Abstract
Drug-induced liver injury (DILI) frequently complicates anti-tuberculosis (TB) treatment, particularly in regions with a high TB burden. Early pre-treatment identification of patients at elevated risk is essential for timely intervention and safer treatment outcomes. In this retrospective two-center cohort study, we collected baseline data from 2022 to 2024 of 2624 patients admitted to two tertiary hospitals before starting standard drug-susceptible anti-TB therapy (isoniazid, rifampicin, pyrazinamide, ethambutol). Patients were randomly divided into training (n = 1512), internal validation (n = 648), and external validation (n = 564) cohorts. Multivariable logistic regression found DILI predictors, and a pre-treatment risk-forecasting nomogram was built. Model performance was assessed by AUC, calibration plots, and decision curve analysis (DCA). Six baseline predictors emerged: age ≥ 60 years, BMI < 18.5 kg/m(2), alcohol use, extrapulmonary TB, albumin < 35 g/L, and hemoglobin < 110 g/L. The nomogram demonstrated robust discrimination (AUCs: 0.80 training, 0.75 internal validation, 0.77 external validation) and favorable calibration and net clinical benefit on DCA. We developed and externally validated a pre-treatment nomogram for DILI risk in TB patients. By enabling risk stratification before therapy begins, this tool supports personalized monitoring and may enhance treatment safety.