Construction and validation of a nomogram for predicting the prognosis of breast cancer patients who received adjuvant therapy: an analysis based on the SEER database.

BACKGROUND

Breast cancer is the most common malignant tumor in women globally. Despite advances in primary treatment, the role of adjuvant therapy in reducing recurrence and improving survival is critical; however, there is a notable lack of tailored prognostic models for patients receiving adjuvant therapy. This study used the Surveillance, Epidemiology, and End Results (SEER) database to develop a prognostic nomogram for breast cancer patients receiving adjuvant therapy.

METHODS

The data of breast cancer patients who received adjuvant therapy after surgery in 2014-2015 were extracted from the SEER database. Univariate Cox regression identified significant prognostic variables that were further refined by least absolute shrinkage and selection operator (LASSO) regression and cross-validation analyses. These variables were incorporated into a multivariate Cox regression analysis to establish the predictive model. This model was visualized and validated using various statistical measures.

RESULTS

A total of 54,960 patients were included in the study, with 38,472 in the training set and 16,488 in the validation set. Age, sex, race, marital status, grade, tumor (T) stage, lymph node (N) stage, subtype, and radiotherapy were found to be significant independent risk factors of 1-, 3-, and 5-year overall survival (OS). The receiver operating characteristic curve area for 1-, 3-, and 5-year OS was >0.76 in both sets. The consistency index values were 0.768 and 0.763 for the training and validation sets, respectively. The calibration curves showed good fit, and the nomogram exhibited substantial clinical utility.

CONCLUSIONS

Incorporating various significant factors, the constructed nomogram was able to effectively predict the prognosis of breast cancer patients who received adjuvant therapy. This nomogram extends understandings of complex prognosis scenarios. In addition, it could enhance personalized treatment plans and assist in patient counseling.