Document Detail


Evaluating variable selection methods for diagnosis of myocardial infarction.
MedLine Citation:
PMID:  10566358     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
This paper evaluates the variable selection performed by several machine-learning techniques on a myocardial infarction data set. The focus of this work is to determine which of 43 input variables are considered relevant for prediction of myocardial infarction. The algorithms investigated were logistic regression (with stepwise, forward, and backward selection), backpropagation for multilayer perceptrons (input relevance determination), Bayesian neural networks (automatic relevance determination), and rough sets. An independent method (self-organizing maps) was then used to evaluate and visualize the different subsets of predictor variables. Results show good agreement on some predictors, but also variability among different methods; only one variable was selected by all models.
Authors:
S Dreiseitl; L Ohno-Machado; S Vinterbo
Related Documents :
17024498 - Inhalation of diluted diesel engine emission impacts heart rate variability and arrhyth...
10367588 - Heart-rate variability effects of beta-adrenoceptor agonists (xamoterol, prenalterol, a...
8444498 - Control of pulmonary vasomotility in congestive heart failure.
7898098 - Interactions between the renin-angiotensin system and the parasympathetic nervous syste...
8450518 - Left ventricular cardiac structure and diastolic function in isolated systolic hyperten...
1396808 - Pharmacological stress echocardiography in the diagnosis of coronary artery disease and...
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't; Research Support, U.S. Gov't, P.H.S.    
Journal Detail:
Title:  Proceedings / AMIA ... Annual Symposium. AMIA Symposium     Volume:  -     ISSN:  1531-605X     ISO Abbreviation:  Proc AMIA Symp     Publication Date:  1999  
Date Detail:
Created Date:  2000-02-01     Completed Date:  2000-02-01     Revised Date:  2012-10-09    
Medline Journal Info:
Nlm Unique ID:  100883449     Medline TA:  Proc AMIA Symp     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  246-50     Citation Subset:  IM    
Affiliation:
Harvard Medical School/Massachusetts Institute of Technology, Division of Health Sciences and Technology, Boston, USA. sdreisei@dsg.harvard.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms*
Artificial Intelligence*
Chest Pain / etiology
Diagnosis, Computer-Assisted
Evaluation Studies as Topic
Humans
Logistic Models
Mathematics
Myocardial Infarction / diagnosis*
Neural Networks (Computer)
Grant Support
ID/Acronym/Agency:
467-MZ-802289//PHS HHS; R01 LM006538/LM/NLM NIH HHS; R29 LM06538-01/LM/NLM NIH HHS
Comments/Corrections

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


Previous Document:  Providing a complete online multimedia patient record.
Next Document:  Efficacy of computerized decision support for mechanical ventilation: results of a prospective multi...