Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study

Smear negative pulmonary tuberculosis (SNPT) accounts for 30% of pulmonary tuberculosis cases reported yearly in Brazil. This study aimed to develop a prediction model for SNPT for outpatients in areas with scarce resources. The study enrolled 551 patients with clinical-radiological suspicion of SNP...

Full description

Saved in:

Bibliographic Details
Published in:	BMC public health Vol. 6; no. 1; p. 43
Main Authors:	Mello, Fernanda Carvalho de Queiroz, Bastos, Luiz Gustavo do Valle, Soares, Sérgio Luiz Machado, Rezende, Valéria M C, Conde, Marcus Barreto, Chaisson, Richard E, Kritski, Afrânio Lineu, Ruffino-Netto, Antonio, Werneck, Guilherme Loureiro
Format:	Journal Article
Language:	English
Published:	England BioMed Central Ltd 23-02-2006 BioMed Central BMC
Subjects:	Adult Area Under Curve Brazil Bronchoscopy Cross-Sectional Studies Decision Trees Diagnostic Errors Female Hospitals, University Humans Logistic Models Male Middle Aged Mycobacterium Mycobacterium tuberculosis - isolation & purification Predictive Value of Tests Radiography Risk Assessment ROC Curve Sputum - microbiology Tuberculosis, Pulmonary - diagnostic imaging Tuberculosis, Pulmonary - pathology
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Smear negative pulmonary tuberculosis (SNPT) accounts for 30% of pulmonary tuberculosis cases reported yearly in Brazil. This study aimed to develop a prediction model for SNPT for outpatients in areas with scarce resources. The study enrolled 551 patients with clinical-radiological suspicion of SNPT, in Rio de Janeiro, Brazil. The original data was divided into two equivalent samples for generation and validation of the prediction models. Symptoms, physical signs and chest X-rays were used for constructing logistic regression and classification and regression tree models. From the logistic regression, we generated a clinical and radiological prediction score. The area under the receiver operator characteristic curve, sensitivity, and specificity were used to evaluate the model's performance in both generation and validation samples. It was possible to generate predictive models for SNPT with sensitivity ranging from 64% to 71% and specificity ranging from 58% to 76%. The results suggest that those models might be useful as screening tools for estimating the risk of SNPT, optimizing the utilization of more expensive tests, and avoiding costs of unnecessary anti-tuberculosis treatment. Those models might be cost-effective tools in a health care network with hierarchical distribution of scarce resources.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1471-2458 1471-2458
DOI:	10.1186/1471-2458-6-43