Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
1
pubmed:dateCreated
1991-4-23
pubmed:abstractText
A prototype expert system was developed to study the problems applying expert system technology to radiographic image interpretation. The Radiographic Image Interpretation System (RIIS) was developed on a microcomputer using Turbo Prolog, a low cost implementation of the prolog programming language. The present implementation of RIIS was developed to highlight potential problems in applying expert system technology in the evaluation of radiographic images. It was believed that the evaluation of this prototype expert system should include a large number of users unfamiliar with the program's use as this would probably be the case in clinical use of an image interpretation expert system. At present, the expert system deals with a limited domain of focal bony lesions. Twenty cases of pathologically proven bony lesions of varying difficulty were used to evaluate potential problems in the use of this expert system technology. RIIS, with the 20 sample cases, was presented as an exhibit at the 1987 Radiological Society of North America (RSNA) meeting to evaluate the potential problems with inexperienced users. These results were compared with those of experienced users. When a musculoskeletal radiologist, familiar with the programs use, provided the "proper description," the program averaged the correct diagnosis in the top five 80% of the time. During the program's use at the RSNA meeting, the program selected the correct diagnosis in the top five 22% of the time.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
Feb
pubmed:issn
0897-1889
pubmed:author
pubmed:issnType
Print
pubmed:volume
2
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
21-6
pubmed:dateRevised
2004-11-17
pubmed:meshHeading
pubmed:year
1989
pubmed:articleTitle
Problems in applying expert system technology to radiographic image interpretation.
pubmed:affiliation
Department of Radiology, Cleveland Clinic Foundation, Ohio 44195-5021.
pubmed:publicationType
Journal Article