Abstract: Objective To construct and validate a nomogram model for predicting the relatively long⁃term survival in patients with metastatic breast cancer based on the SEER database. Methods The clinicopathological data of patients with metastatic breast cancer from 2010 to 2015 in SEER database were randomly divided into a training set and a validation set in a 7∶3 ratio. Univariable and multivariable logistic regression analyses were performed and the nomogram model was constructed in the training set. The receiver operating characteristic (ROC) curve, calibration curve, and clinical decision curve were plotted for both the training and validation sets to evaluate the efficacy of the model. Results A total of 6,515 eligible patients with metastatic breast cancer were included, with 4,560 patients in the training set and 1,955 patients in the validation set. In the training set, 2,229 (48.9%) patients were relatively long⁃term survivors (>24 months), and in the validation set, 970 (49.6%) patients were relatively long⁃term survivors. Multivariable Logistic regression analysis showed that age, marital status, race, histological grade, T stage, N stage, brain metastasis, liver metastasis, lung metastasis, time from initial diagnosis to treatment, estrogen receptor (ER) status, progesterone receptor (PR) status, surgical approach and molecular subtype were all independent factors which could affect the relatively long⁃term survival in patients with metastatic breast cancer (all P<0.05). The AUCs of the nomogram model in the training and validation sets were 0.738 (95%CI: 0.724-0.752) and 0.745 (95%CI: 0.723-0.766), respectively. The calibration curve showed a good consistency between the  predicted outcomes and actual outcomes of the model, and the clinical decision curve showed a high net benefit of the model. Conclusions The nomogram model constructed in this study can predict the relatively long⁃term survival of patients with metastatic breast cancer, providing an auxiliary decision⁃making basis for clinical practice and supporting individualized treatment decisions.

Key words: Metastatic breast cancer')">Metastatic breast cancer, SEER, Nomogram model, Prediction, Survival