TY - JOUR
T1 - Comparative analysis of expert and machine-learning methods for classification of body cavity effusions in companion animals
AU - Hotz, Christine S.
AU - Templeton, Steven J.
AU - Christopher, Mary M
PY - 2005/3
Y1 - 2005/3
N2 - A rule-based expert system using CLIPS programming language was created to classify body cavity effusions as transudates, modified transudates, exudates, chylous, and hemorrhagic effusions. The diagnostic accuracy of the rule-based system was compared with that produced by 2 machine-learning methods: Rosetta, a rough sets algorithm and RIPPER, a rule-induction method. Results of 508 body cavity fluid analyses (canine, feline, equine) obtained from the University of California-Davis Veterinary Medical Teaching Hospital computerized patient database were used to test CLIPS and to test and train RIPPER and Rosetta. The CLIPS system, using 17 rules, achieved an accuracy of 93.5% compared with pathologist consensus diagnoses. Rosetta accurately classified 91% of effusions by using 5,479 rules. RIPPER achieved the greatest accuracy (95.5%) using only 10 rules. When the original rules of the CLIPS application were replaced with those of RIPPER, the accuracy rates were identical. These results suggest that both rule-based expert systems and machine-learning methods hold promise for the preliminary classification of body fluids in the clinical laboratory.
AB - A rule-based expert system using CLIPS programming language was created to classify body cavity effusions as transudates, modified transudates, exudates, chylous, and hemorrhagic effusions. The diagnostic accuracy of the rule-based system was compared with that produced by 2 machine-learning methods: Rosetta, a rough sets algorithm and RIPPER, a rule-induction method. Results of 508 body cavity fluid analyses (canine, feline, equine) obtained from the University of California-Davis Veterinary Medical Teaching Hospital computerized patient database were used to test CLIPS and to test and train RIPPER and Rosetta. The CLIPS system, using 17 rules, achieved an accuracy of 93.5% compared with pathologist consensus diagnoses. Rosetta accurately classified 91% of effusions by using 5,479 rules. RIPPER achieved the greatest accuracy (95.5%) using only 10 rules. When the original rules of the CLIPS application were replaced with those of RIPPER, the accuracy rates were identical. These results suggest that both rule-based expert systems and machine-learning methods hold promise for the preliminary classification of body fluids in the clinical laboratory.
KW - Computer
KW - Decision support
KW - Effusion
KW - Expert system
KW - Laboratory information
KW - Machine-learning system
UR - http://www.scopus.com/inward/record.url?scp=15944406501&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=15944406501&partnerID=8YFLogxK
M3 - Article
C2 - 15825497
AN - SCOPUS:15944406501
VL - 17
SP - 158
EP - 164
JO - Journal of Veterinary Diagnostic Investigation
JF - Journal of Veterinary Diagnostic Investigation
SN - 1040-6387
IS - 2
ER -