Prediction of bone metastasis risk of early breast cancer based on nomogram of clinicopathological characteristics and hematological parameters.

Objectives: The purpose of this study was to determine the independent risk factors for bone metastasis in breast cancer and to establish a nomogram to predict the risk of bone metastasis in early stages through clinicopathological characteristics and hematological parameters. Methods: We selected 1042 patients with breast cancer from the database of Shandong Cancer Hospital for retrospective analysis, and determined independent risk factors for bone metastatic breast cancer (BMBC). A BMBC nomogram based on clinicopathological characteristics and hematological parameters was constructed using logistic regression analysis. The performance of the nomograph was evaluated using the receiver operating characteristic (ROC) and calibration curves. The clinical effect of risk stratification was tested using Kaplan-Meier analysis. Results: BMBC patients were found to be at risk for eight independent risk factors based on multivariate analysis: age at diagnosis, lymphovascular invasion, pathological stage, pathological node stage, molecular subtype, platelet count/lymphocyte count, platelet count * neutrophil count/lymphocyte count ratio, Systemic Immunological Inflammation Index, and radiotherapy. The prediction accuracy of the BMBC nomogram was good. In the training set, the area under the ROC curve (AUC) was 0.909, and in the validation set, it was 0.926, which proved that our model had good calibration. The risk stratification system can analyze the risk of relapse in individuals into high- and low-risk groups. Conclusion: The proposed nomogram may predict the possibility of breast cancer bone metastasis, which will help clinicians optimize metastatic breast cancer treatment strategies and monitoring plans to provide patients with better treatment.