a better understanding of infant sleep patterns and potential biomarkers for brain maturation.
Editorial Material
Clinical Neurology
Ronit M. Pressler, Geraldine B. Boylan
Editorial Material
Pediatrics
Sampsa Vanhatalo, Nathan J. Stevenson, Ronit M. Pressler, Nicholas S. Abend, Stephane Auvin, Francesco Brigo, M. Roberta Cilio, Cecil D. Hahn, Hans Hartmann, Lena Hellstrom-Westas, Terrie E. Inder, Solomon L. Moshe, Magda L. Nunes, Renee A. Shellhaas, Kollencheri P. Vinayan, Linda S. de Vries, Jo M. Wilmshurst, Elissa Yozawitz, Geraldine B. Boylan
Summary: Brain monitoring plays a crucial role in neonatal neurocritical care, but recent research failed to prove its effectiveness in seizure treatment.
PEDIATRIC RESEARCH
(2023)
Review
Pediatrics
Antoine Giraud, Carol M. Stephens, Geraldine B. Boylan, Brian H. Walsh
Summary: This study aimed to summarise the association between perinatal inflammation exposure and electroencephalography (EEG) features in preterm infants. The results showed that perinatal inflammation exposure was associated with a decrease in amplitude and a reduced incidence of sleep-wake cycling patterns.
PEDIATRIC RESEARCH
(2022)
Editorial Material
Pediatrics
Antoine Giraud, Carol M. Stephens, Geraldine B. Boylan, Brian H. Walsh
PEDIATRIC RESEARCH
(2023)
Article
Clinical Neurology
Andreea M. Pavel, John M. O'Toole, Jacopo Proietti, Vicki Livingstone, Subhabrata Mitra, William P. Marnane, Mikael Finder, Eugene M. Dempsey, Deirdre M. Murray, Geraldine B. Boylan, ANSeR Consortium
Summary: The study aimed to assess whether early clinical and electroencephalography (EEG) features can predict seizures in infants with hypoxic-ischemic encephalopathy (HIE). Machine learning models were developed using clinical and EEG parameters to predict infants at high risk of seizures. The results showed that the combination of clinical and EEG analysis can accurately predict seizure development in HIE infants.
Article
Pediatrics
Mary Anne J. Ryan, Sean R. Mathieson, Vicki Livingstone, Marc Paul O'Sullivan, Eugene M. Dempsey, Geraldine B. Boylan
Summary: This prospective observational study examines the nocturnal sleep architecture of healthy moderate to late preterm infants at 36 weeks post menstrual age. The study finds that sleep state architecture is dependent on birth GA, with infants born at lower GA having less active sleep and more quiet sleep. These findings may have implications for the neurodevelopment of the infants.
PEDIATRIC RESEARCH
(2023)
Review
Pediatrics
Mohamed El-Dib, Nicholas S. J. Abend, Topun Austin, Geraldine Boylan, Valerie Chock, M. Roberta Cilio, Gorm Greisen, Lena Hellstroem-Westas, Petra Lemmers, Adelina Pellicer, Ronit Pressler, Arnold Sansevere, Tammy Tsuchida, Sampsa Vanhatalo, Courtney J. Wusthoff
Summary: The development of neonatal neurocritical care in the past decade has shown significant progress in neuromonitoring and neuroprotection. Commonly used brain monitoring tools in the neonatal intensive care unit (NICU) include amplitude integrated EEG (aEEG), full multichannel continuous EEG (cEEG), and near-infrared spectroscopy (NIRS). However, there is no consensus on the consistent and efficient use of these modalities in common NICU scenarios. This review summarizes current evidence for the best utilization of neuromonitoring modalities in neonates with encephalopathy or possible seizures.
PEDIATRIC RESEARCH
(2023)
Review
Pediatrics
Mohamed El-Dib, Nicholas S. Abend, Topun Austin, Geraldine Boylan, Valerie Chock, M. Roberta Cilio, Gorm Greisen, Lena Hellstrom-Westas, Petra Lemmers, Adelina Pellicer, Ronit M. Pressler, Arnold Sansevere, Eniko Szakmar, Tammy Tsuchida, Sampsa Vanhatalo, Courtney J. Wusthoff
Summary: Neonatal intensive care has shifted focus from cardiorespiratory care to a holistic approach that emphasizes brain health. The most commonly used tools in the neonatal intensive care unit (NICU) to monitor brain function and physiology are amplitude-integrated EEG, full multichannel continuous EEG, and near-infrared spectroscopy. Each of these tools has unique characteristics and functions, but there is no consensus on the optimal approach to neuromonitoring in the NICU. This review examines current evidence to guide the use of these neuromonitoring tools for neuroprotective care in extremely premature infants and critically ill neonates.
PEDIATRIC RESEARCH
(2023)
Review
Public, Environmental & Occupational Health
Sonia Marie Lenehan, Leanna Fogarty, Cathal O'Connor, Sean Mathieson, Geraldine B. Boylan
Summary: This review investigates the development of early childhood sleep and its association with neurodevelopment. Results show changes in sleep architecture during the first two years, with sleep playing a critical role in memory, learning, and socio-emotional development. Future studies should focus on sleep architecture at each month of life, especially during periods of rapid neurodevelopment between 7-24 months.
MATERNAL AND CHILD HEALTH JOURNAL
(2023)
Article
Computer Science, Information Systems
Duc-Minh Ngo, Dominic Lightbody, Andriy Temko, Cuong Pham-Quoc, Ngoc-Thinh Tran, Colin C. C. Murphy, Emanuel Popovici
Summary: This study proposes a hardware-based framework for network intrusion detection using lightweight artificial neural network models. Anomaly-based intrusion detection systems using machine learning have gained popularity due to their ability to detect unseen attacks, but deploying them on IoT devices is computationally expensive. This paper presents a high-performance and ultra-low power consumption framework that achieves high accuracy and faster inference compared to traditional hardware.
Article
Pediatrics
Marc Paul O. Sullivan, Vicki Livingstone, Irina Korotchikova, Eugene M. Dempsey, Deirdre M. Murray, Geraldine B. Boylan
Summary: Unconditional reference centiles for sleep parameters were established in infants 4-16 weeks of age based on data from a randomized controlled trial. The results showed that total sleep duration in a 24-hour period, night-time sleep duration in a 12-hour period, and longest sleep episode duration increased from 4 to 16 weeks, while daytime sleep duration in a 12-hour period decreased.
ARCHIVES OF DISEASE IN CHILDHOOD
(2023)
Article
Clinical Neurology
Soraia Ventura, Sean R. Mathieson, Marc P. O'Sullivan, John M. O'Toole, Vicki Livingstone, Ronit M. Pressler, Eugene M. Dempsey, Deirdre M. Murray, Geraldine B. Boylan
Summary: The study aims to examine the impact of parent-led massage on the sleep electroencephalogram (EEG) features of typically developing term-born infants at 4 months. The results show that parent-led massage is associated with distinct functional brain changes in the sleep EEG at 4 months.
DEVELOPMENTAL MEDICINE AND CHILD NEUROLOGY
(2023)
Article
Multidisciplinary Sciences
John M. M. O'Toole, Sean R. R. Mathieson, Sumit A. A. Raurale, Fabio Magarelli, William P. P. Marnane, Gordon Lightbody, Geraldine B. B. Boylan
Summary: This report presents a dataset of neonatal electroencephalogram (EEG) recordings graded based on the severity of abnormalities in the background pattern. The dataset includes 169 hours of multi-channel EEG from 53 neonates diagnosed with hypoxic-ischaemic encephalopathy (HIE). The grading system assesses attributes such as amplitude, continuity, sleep-wake cycling, symmetry and synchrony, and abnormal waveforms to categorize the background severity into 4 grades. The dataset can be used for reference, training, and algorithm development for neonatal EEG with HIE.
Article
Allergy
Cathal O'Connor, Vicki Livingstone, Jonathan O'B Hourihane, Alan D. Irvine, Geraldine Boylan, Deirdre Murray
Summary: This large birth cohort study examined the relationship between emollient bathing at 2 months and the trajectory of atopic dermatitis (AD) in the first 2 years of life. The results showed that infants who had emollient baths at 2 months had a higher prevalence of AD, suggesting that early use of emollients may increase the risk of AD.
PEDIATRIC ALLERGY AND IMMUNOLOGY
(2023)
Article
Clinical Neurology
Jaakko Vallinoja, Timo Nurmi, Julia Jaatela, Vincent Wens, Mathieu Bourguignon, Helena Maenpaa, Harri Piitulainen
Summary: The study aimed to assess the effects of lesions related to spastic diplegic cerebral palsy on functional connectivity. Using multiple imaging modalities, the researchers found enhanced functional connectivity in the sensorimotor network of individuals with spastic diplegic cerebral palsy, which was not correlated with hand coordination performance.
CLINICAL NEUROPHYSIOLOGY
(2024)
Article
Clinical Neurology
Francesca Ginatempo, Nicola Loi, John C. Rothwell, Franca Deriu
Summary: This study comprehensively investigated sensorimotor integration in the cranial-cervical muscles of healthy adults and found that the integration of sensory inputs with motor output is profoundly influenced by the type of sensory afferent involved and the functional role played by the target muscle.
CLINICAL NEUROPHYSIOLOGY
(2024)
