Objective: In the United States, breast cancer is the most common cancer for women, and it alone accounts for 30% of all new cancer diagnoses in women. Considered the complexity of decision on breast cancer therapy decision, we develop a model to predict 5-year overall survival at the time of diagnosis based on demographic and pathological factors, and estimate the potential benefit from different breast cancer treatment regimens for each individual patient. Methods: Using tumor registry data from University of Miami Health System and Jackson Memorial Hospital from 2008 to 2018, 4021 breast cancer patients were selected.

After preliminary screening of data, based on previous research and clinical evidence, univariate and multivariate Cox regression analysis were performed to assess the effect of the potential prognosticators of overall survival. Twelve variables from multivariate Cox model were selected to build the prediction model with adjustment of interaction between predictors. Results: This prediction model based on race/ethnicity, age at diagnosis, smoking status, tumor stage, tumor grade, hormone receptor status, human epidermal growth factor 2, surgery, radiotherapy, chemotherapy, hormone therapy, and immunotherapy had good discrimination and calibration in bootstrap validation set with an C-statistic 0.82, and no significant difference between the predicted and the observed probabilities. Conclusion: We have developed a robust, relatively accurate, and easy-demonstrated tool that is able to predict 5-year overall survival in patients with invasive breast cancer, with reference to indicate the impact of potential treatment on prognosis. This allowed better communication between clinician and individual patient to make joint clinical decision.

Citation Format: Kaicheng Wang, George R. Yang, Jennifer J. Hu, Isildinha M. Reis, Wei Zhao, Stuart Herna. Predicting breast cancer survival outcomes in a tri-racial/ethnic population [abstract]. In: Proceedings of the AACR Virtual Conference: Thirteenth AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2020 Oct 2-4. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2020;29(12 Suppl):Abstract nr PO-046.