Development and validation of a prediction model to assess the probability of tuberculous pleural effusion in patients with unexplained pleural effusion.

Differentiating tuberculous pleural effusion (TPE) from non-tuberculosis pleural effusion remains a challenge in clinical practice. This study aimed to develop and externally validate a novel prediction model using the peripheral blood tuberculous infection of T cells spot test (T-SPOT.TB) to assess the probability of TPE in patients with unexplained pleural effusion. Patients with pleural effusion and confirmed etiology were included in this study. A retrospective derivation population was used to develop and internally validate the predictive model. Clinical, radiological, and laboratory features were collected, and important predictors were selected using the least absolute shrinkage and selection operator. The prediction model, presented as a web calculator, was developed using multivariable logistic regression. The predictive performance of the model was evaluated for discrimination and calibration and verified in an independent validation population. The developed prediction model included age, positive T-SPOT.TB result, logarithm of the ratio of mononuclear cells to multiple nuclear cells in pleural effusion (lnRMMPE), and adenosine deaminase in pleural effusion ≥ 40 U/L. The model demonstrated good discrimination [with area under the curve of 0.837 and 0.903, respectively] and calibration (with a Brier score of 0.159 and 0.119, respectively) in both the derivation population and the validation population. Using a cutoff value of 60%, the sensitivity and specificity for identifying TPE were 70% and 88%, respectively, in the derivation population, and 77% and 92%, respectively, in the validation population. A novel predictive model based on T-SPOT.TB was developed and externally validated, demonstrating good diagnostic performance in identifying TPE.