Application of the log-linear and logistic regression models in the prediction of systemic lupus erythematosus in the dog.

Research output: Contribution to journalArticle

12 Scopus citations

Abstract

This study sought to mathematically define canine systemic lupus erythematosus (SLE) by unifying diagnostic criteria proposed by others. Thirty-one cases of canine SLE were selected for modeling when 4 different published schemes agreed on the diagnosis, and 122 controls were selected when a patient's status met no scheme's criteria. The log-linear method showed an association between SLE and polyarthritis, hematologic abnormalities, renal damage, dermatologic disorders, and antinuclear antibody test response (positive). Logistic regression was then used to derive a predictive algorithm that could identify cases and controls with which all published criteria would be in accordance. The final equation correctly classified 93.5% of the affected dogs and 98.4% of the controls. It was concluded that the log-linear and logistic regression models are useful for the diagnosis of clinically similar, but distinguishable, disease states.

Original languageEnglish (US)
Pages (from-to)2340-2345
Number of pages6
JournalAmerican Journal of Veterinary Research
Volume46
Issue number11
StatePublished - Nov 1985

ASJC Scopus subject areas

  • veterinary(all)

Fingerprint Dive into the research topics of 'Application of the log-linear and logistic regression models in the prediction of systemic lupus erythematosus in the dog.'. Together they form a unique fingerprint.

  • Cite this