Autoantibodies combined with systemic inflammation markers for predicting bone metastases in non-small cell lung cancer patients

Objective This study aims to develop and validate a nomogram model that integrates autoantibodies and systemic inflammation markers to predict the risk of bone metastases in patients with non-small cell lung cancer (NSCLC). Additionally, we propose a novel approach for risk stratification and adjunctive assessment of bone metastases in NSCLC patients, aiming to support clinical decision-making. Methods This retrospective study analyzed 323 NSCLC patients treated at the Affiliated Hospital of Southwest Medical University from January 2020 to July 2024. Comprehensive clinical, laboratory, and imaging data were collected. Key predictors included histology, TNM stage, ANA fluorescence patterns, anti-extractable nuclear antigens (anti-ENAs), SIRI, LWR, and anti-AMA-M2. Least absolute shrinkage and selection operator (LASSO) regression was used for feature selection, and variables with non-zero coefficients were incorporated into a nomogram. The model was validated internally using receiver operator characteristic curve (ROC) analysis, calibration curves, and decision curve analysis (DCA). The incremental value of novel biomarkers was assessed using NRI and IDI. Results Seven variables were retained in the final nomogram, including histology, TNM stage, anti-ENAs, SIRI, LWR, anti-AMA-M2, and ANA fluorescence pattern. The nomogram demonstrated good discriminatory ability, with the receiver operating characteristic curve (AUC) of 0.921 (95% CI: 0.887-0.955) in the training cohort and 0.870 (95% CI: 0.795-0.945) in the validation cohort. Calibration plots showed good agreement between predicted and observed outcomes. Decision Curve Analysis (DCA) indicated that the nomogram provided a higher net benefit compared to “treat-all” and “treat-none” strategies across a range of threshold probabilities. The inclusion of novel biomarkers significantly improved the model’s predictive performance, as evidenced by continuous NRI (0.822, P< 0.001) and IDI (0.121, P <0.001). Conclusion The nomogram developed in this study offers a reliable tool for individualized risk prediction of bone metastasis in NSCLC patients. Incorporating autoantibody and inflammation-related biomarkers significantly enhances the predictive performance, which may help in risk stratification and early intervention.