Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients

Background: Tuberculosis (TB) remains a public health issue worldwide. The lack of specific clinical symptoms to diagnose TB makes the correct decision to admit patients to respiratory isolation a difficult task for the clinician. Isolation of patients without the disease is common and increases health costs. Decision models for the diagnosis of TB in patients attending hospitals can increase the quality of care and decrease costs, without the risk of hospital transmission. We present a predictive model for predicting pulmonary TB in hospitalized patients in a high prevalence area in order to contribute to a more rational use of isolation rooms without increasing the risk of transmission. Methods: Cross sectional study of patients admitted to CFFH from March 2003 to December 2004. A classification and regression tree (CART) model was generated and validated. The area under the ROC curve (AUC), sensitivity, specificity, positive and negative predictive values were used to evaluate the performance of model. Validation of the model was performed with a different sample of patients admitted to the same hospital from January to December 2005. Results: We studied 290 patients admitted with clinical suspicion of TB. Diagnosis was confirmed in 26.5% of them. Pulmonary TB was present in 83.7% of the patients with TB (62.3% with positive sputum smear) and HIV/AIDS was present in 56.9% of patients. The validated CART model showed sensitivity, specificity, positive predictive value and negative predictive value of 60.00%, 76.16%, 33.33%, and 90.55%, respectively. The AUC was 79.70%. Conclusions: The CART model developed for these hospitalized patients with clinical suspicion of TB had fair to good predictive performance for pulmonary TB. The most important variable for prediction of TB diagnosis was chest radiograph results. Prospective validation is still necessary, but our model offer an alternative for decision making in whether to isolate patients with clinical suspicion of TB in tertiary health facilities in countries with limited resources.

Habitação e gestão ambiental em áreas de mananciais: o caso do município de Santo André (SP)

Este artigo tem como objetivo levantar e discutir as ações de gestão ambiental e sua interface com a questão habitacional junto à área administrada pela Subprefeitura de Paranapiacaba e Parque Andreense, Santo André-SP, no biênio 2007-2008. O foco do trabalho é a capacidade política e institucional do município criada para tratar de tais questões. Os métodos usados foram pesquisa documental, bibliográfica e de campo, com entrevista a gestores do município. A pesquisa identificou que o município conta com propostas com grande potencial de contribuição para a melhoria da qualidade ambiental e habitacional na área de mananciais, principalmente por seu caráter de integração entre planejamentos. O estabelecimento de conselhos com participação de várias pastas representa um potencial elemento de integração nas ações desses órgãos, permitindo o compartilhamento de temas pertinentes ao longo do desenvolvimento das agendas de forma contínua. Quanto à recuperação urbana e ambiental dos loteamentos irregulares, é possível afirmar que os parâmetros urbanísticos e a definição do uso e ocupação do solo estão intimamente relacionados à qualidade ambiental e precisam ser construídos em conjunto por profissionais da área de urbanismo e da área ambiental, e discutidos com a comunidade local. O formato de gestão na área de mananciais, foco deste estudo de caso no município de Santo André, representa um significativo passo na construção da integração entre os sistemas de gerenciamento de recursos hídricos e de planejamento urbano/metropolitano.

Metropolitan and regional health planning: dilemmas of the Pact for Health in the Baixada Santista Metropolitan Area, Sao Paulo State, Brazil

This paper focuses on the relationship between metropolitan and regional health planning based on the processes of regionalization and the Pact for Health in the Baixada Santista Metropolitan Area, Sao Paulo State, Brazil. The method used was a case study in two stages, namely during initial implementation of the Pact for Health (2007) and the Regional Administration Committees (CGR) and in 2010. Municipal and regional health systems managers and the director of the Metropolitan Agency were interviewed, and records were analyzed from ten years of meetings of the Regional Inter-Administration Committee and the Regional Development Council. Four issues emerged: financing and infrastructure; health services utilization; inefficiency of the Regional Health Administration's instruments and decision-making levels; and the relationship between different levels in the Administration. Metropolitan health management remained as an underlying issue, appearing only incidentally or tangentially to regional management. Despite some limitations, the CGR has been legitimized as a space for regional health management.