Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study
<p>Abstract</p> <p>Background</p> <p>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.</p>...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2006-02-01
|
| Series: | BMC Public Health |
| Online Access: | http://www.biomedcentral.com/1471-2458/6/43 |
| _version_ | 1818081056868270080 |
|---|---|
| author | Kritski Afrânio Chaisson Richard E Conde Marcus Rezende Valéria MC Soares Sérgio Bastos Luiz Mello Fernanda Ruffino-Netto Antonio Werneck Guilherme |
| author_facet | Kritski Afrânio Chaisson Richard E Conde Marcus Rezende Valéria MC Soares Sérgio Bastos Luiz Mello Fernanda Ruffino-Netto Antonio Werneck Guilherme |
| author_sort | Kritski Afrânio |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>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.</p> <p>Methods</p> <p>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.</p> <p>Results</p> <p>It was possible to generate predictive models for SNPT with sensitivity ranging from 64% to 71% and specificity ranging from 58% to 76%.</p> <p>Conclusion</p> <p>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.</p> |
| first_indexed | 2024-12-10T19:00:09Z |
| format | Article |
| id | doaj.art-195596f2a1bd43be82ed6267be2f74f4 |
| institution | Directory Open Access Journal |
| issn | 1471-2458 |
| language | English |
| last_indexed | 2024-12-10T19:00:09Z |
| publishDate | 2006-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj.art-195596f2a1bd43be82ed6267be2f74f42022-12-22T01:37:01ZengBMCBMC Public Health1471-24582006-02-01614310.1186/1471-2458-6-43Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional studyKritski AfrânioChaisson Richard EConde MarcusRezende Valéria MCSoares SérgioBastos LuizMello FernandaRuffino-Netto AntonioWerneck Guilherme<p>Abstract</p> <p>Background</p> <p>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.</p> <p>Methods</p> <p>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.</p> <p>Results</p> <p>It was possible to generate predictive models for SNPT with sensitivity ranging from 64% to 71% and specificity ranging from 58% to 76%.</p> <p>Conclusion</p> <p>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.</p>http://www.biomedcentral.com/1471-2458/6/43 |
| spellingShingle | Kritski Afrânio Chaisson Richard E Conde Marcus Rezende Valéria MC Soares Sérgio Bastos Luiz Mello Fernanda Ruffino-Netto Antonio Werneck Guilherme Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study BMC Public Health |
| title | Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study |
| title_full | Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study |
| title_fullStr | Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study |
| title_full_unstemmed | Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study |
| title_short | Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study |
| title_sort | predicting smear negative pulmonary tuberculosis with classification trees and logistic regression a cross sectional study |
| url | http://www.biomedcentral.com/1471-2458/6/43 |
| work_keys_str_mv | AT kritskiafranio predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT chaissonricharde predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT condemarcus predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT rezendevaleriamc predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT soaressergio predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT bastosluiz predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT mellofernanda predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT ruffinonettoantonio predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy AT werneckguilherme predictingsmearnegativepulmonarytuberculosiswithclassificationtreesandlogisticregressionacrosssectionalstudy |