Nomogram model for prediction of pulmonary tuberculosis patients with intestinal tuberculosis.

BACKGROUND: In clinical settings, pulmonary tuberculosis (PTB) patients were often found to have intestinal tuberculosis (ITB). The aim of this study was to construct a predictive model to evaluate the probability of intestinal tuberculosis in patients with pulmonary tuberculosis.

METHODS: The present case-control study retrospectively collected information from 348 patients affected by PTB who received treatment from January 1, 2019 - August 1, 2023 at Changsha Central Hospital. The 348 patients were divided into ITB group and non-ITB group according to the presence or absence of intestinal tuberculosis. logistic regression analysis was performed and a nomogram was established using the selected predictors. Bootstrapping was performed for internal validation.

RESULTS: Five variables [age, abdominal pain, diarrhoea, hemoglobin (HGB), albumin (ALB)] were validated and used to develop a predictive model which showed good discrimination capability [area under the curve (AUC) = 0.856]. The calibration curve demonstrated the best consistency between nomogram predictions and actual observations. In addition, Decision Curve Analysis (DCA) showed that the nomogram model is effective in clinical practice.

CONCLUSIONS: We developed a preliminary predictive model that can help assess the probability of intestinal tuberculosis in pulmonary tuberculosis patients. Its clinical utility requires further validation in multi-center, prospective studies.

CLINICAL TRIAL: Not applicable.