Exploring the predictive value of mammography combined with clinical factors in recurrent metastasis of breast cancer

This study was to construct a radiomics nomogram based on mammography (MG) combined with clinical factors for the prediction of recurrent and metastasis in breast cancer. A total of 762 patients, all diagnosed with pathologically confirmed and undergoing MG examination, was encompassed within this article. These patients were initially diagnosed at the Affiliated Cancer Hospital of Xinjiang Medical University between January 1, 2018, and December 31, 2022, the patients were Randomly divided in a 7:3 ratio into a training set of 534 cases and a validation set of 228 cases. Using the collected data, a combined predictive model was established based on statistical methods. In forecasting the recurrence of metastasis in breast cancer, the combined model (AUC of 0.851 and 0.809 for the training and validation sets, respectively) had a higher predictive performance compared to the clinical model (AUC of 0.757 and 0.753 for the training and validation sets, respectively) and the imaging histology model (AUC of 0.802 and 0.748 for the training and validation sets, respectively).The combined model outperforms the single-modal model in terms of efficacy, which can be used as an important reference for clinically determining the prognosis of breast cancer patients.