In this paper, we study machine learning techniques and features of electroencephalography activity bursts for predicting outcome in extremely preterm infants. It was previously shown that the distribution of interburst interval durations predicts clinical outcome, but in previous work the information within the bursts has been neglected. In this paper, we perform exploratory analysis of feature extraction of burst characteristics and use machine learning techniques to show that such features could be used for outcome prediction. The results are promising, but further verification in larger datasets is needed to obtain conclusive results.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2013.6610495 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Assessment of interfacial properties in a two-layered plate using quasi-static component generation during primary Lamb wave propagation.
Ultrasonics
January 2025
College of Aerospace Engineering, Chongqing University, Chongqing 400044, China. Electronic address:
This study delves into the feasibility of leveraging quasi-static component (QSC) generation during primary Lamb wave propagation to discern subtle alterations in the interfacial properties of a two-layered plate. Unlike the second-harmonic generation of Lamb waves, QSC generation doesn't necessitate precise phase-velocity matching but rather requires an approximate matching of group velocities to ensure the emergence of cumulative growth effects. This unique characteristic empowers the QSC-based nonlinear ultrasonic method to effectively surmount the limitations associated with inherent dispersion and multimode traits of Lamb wave propagation.
View Article and Find Full Text PDFBibliometric Analysis of Neuroinflammation and Postoperative Cognitive Dysfunction.
Brain Behav
January 2025
Department of Anesthesiology, the Second Hospital, Cheeloo College of Medicine, Shandong University, Jinan, People's Republic of China.
Background: The occurrence and development of postoperative cognitive dysfunction (POCD) are closely linked to neuroinflammation. This bibliometric analysis aims to provide novel insights into the research trajectory, key research topics, and potential future development trends in the field of neuroinflammation-induced POCD.
Methods: The Web of Science Core Collection (WoSCC) database was searched to identify publications from 2012 to 2023 on neuroinflammation-induced POCD.
The trait-specific timing of accelerated genomic change in the human lineage.
Cell Genom
January 2025
Department of Integrative Biology, The University of Texas at Austin, Austin, TX, USA; Department of Statistics and Data Science, The University of Texas at Austin, Austin, TX, USA. Electronic address:
Humans exhibit distinct characteristics compared to our primate and ancient hominin ancestors. To investigate genomic bursts in the evolution of these traits, we use two complementary approaches to examine enrichment among genome-wide association study loci spanning diseases and AI-based image-derived brain, heart, and skeletal tissue phenotypes with genomic regions reflecting four evolutionary divergence points. These regions cover epigenetic differences among humans and rhesus macaques, human accelerated regions (HARs), ancient selective sweeps, and Neanderthal-introgressed alleles.
View Article and Find Full Text PDFDeveloping an EEG-based model to predict awakening after cardiac arrest using partial processing with the BIS Engine.
Anesthesiology
January 2025
Department of Anesthesiology, Brigham and Women's Hospital and Harvard Medical School, Boston MA, USA.
Introduction: Accurate prognostication in comatose survivors of cardiac arrest is a challenging and high-stakes endeavor. We sought to determine whether internal EEG subparameters extracted by the Bispectral Index (BIS) monitor, a device commonly used to estimate depth-of-anesthesia intraoperatively, could be repurposed to predict recovery of consciousness after cardiac arrest.
Methods: In this retrospective cohort study, we trained a 3-layer neural network to predict recovery of consciousness to the point of command following versus not based on 48 hours of continuous EEG recordings in 315 comatose patients admitted to a single US academic medical center after cardiac arrest (Derivation cohort: N=181; Validation cohort: N=134).
Myoclonus After Cardiac Arrest: Need for Standardization-A Systematic Review and Research Proposal on Terminology.
Crit Care Med
November 2024
Department of Neurology, Neurocritical Care and Neurorehabilitation, Christian Doppler University Hospital, Paracelsus Medical University, Member of the European Reference Network EpiCARE, Salzburg, Austria.
Objectives: Although myoclonus less than or equal to 72 hours after cardiac arrest (CA) is often viewed as a single entity, there is considerable heterogeneity in its clinical and electrophysiology characteristics, and its strength of association with outcome. We reviewed definitions, electroencephalogram, and outcome of myoclonus post-CA to assess the need for consensus and the potential role of electroencephalogram for further research.
Data Sources: PubMed, Embase, and Cochrane databases.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!