2006
DOI: 10.1186/1471-2458-6-43
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: Background: 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.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

2
55
0
4

Year Published

2009
2009
2024
2024

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 63 publications
(61 citation statements)
references
References 20 publications
(17 reference statements)
2
55
0
4
Order By: Relevance
“…progressive weight loss) were also absent. 1,2,23,24 These results suggest that IGRA may have a role to assist management of hospitalized patients suspected of active PTB, in conjunction with existing diagnostic modalities, through risk stratification and the identification of 'non-PTB' cases.…”
Section: Discussionmentioning
confidence: 93%
“…progressive weight loss) were also absent. 1,2,23,24 These results suggest that IGRA may have a role to assist management of hospitalized patients suspected of active PTB, in conjunction with existing diagnostic modalities, through risk stratification and the identification of 'non-PTB' cases.…”
Section: Discussionmentioning
confidence: 93%
“…It may therefore be useful in cases with no bacteriological confi rmation, which would eliminate the possibility of patients receiving nonspecifi c treatments. Around 30% of suspected TB cases are treated in an empirical manner without bacteriological confi rmation based on a set of clinical, epidemiological, and laboratory criteria or on radiological evaluation (41) .…”
Section: Discussionmentioning
confidence: 99%
“…Among statistical models that have been used to assist medical procedures, one can enumerate Bayesian networks, multivariate logistic regression, neural networks (El-Solh et al, 1999) and classification trees (Mello, 2006). Artificial Neural Network (ANN) is a biological inspired intelligence model, capable to learn through examples and to generalize, i.e.…”
Section: Neural Networkmentioning
confidence: 99%