Document Detail


Predicting high-risk preterm birth using artificial neural networks.
MedLine Citation:
PMID:  16871723     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
A reengineered approach to the early prediction of preterm birth is presented as a complimentary technique to the current procedure of using costly and invasive clinical testing on high-risk maternal populations. Artificial neural networks (ANNs) are employed as a screening tool for preterm birth on a heterogeneous maternal population; risk estimations use obstetrical variables available to physicians before 23 weeks gestation. The objective was to assess if ANNs have a potential use in obstetrical outcome estimations in low-risk maternal populations. The back-propagation feedforward ANN was trained and tested on cases with eight input variables describing the patient's obstetrical history; the output variables were: 1) preterm birth; 2) high-risk preterm birth; and 3) a refined high-risk preterm birth outcome excluding all cases where resuscitation was delivered in the form of free flow oxygen. Artificial training sets were created to increase the distribution of the underrepresented class to 20%. Training on the refined high-risk preterm birth model increased the network's sensitivity to 54.8%, compared to just over 20% for the nonartificially distributed preterm birth model.
Authors:
Christina Catley; Monique Frize; C Robin Walker; Dorina C Petriu
Related Documents :
844353 - Caregiving behaviors and early cognitive development as related to ordinal position in ...
10759153 - Effects of prematurity on arousal from sleep in the newborn infant.
656873 - When and why are babies weaned?
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society     Volume:  10     ISSN:  1089-7771     ISO Abbreviation:  IEEE Trans Inf Technol Biomed     Publication Date:  2006 Jul 
Date Detail:
Created Date:  2006-07-28     Completed Date:  2006-09-05     Revised Date:  2006-11-15    
Medline Journal Info:
Nlm Unique ID:  9712259     Medline TA:  IEEE Trans Inf Technol Biomed     Country:  United States    
Other Details:
Languages:  eng     Pagination:  540-9     Citation Subset:  IM    
Affiliation:
Systems and Computer Engineering Department, Carleton University, Ottawa, ON, Canada. ccatley@ieee.org
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Artificial Intelligence
Canada / epidemiology
Decision Support Systems, Clinical*
Diagnosis, Computer-Assisted / methods*
Humans
Incidence
Infant, Newborn
Nerve Net*
Outcome Assessment (Health Care) / methods*
Pattern Recognition, Automated / methods
Perinatal Care / methods
Premature Birth / diagnosis*,  epidemiology*
Reproducibility of Results
Risk Assessment / methods*
Risk Factors
Sensitivity and Specificity

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


Previous Document:  Local dimensionality reduction and supervised learning within natural clusters for biomedical data a...
Next Document:  Biological data warehousing system for identifying transcriptional regulatory sites from gene expres...