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 Citations (Scopus)

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

Fingerprint

lupus erythematosus
Systemic Lupus Erythematosus
Linear Models
Logistic Models
Dogs
prediction
Canidae
dogs
Antinuclear Antibodies
arthritis
Arthritis
Antibody Formation
kidneys
Kidney
antibodies
testing
methodology

ASJC Scopus subject areas

  • veterinary(all)

Cite this

@article{d8f69c765dc245ed8dd55fb014989e38,
title = "Application of the log-linear and logistic regression models in the prediction of systemic lupus erythematosus in the dog.",
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.",
author = "Kass, {P. H.} and Farver, {T. B.} and Strombeck, {D. R.} and Ardans, {A. A.}",
year = "1985",
month = "11",
language = "English (US)",
volume = "46",
pages = "2340--2345",
journal = "American Journal of Veterinary Research",
issn = "0002-9645",
publisher = "American Veterinary Medical Association",
number = "11",

}

TY - JOUR

T1 - Application of the log-linear and logistic regression models in the prediction of systemic lupus erythematosus in the dog.

AU - Kass, P. H.

AU - Farver, T. B.

AU - Strombeck, D. R.

AU - Ardans, A. A.

PY - 1985/11

Y1 - 1985/11

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0022159099&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022159099&partnerID=8YFLogxK

M3 - Article

C2 - 4073644

AN - SCOPUS:0022159099

VL - 46

SP - 2340

EP - 2345

JO - American Journal of Veterinary Research

JF - American Journal of Veterinary Research

SN - 0002-9645

IS - 11

ER -