Document Detail


Using dependency/association rules to find indications for computed tomography in a head trauma dataset.
MedLine Citation:
PMID:  12234717     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Analysis of a clinical head trauma dataset was aided by the use of a new, binary-based data mining technique, termed Boolean analyzer (BA), which finds dependency/association rules. With initial guidance from a domain user or domain expert, the BA algorithm is given one or more metrics to partition the entire dataset. The weighted rules are in the form of Boolean expressions. To augment the analysis of the rules produced, we applied a probabilistic interestingness measure (PIM) to order the generated rules based on event dependency, where events are combinations of primed and unprimed variables. Interpretation of the dependency rules generated on the clinical head trauma data resulted in a set of criteria that identified minor head trauma patients needing computed tomography (CT) scans. The BA criteria contained fewer variables than were found using recursive partitioning of Chi-square values (five variables versus seven variables, respectively). The BA five-variable criteria set was more sensitive but less specific than the seven-variable Chi-square criteria set. We believe that the BA method has broad applicability in the medical domain, and hope that this paper will stimulate other creative applications of the technique.
Authors:
Susan P Imberman; Bernard Domanski; Hilary W Thompson
Related Documents :
21435727 - Staging methods for treatment resistant depression. a systematic review.
21219597 - Estimating spatial accessibility to facilities on the regional scale: an extended commu...
15550577 - Clinical trial design for microarray predictive marker discovery and assessment.
21235017 - Bayesian inference of gene-environment interaction from incomplete data: what happens w...
8241917 - Genes, environment, and addictive behavior: etiology of individual differences and extr...
15878477 - Simulated computerized adaptive tests for measuring functional status were efficient wi...
Publication Detail:
Type:  Journal Article; Research Support, U.S. Gov't, P.H.S.    
Journal Detail:
Title:  Artificial intelligence in medicine     Volume:  26     ISSN:  0933-3657     ISO Abbreviation:  Artif Intell Med     Publication Date:    2002 Sep-Oct
Date Detail:
Created Date:  2002-09-17     Completed Date:  2002-10-23     Revised Date:  2007-11-14    
Medline Journal Info:
Nlm Unique ID:  8915031     Medline TA:  Artif Intell Med     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  55-68     Citation Subset:  IM    
Affiliation:
College of Staten Island, City University of New York, 2800 Victory Boulevard, Staten Island, NY 10314, USA. imberman@postbox.csi.cuny.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Artificial Intelligence
Craniocerebral Trauma / radiography*
Databases, Factual
Humans
Information Storage and Retrieval*
Sensitivity and Specificity
Tomography, X-Ray Computed*
Grant Support
ID/Acronym/Agency:
P30 EY02377/EY/NEI NIH HHS

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


Previous Document:  Data mining a diabetic data warehouse.
Next Document:  Analysis of respiratory pressure-volume curves in intensive care medicine using inductive machine le...