Development and validation of a nomogram for predicting pulmonary embolism in patients with pulmonary tuberculosis

Highlight box

Key findings

• In our study, the area under the receiver operating characteristic curve of the development cohort and validation cohort in the prediction model were 0.903 and 0.821. The calibration curves for the two cohorts showed that the probabilities predicted by the model were very close to the actual probabilities. This indicates that nomogram has significant clinical applications.

What is known and what is new?

• The clinical symptoms of pulmonary embolism (PE) are usually similar to those of respiratory diseases, which makes early clinical diagnosis difficult.

• Our predictive models can better predict the risk of PE in pulmonary tuberculosis (PTB) patients and aid in early clinical identification.

What is the implication, and what should change now?

• The clinical presentation of PTB is clinically difficult to identify early with PE, the developed nomogram performed well in both the predictive development cohort and the validation cohort. Patients with high model scores are more likely to develop PE, and early identification and timely intervention are prognostically helpful.

Publication: Kong H, Sang Y, Pan J, Liang M, Geng Z, Li Y. Development and validation of a nomogram for predicting pulmonary embolism in patients with pulmonary tuberculosis. J Thorac Dis 2025;17(3):1197-1206. doi: 10.21037/jtd-24-1627