Nomogram for predicting overall survival in patients with lung cancer complicated by bone metastasis: a two-center retrospective cohort study

The survival of patients with lung cancer bone metastases (LCBM) has improved considerably, making earlier prognostic models less applicable. This study aimed to develop and validate an updated prognostic nomogram for LCBM patients. This two-center retrospective cohort study included patients diagnosed with LCBM between January 2019 and June 2025. The primary endpoint was overall survival. Prognostic variables were first selected using least absolute shrinkage and selection operator (LASSO) penalized Cox regression with 10-fold cross-validation. The selected variables were subsequently entered into a multivariate Cox proportional hazards regression model to estimate hazard ratios (HRs) and 95% confidence intervals (CIs). A nomogram was constructed and evaluated using time-dependent receiver operating characteristic curves, calibration plots, and decision curve analysis (DCA). Internal validation was performed using1,000-iteration bootstrap resampling. 343 patients with LCBM were included and divided into training ( n = 274) and validation ( n = 69) cohorts. Six independent prognostic factors were identified: female sex (HR 0.74, 95% CI 0.55–0.99), radiotherapy (HR 0.73, 95% CI 0.55–0.98), targeted therapy (HR 0.62, 95% CI 0.45–0.85), spinal metastasis (HR 0.67, 95% CI 0.46–0.98), liver metastasis (HR 1.49, 95% CI 1.01–2.21), and time from lung cancer to BM diagnosis (HR 0.98, 95% CI 0.98–0.99). The nomogram achieved AUC values of 0.79 (1-year), 0.84 (3-year) and 0.87 (5-year) overall survival in the training cohort, and 0.78, 0.91, and 0.98 in the validation cohort respectively, with satisfactory calibration and positive net benefit on DCA. This nomogram demonstrates moderate-to-good discrimination for predicting 1-, 3-, and 5-year overall survival in LCBM patients.