The study developed and validated a nomogram to predict adverse treatment outcomes in patients with pulmonary tuberculosis and diabetes mellitus (PTB-DM). 110 hospitalized patients were included in the retrospective analysis, divided equally into groups with favorable (n=55) and unfavorable (n=55) results. Using LASSO regression, four predictors were selected: age, body mass index (BMI), lung cavity, and glucose-to-lymphocyte ratio (GLR), which the multivariate model confirmed as independent risk factors. The nomogram achieved excellent discrimination with an AUC of 0.885 (95% CI: 0.826–0.944) and a bootstrap-corrected AUC of 0.858. Calibration was good according to the non-significant Hosmer-Lemeshow test (P=0.856). Decision curve analysis showed net clinical benefit across a wide range of risk thresholds. The nomogram integrates these readily available parameters and helps clinicians identify high-risk patients for personalized treatment.