Document Detail


Automating the analysis of EEG recordings from prematurely-born infants: a Bayesian approach.
MedLine Citation:
PMID:  23014143     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
OBJECTIVE: To implement an automated analysis of EEG recordings from prematurely-born infants and thus provide objective, reproducible results.
METHODS: Bayesian probability theory is employed to compute the posterior probability for developmental features of interest in EEG recordings. Currently, these features include smooth delta waves (0.5-1.5Hz, >100μV), delta brushes (delta portion: 0.5-1.5Hz, >100μV; "brush" portion: 8-22Hz, <75μV), and interburst intervals (<10μV), though the approach taken can be generalized to identify other EEG features of interest.
RESULTS: When compared with experienced electroencephalographers, the algorithm had a true positive rate between 72% and 79% for the identification of delta waves (smooth or "brush") and interburst intervals, which is comparable to the inter-rater reliability. When distinguishing between smooth delta waves and delta brushes, the algorithm's true positive rate was between 53% and 88%, which is slightly less than the inter-rater reliability.
CONCLUSION: Bayesian probability theory can be employed to consistently identify features of EEG recordings from premature infants.
SIGNIFICANCE: The identification of features in EEG recordings provides a first step towards the automated analysis of EEG recordings from premature infants.
Authors:
Timothy J Mitchell; Jeffrey J Neil; John M Zempel; Liu Lin Thio; Terrie E Inder; G Larry Bretthorst
Related Documents :
23598123 - Synthesis and characterization of hapten-quantum dots bioconjugates: application to dev...
22653463 - Petechiae/purpura in well-appearing infants.
2289543 - Variations in fertility by marital status and marriage order.
Publication Detail:
Type:  Journal Article; Research Support, N.I.H., Extramural     Date:  2012-09-24
Journal Detail:
Title:  Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology     Volume:  124     ISSN:  1872-8952     ISO Abbreviation:  Clin Neurophysiol     Publication Date:  2013 Mar 
Date Detail:
Created Date:  2013-02-08     Completed Date:  2013-04-02     Revised Date:  2014-09-03    
Medline Journal Info:
Nlm Unique ID:  100883319     Medline TA:  Clin Neurophysiol     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  452-61     Citation Subset:  IM    
Copyright Information:
Copyright © 2012 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Bayes Theorem
Electroencephalography / methods*
Humans
Infant, Newborn
Infant, Premature / physiology*
Reproducibility of Results
Signal Processing, Computer-Assisted*
Grant Support
ID/Acronym/Agency:
P30 HD062171/HD/NICHD NIH HHS; P30HD062171/HD/NICHD NIH HHS; R01 HD057098/HD/NICHD NIH HHS; R01HD057098/HD/NICHD NIH HHS
Comments/Corrections

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Physical exercise during pregnancy: a systematic review.
Next Document:  Thermoelectric properties of HfN/ScN metal/semiconductor superlattices: a first-principles study.