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

de Queiroz Mello, Fernanda Carvalho; do Valle Bastos, Luiz Gustavo; Soares, Sérgio Luiz Machado; Rezende, Valéria M. C.; Conde, Marcus Barreto; Chaisson, Richard E.; Kritski, Afrânio Lineu; Ruffino-Netto, Antonio; Werneck, Guilherme Loureiro
January 2006
BMC Public Health;2006, Vol. 6 Issue 1, p43
Academic Journal
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. Methods: 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. Results: It was possible to generate predictive models for SNPT with sensitivity ranging from 64% to 71% and specificity ranging from 58% to 76%. Conclusion: 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.


Related Articles

  • Call it post-traumatic health cuts syndrome. Cosh, Colby // Alberta Report / Newsmagazine;5/13/96, Vol. 23 Issue 22, p14 

    Reports on the status of Alberta's Capital Health Authority (CHA) in May 1996. Details about the creation of health authorities in Alberta; CHA exceeding its budget and indicating cuts in service would be necessary if further funding is not received; The role of Premier Ralph Klein and Health...

  • STATUS QUO KILLS KENTUCKY NETWORK.  // H&HN: Hospitals & Health Networks;8/20/96, Vol. 70 Issue 16, p47 

    Reports on the closure of health care network, Univa Health Network following changes in Kentucky's health care reform system.

  • Area health info network seeing a sluggish start. Schrimpf, Natalie // Crain's Cleveland Business;10/2/95, Vol. 16 Issue 40, p39 

    Reports on hospitals' reluctance to support the Regional Health Network of Northern Ohio, a community health information network launched in Cleveland in 1994. Network features and benefits; Amount spent to build the network.

  • EDITORIAL. Grazier, Kyle L. // Journal of Healthcare Management;Nov/Dec2005, Vol. 50 Issue 6, p355 

    The article introduces various reports published within the issue, including one by Chip Holmes sharing his perspectives that managers need to acknowledge their own strengths and weaknesses to improve and another by William Cleverley and Sarah Jane Baserman on the differences between...

  • Tracing contacts of TB patients in Malaysia: Costs and practicality. Atif, Muhammad; Sulaiman, Syed Azhar Syed; Shafie, Asrul Akmal; Ali, Irfhan // HealthMed;2013, Vol. 7 Issue 2, p435 

    Background: Tuberculin skin testing (TST) and chest X-ray are the conventional methods adopted for tracing a tuberculosis (TB) suspects. The purpose of the study was to calculate the cost incurred by Penang General Hospital on performing one contact tracing procedure by activity based costing...

  • Treatment Outcome Among the Retreatment Tuberculosis (TB) Patients under RNTCP in Chandigarh, India. SARPAL, SANDEEP SINGH; GOEL, NAVEEN KRISHAN; KUMAR, DINESH; JANMEJA, A. K. // Journal of Clinical & Diagnostic Research;Feb2014, Vol. 8 Issue 2, p53 

    Background: 'RETREATMENT' for Tuberculosis (TB) has long been a neglected area in global TB control. While other components of the Stop TB Strategy have garnered appropriate focus and, increasingly, sufficient resources, issues related to the TB of patients previously treated for tuberculosis...

  • Tuberculosis Outbreak in a Circus: Report of a Cooperative Investigation. Darney, Philip D.; Greene, Joe E. // American Journal of Public Health;Jan1973, Vol. 63 Issue 1, p43 

    This paper presents a case study of the satisfactory results that can be obtained when local health departments communicate and cooperate with each other.

  • Introduction. Willner, Sam // Hygiea Internationalis;2008, Vol. 7 Issue 1, p5 

    The article discusses various reports published within the issue, including one on the use of quantitative survey research in social sciences and another on the modernization of health care and medical science in Turkey in the 20th century.

  • Treatment Default amongst Patients with Tuberculosis in Urban Morocco: Predicting and Explaining Default and Post-Default Sputum Smear and Drug Susceptibility Results. Cherkaoui, Imad; Sabouni, Radia; Ghali, Iraqi; Kizub, Darya; Billioux, Alexander C.; Bennani, Kenza; Bourkadi, Jamal Eddine; Benmamoun, Abderrahmane; Lahlou, Ouafae; Aouad, Rajae El; Dooley, Kelly E. // PLoS ONE;Apr2014, Vol. 9 Issue 4, p1 

    Setting: Public tuberculosis (TB) clinics in urban Morocco. Objective: Explore risk factors for TB treatment default and develop a prediction tool. Assess consequences of default, specifically risk for transmission or development of drug resistance. Design: Case-control study comparing patients...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics