RESUMO
OBJECTIVES: To develop a clinical prediction rule (CPR) for the diagnosis of pleural tuberculosis (PT) in patients with pleural exudates in Peru. METHODS: Clinical and laboratory information was collected from patients with exudative pleural effusion attending two reference hospitals in Lima, Peru. Predictive findings associated with PT in a multiple logistic regression model were used to develop the CPR. A definite diagnosis of PT was based on a composite reference standard including bacteriological and/or histological analysis of pleural fluid and pleural biopsy specimens. RESULTS: A total of 238 patients were included in the analysis, of whom 176 had PT. Age, sex, previous contact with a TB patient, presence of lymphadenopathy, and pleural adenosine deaminase (ADA) levels were found to be independently associated with PT. These predictive findings were used to construct a CPR, for which the area under the receiver operating characteristics curve (AUC) was 0.92. The single best cut-off point was a score of ≥60 points, which had a sensitivity of 88%, specificity of 92%, a positive likelihood ratio of 10.9, and a negative likelihood ratio of 0.13. CONCLUSIONS: The CPR is accurate for the diagnosis of PT and could be useful for treatment initiation while avoiding pleural biopsy. A prospective evaluation is needed before its implementation in different settings.