Abstract: Objective  To investigate the risk factors of postoperative depression in patients with breast cancer and to establish a predictive model, thereby providing reference for clinical work. 
Methods   A total of 200 female patients with breast cancer were enrolled in this study. The patients were evaluated by the self-rating depression scale and the family support self-rating scale, and their age, education level, monthly income per capita, type of medical insurance, marital status, tumor stage and mode of operation were recorded. Multivariate Logistic regression analysis was used to determine the risk factors of postoperative depression in patients with breast cancer, and ROC curve was used to evaluate the value of clinical predictive model. 
Results  Multivariate Logistic regression analysis showed that young age, low monthly income per capita, being unmarried/ divorced/widowed were risk factors for postoperative depression in patients with breast cancer, while good family support and early tumor stage were protective factors. The cutoff value of the clinical predictive model was -0.475, and the area under curve was 0.856(95%CI：0.794-0.919). 
Conclusion  The clinical predictive model based on age, monthly income per capita, marital status, family support and tumor stage has good predictive value for postoperative depression in patients with breast cancer.

Key words: breast neoplasms, depression, risk factors