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

• Published in: American journal of veterinary research Vol. 46; no. 11; p. 2340
• Main Authors: Kass, P.H, Farver, T.B, Strombeck, D.R, Ardans, A.A
• Format: Journal Article
• Language: English
• Published: United States 01.11.1985
• Subjects: ANALISIS ESTADISTICO; ANALYSE STATISTIQUE; Animals; CHIEN; DIAGNOSIS; DIAGNOSTIC; DIAGNOSTICO; Dog Diseases - diagnosis; DOGS; ENFERMEDADES SISTEMICAS; FORECASTING; Lupus Erythematosus, Systemic - diagnosis; Lupus Erythematosus, Systemic - veterinary; MALADIE GENERALISEE; MODELE; MODELOS; Models, Biological; PERRO; PREVISION; PRONOSTICO; Regression Analysis; STATISTICAL ANALYSIS; SYSTEMIC DISEASES
• ISSN: 0002-9645; 1943-5681

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.