AN INEXPENSIVE CLINICAL-LABORATORY NOMOGRAM TO PREDICT POST-TREATMENT LUNG DESTRUCTION IN PULMONARY TUBERCULOSIS

Background: Post-treatment lung destruction (LD) impairs quality of life in pulmonary tuberculosis (TB) survivors, yet early risk-stratification tools are lacking. We aimed to develop and internally validate a clinical-laboratory nomogram for predicting LD at completion of standard anti-TB therapy.

Methods: This retrospective cohort study enrolled 205 adult, drug-naïve TB patients from April 2021 to April 2025. LD was defined by follow-up chest CT showing extensive fibrosis, bronchiectasis with volume loss, or parenchymal destruction. Twenty-two baseline demographic, clinical, laboratory and imaging variables were screened. Least-absolute-shrinkage-and-selection-operator (LASSO) regression (10-fold cross-validation) reduced dimensionality, and stepwise Akaike information criterion guided multivariable logistic regression. Model performance was compared with random-forest (RF) and support-vector-machine (SVM) classifiers. Discrimination (area under the receiver-operating characteristic curve, AUC), calibration (bootstrap-corrected curve, Brier score) and clinical utility (decision-curve analysis, DCA) were assessed; 1,000-sample bootstrap provided internal validation.

Results: LD occurred in 61/205 patients (29.8%). Nine predictors—silicosis, drug resistance, symptom-to-treatment delay, lymphocyte count, C-reactive protein, aspartate aminotransferase, γ-glutamyltransferase, albumin, and atelectasis/cavity—constituted the final model. The nomogram demonstrated excellent discrimination (AUC = 0.93, 95% CI 0.897–0.971; optimism-corrected AUC = 0.93) and good calibration (Brier = 0.13). Across risk thresholds of 10–40%, DCA showed a higher net benefit than treat-all or treat-none strategies. Logistic regression was slightly better than RF (AUC = 0.91) and SVM (AUC = 0.92) while retaining interpretability.

Conclusions: An inexpensive, easily applicable nomogram integrating routine clinical and laboratory indices accurately predicts post-treatment LD in TB patients. The tool can support personalized follow-up and timely interventions, warranting external validation in multi-center prospective cohorts.